TWI760710B - Recognition and collection device for recyclable containers, and recognition method thereof - Google Patents

Abstract

A recognition and collection device for recyclable containers is provided, which may include a first image capturing module, a second image capturing module, at least one sorting mechanism, a processor and a controller. The first and the second image capturing modules may capture the neck image and the bottom image of a container. The sorting mechanism may be connected to a plurality of storage boxes. The processor may analyze the neck image to determine whether the neck of the container is conical to generate a first analysis result, analyze the bottom image to determine whether the bottom of the container is circular to generate a second analysis result, analyze the bottom image to determine whether the bottom of the container is transparent to generate a third analysis result, and generate a control signal according to these analysis results. The controller controls the sorting mechanism to transport the container to the corresponding storage box according to the control signal.

Description

Civil life container identification and recycling device and identification method thereof

The present invention relates to an identification and recycling device for civilian containers, in particular to an identification and recycling device for civilian containers using an image identification mechanism. The present invention also relates to an identification method for the identification and recovery device for the livelihood container.

At present, most of the recycling and sorting of livelihood containers is still performed manually; however, since most developed countries are facing a serious population aging problem, the labor force in these countries is gradually becoming insufficient, so people's livelihood is performed manually. Container recycling and sorting can no longer meet future needs.

In order to solve the above problems, a variety of KIOSK civilian container automatic sorting devices have been developed for automatic sorting and recycling of civilian containers. There are mainly two classification modes adopted by these automatic classification devices for civilian containers, namely barcode scanning mode and image recognition + weight sensing mode.

The barcode scanning mode requires a barcode scanner to scan the barcode of the container. This mode not only has a slow recognition speed (about 4 seconds/each), but also the label film of the container cannot be removed in advance; It also needs to be removed manually, which cannot achieve the purpose of simplifying the recycling process.

Image recognition + weight perception mode can achieve a high recognition speed (about 1 second/each), but if the container label film is damaged, it cannot be recognized, and new products can be effectively recognized if the database needs to be updated in advance. This mode cannot meet the needs of practical applications.

In addition, the training mechanism and identification mechanism of some of the existing automatic sorting devices for recycling containers for people's livelihood are too complicated, and additional training equipment and operating equipment are required, which greatly increases the manufacturing cost and is not conducive to product promotion.

The main purpose of the present invention is to provide a livelihood container identification and recovery device and an identification method thereof, so as to solve the problems that the existing civilian livelihood container recovery automatic sorting device cannot simplify the recovery process, cannot meet the needs of practical applications and the manufacturing cost is too high.

According to a first embodiment of the present invention, an identification and recycling device for household containers is provided, which includes a first image capturing module, a second image capturing module, at least one sorting mechanism, a processor and a controller. The first image capturing module and the second image capturing module capture images of the neck and bottom of the container, respectively. The sorting mechanism is connected to the plurality of storage tanks. The processor analyzes the neck image to determine whether the neck of the container is tapered and generates a first analysis result, and analyzes the bottom image to determine whether the bottom of the container is circular and generates a second analysis result, and then analyzes the bottom image to determine the container Whether the bottom is transparent and generates a third analysis result, and generates a control signal according to the analysis results. The controller controls the sorting mechanism to transport the container to the corresponding storage tank according to the control signal.

In one embodiment, the present invention can analyze and generate a fourth analysis result according to structural features of the bottom of the container, such as point or line structural features.

According to a second embodiment of the present invention, a method for identifying a livelihood container is further provided, which includes the following steps: capturing an image of the neck of the container; capturing an image of the bottom of the container; analyzing the image of the neck to determine whether the neck of the container is a cone shape and generate a first analysis result; analyze the bottom image to determine whether the bottom of the container is circular and generate a second analysis result; analyze the bottom image to determine whether the bottom of the container is transparent and generate a third analysis result; and according to the first analysis The result, the second analysis result, and the third analysis result determine the type of the container.

In one embodiment, the present invention can analyze and generate a fourth analysis result according to structural features of the bottom of the container, such as point or line structural features.

According to a third embodiment of the present invention, there is further provided a civilian container identification and recycling device, which includes a sorting channel, at least one sorting mechanism, a first image capture module, a second image capture module, a processor and a control device. The sorting mechanism includes a first solenoid valve group, a second solenoid valve group and a sorting channel. The sorting channel includes a first channel, a second channel and a central channel; the first channel and the second channel are respectively connected with a plurality of storage tanks, and the central channel is respectively connected with the first channel and the second channel and is used for placing containers. The first solenoid valve group includes a plurality of first solenoid valves, and the second solenoid valve group includes a plurality of second solenoid valves, the first solenoid valves and the second solenoid valves are respectively disposed in the first channel and the second channel on the channel port. The first image capturing module captures the neck image of the container. The second image capturing module captures the bottom image of the container. The processor analyzes the neck image and bottom image, transparency, and structural features to generate control signals. The controller controls the first solenoid valve group or the second solenoid valve group to open the first channel or the second channel according to the control signal, so as to transport the container to the corresponding storage tank.

Based on the above, according to the identification and recovery device of the people's livelihood container and the identification method thereof of the present invention, it can have one or more of the following advantages:

(1) The people's livelihood container identification and recycling device of the present invention completes the classification and recycling of the people's livelihood containers by means of human-machine cooperation, so it can effectively reduce the manpower required for the recovery and classification of the people's livelihood containers, so that the people's livelihood container identification and recycling device can better meet the future needs. .

(2) The identification and recycling device of the livelihood container of the present invention adopts the image recognition method to identify the characteristic information of the bottle body and/or the characteristic information of the bottle bottom of the container, so that a faster identification speed can be achieved, and thus the recycling process can be effectively simplified.

(3) The image recognition program of the civil container identification and recycling device of the present invention adopts a simple and accurate identification logic; compared with the existing automatic sorting device for civil container recycling, the civil container identification and recycling device of the present invention does not require a complex training mechanism, and also There is no need for additional training equipment and operating equipment, so the manufacturing cost of the civilian container identification and recycling device can be greatly reduced.

The following will refer to the relevant drawings to describe the embodiments of the identification and recovery device for civil life containers and the method for identifying the same according to the present invention. For the sake of clarity and convenience in the description of the drawings, the dimensions and proportions of the components in the drawings may be exaggerated. or rendered in a reduced size. In the following description and/or claims, when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present; When an element is "directly connected" or "directly coupled" to another element, there are no intervening elements present, and other words used to describe the relationship between the elements or layers should be interpreted in the same fashion. For ease of understanding, the same elements in the following embodiments are marked with the same symbols for description.

Please refer to FIG. 1 , which is a block diagram of an apparatus 1 for identifying and recycling livelihood containers according to the first embodiment of the present invention. As shown in the figure, the apparatus 1 for identifying and recycling livelihood containers includes a first image capturing module 11, a second image capturing module 12, a processor 13, a controller 14, a first sorting mechanism 3a and a second sorting mechanism 3b.

The first sorting mechanism 3a and the second sorting mechanism 3b can be respectively connected to a plurality of storage tanks; the first sorting mechanism 3a has a recovery port 1331A, and the second sorting mechanism 3b has a recovery port 1331B. The user can place a container to be identified on the first sorting mechanism 3a or the second sorting mechanism 3b through the recovery port 1331A or 1331B to perform subsequent image identification procedures. This container can be a general recyclable container, including but not limited to polyvinyl chloride (PVC) containers (for mineral water and various beverage bottles), polyethylene (PE) containers (for milk, coffee and various beverages) plastic bottles), polyethylene terephthalate (PET) containers (bottlenecks for mineral water and various beverages), metal containers (such as iron cans, aluminum cans, etc.) or carton containers (Tetra Pak) and many more. In this embodiment, the first sorting mechanism 3a is used for recycling metal containers and carton containers, so the recycling port 1331A is marked for recycling metal containers and carton containers, and the recycled metal containers and carton containers are sorted by the first sorting The sorting mechanism 3a is sorted and stored in different storage tanks; the second sorting mechanism 3b is used for recycling PET containers and PE containers, and the recycling port 1331B is marked for recycling PET containers and PE containers, and recycled PET containers and PE containers. After being sorted by the second sorting mechanism 3b, they are also stored in different storage tanks.

In another embodiment, the metal container and the carton container may exist in the same storage tank, and the PET container and the PE container may also exist in the same storage tank.

For example, in another embodiment, the first sorting mechanism 3a can also sort metal containers and carton containers, while the second sorting mechanism 3b can sort PET containers and PVC containers.

The first image capturing module 11 captures the neck image M1 of the container, and the second image capturing module 12 captures the bottom image M2 of the container. In one embodiment, the first image capturing module 11 and the second image capturing module 12 may be cameras, video cameras or other similar components.

The processor 13 analyzes the neck image M1 to determine whether the neck of the container is tapered and generates a first analysis result A1. At the same time, the processor 13 analyzes the bottom image M2 to determine whether the bottom of the container is circular and generates a second analysis result A2. Next, the processor 13 analyzes the bottom image M2 to determine whether the bottom of the container is transparent and generates a third analysis result A3. Then, the processor 13 analyzes the bottom image M2 to determine whether the bottom of the container contains structural features and generates a fourth analysis result A4; wherein the structural features can be one or more of point structural features and line structural features. In one embodiment, the processor 13 may be a central processing unit (CPU), a microcontroller (MCU), or other similar elements. In one embodiment, the processor 13 may analyze the neck image M1 and the bottom image M2 through an automatic optical inspection (AOI) technique to generate the above-mentioned analysis results A1 to A4, but not limited thereto. In another embodiment, the processor 13 can also analyze the neck image M1 and the bottom image M2 through other existing image analysis techniques to generate the above-mentioned analysis results A1 - A4 .

Finally, the processor 13 can generate an identification result according to the first analysis result A1, the second analysis result A2, the third analysis result A3 and the fourth analysis result A4, and determine the type of the container according to the identification result and generate the corresponding control signal C , and transmits the control signal C to the controller 14 . The controller 14 controls the first sorting mechanism 3a (or the second sorting mechanism 3b) according to the control signal C to transport the containers to the corresponding storage tanks. In one embodiment, the controller 14 may also be a central processing unit (CPU), microcontroller (MCU), or other similar elements.

Because different livelihood containers have different structural characteristics. For example, a PVC container has a tapered neck while the bottom is transparent and has no structural features; a PET container has a tapered neck and an opaque bottom with dotted features; a PE container may have a tapered neck or Not tapered, but opaque at the bottom with a line structure feature; carton containers with non-tapered necks and opaque bottoms; metal containers with necks that may or may not be tapered, with opaque bottoms and no Structure. Therefore, the people's livelihood container identification and recycling device 1 adopts the image identification method to analyze the neck image M1 and the bottom image M2 of the container respectively, and judge the shape of the neck of the container, the shape of the bottom of the container and the transparency of the bottom of the container in sequence respectively. Identify the type of container. If the above three stages are still unable to determine the type of the container, the livelihood container identification and recovery device 1 further determines the structural characteristics of the bottom of the container to achieve a better identification effect.

For example, when the first analysis result A1 shows that the neck of the container is tapered, the second analysis result A2 shows that the bottom of the container is circular, the third analysis result A3 shows that the bottom of the container is transparent, and the fourth analysis result A4 shows that the container is transparent If the bottom has no structural features, the processor 13 determines that the container is a PVC container.

For example, when the first analysis result A1 shows that the neck of the container is tapered, the second analysis result A2 shows that the bottom of the container is circular, the third analysis result A3 shows that the bottom of the container is opaque, and the fourth analysis result A4 shows that the bottom of the container is opaque. The bottom has a line structure, and the processor 13 determines that the container is a PE container. However, if the fourth analysis result A4 shows that the bottom of the container has no structural features, the processor 13 determines that the container is a metal container, such as a metal can.

For example, when the first analysis result A1 shows that the neck of the container is conical, the second analysis result A2 shows that the bottom of the container is not circular, the third analysis result A3 shows that the bottom of the container is transparent, and the fourth analysis result A4 shows that the container is transparent The bottom has a point structure feature, and the processor 13 determines that the container is a PET container. However, if the fourth analysis result A4 shows that the bottom of the container has no structural features, the processor 13 determines that the container is a PVC container.

For example, when the first analysis result A1 shows that the neck of the container is not conical, the second analysis result A2 shows that the bottom of the container is round, the third analysis result A3 shows that the bottom of the container is opaque, and the fourth analysis result A4 shows that the container is not transparent. The bottom has a line structure, and the processor 13 determines that the container is a PE container. However, if the fourth analysis result A4 shows that the bottom of the container has no structural features, the processor 13 determines that the container is a metal container, such as a metal can.

For example, when the first analysis result A1 shows that the neck of the container is not conical, the second analysis result A2 shows that the bottom of the container is not circular, and the third analysis result A3 shows that the bottom of the container is opaque, the processor 13 determines that the container is Carton containers, such as Leli packs, etc.

If the processor 13 cannot identify the type of the container, the processor 13 generates a control signal C to control the first sorting mechanism 3a or the first sorting mechanism 3b to push the container out of the recovery port. For example, when the first analysis result A1 shows that the neck of the container is conical, the second analysis result A2 shows that the bottom of the container is not circular, and the third analysis result A3 shows that the bottom of the container is opaque, the processor 13 determines the type of the container Unrecognized.

For example, when the first analysis result A1 shows that the neck of the container is not conical, the second analysis result A2 shows that the bottom of the container is circular, and the third analysis result A3 shows that the bottom of the container is transparent, the processor 13 determines the type of the container Unrecognized.

For example, when the first analysis result A1 shows that the neck of the container is not conical, the second analysis result A2 shows that the bottom of the container is not circular, and the third analysis result A3 shows that the bottom of the container is transparent, the processor 13 determines that the container is Type not recognized.

For example, when the user wants to discard a metal container, the user can judge that the recycling port 1331A is used for recycling the metal container according to the indication, and place the metal container on the first sorting mechanism 3a through the recycling port 1331A. Next, the processor 13 performs the above-mentioned image recognition mechanism to recognize the appearance of the container, and controls the upper 3a of the first sorting mechanism to transport the metal container to the storage tank for storing the metal container. When the user wants to discard a carton container, the carton container can be placed on the first sorting mechanism 3a through the recovery port 1331A, and the processor 13 controls the first sorting mechanism 3a to transport the carton container to the storage paper. Storage slot for box containers. If the user wants to discard a PET container but throws the PET container into the recycling port 1331A by mistake, the processor 13 determines that the PET container does not belong to the recycling target of the first sorting mechanism 3a, so the PET container will not be recycled.

Similarly, when the user wants to discard a PET container, the user can judge that the recycling port 1331B is used for recycling the PET container according to the label, and place the PET container on the second sorting mechanism 3b through the recycling port 1331B. Next, the processor 13 performs the above-mentioned image recognition mechanism to recognize the appearance of the container, and controls the upper 3b of the second sorting mechanism to transport the PET container to the storage tank for storing the PET container. When the user wants to discard a PE container, he can place the PE container on the second sorting mechanism 3b through the recovery port 1331B, and the processor 13 controls the second sorting mechanism 3b to transport the PE container to the storage for storing the PE container. groove. If the user wants to discard a metal container but throws the metal container into the recycling port 1331B by mistake, the processor 13 determines that the metal container does not belong to the recycling target of the second sorting mechanism 3b, so the metal container will not be recycled.

The people's livelihood container identification and recycling device 1 can first put the container into the corresponding recycling port (1331A or 1331B) by the user through human-machine cooperation, and then classify and recycle the container through the above-mentioned mechanism. The above-mentioned human-machine cooperation method can effectively The manpower required for the recycling and sorting of the livelihood containers is reduced, and the manufacturing cost of the identification and recycling device 1 for the livelihood containers can be reduced.

Through the above-mentioned mechanism, the people's livelihood container identification and recycling device 1 can identify the appearance of the container through the man-machine cooperation and image recognition method to determine the type of the container, so as to classify and recycle the container, so it can effectively reduce the collection and classification of the people's livelihood container. The manpower required makes the livelihood container identification and recycling device more suitable for future needs.

Certainly, each element of the civil life container identification and recovery device 1 in this embodiment, the synergistic relationship of these elements, and the identification method are all examples, and are not limited thereto.

Please refer to FIG. 2 , which is a flowchart of a method for identifying a livelihood container according to the first embodiment of the present invention. As shown in the figure, the identification method adopted by the livelihood container identification and recycling device 1 of this embodiment includes the following steps:

Step S21: Capture the neck image of the container.

Step S22: Capture the bottom image of the container.

Step S23: Analyze the neck image to determine whether the neck of the container is tapered and generate a first analysis result.

Step S24: Analyze the bottom image to determine whether the bottom of the container is circular and generate a second analysis result.

Step S25: Analyze the bottom image to determine whether the bottom of the container is transparent and generate a third analysis result.

Step S26: Analyze the bottom image to determine whether the bottom of the container contains structural features and generate a fourth analysis result.

Step 27: Determine the type of the container or the non-recyclable object according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result.

Of course, each step of the method for identifying a livelihood container in this embodiment is for illustration only, and the sequence and yield of these steps can be adjusted according to requirements, but not limited thereto.

Please refer to FIG. 3 , which is a perspective view of the apparatus 2 for identifying and recycling livelihood containers according to the second embodiment of the present invention. As shown in FIG. 3 , the apparatus 2 for recycling and identifying livelihood containers in this embodiment includes a box body 20 , a server host 21 , a plurality of storage tanks 22 a , 22 b , 22 c , 22 d and at least one sorting mechanism. For example, in the present embodiment, the apparatus 2 for recycling and identifying the livelihood containers may have two sorting mechanisms 3a, 3b. The first sorting mechanism 3a on the left has a recovery port 3331A, and the second sorting mechanism 3b on the right has a recovery port 3331B. The server host 21 includes a processor, a controller, and the like. In this embodiment, the storage tanks may include a PET container storage tank 22a, a PE container storage tank 22b, a metal container (iron aluminum can) storage tank 22c, and a carton container (Tetra Pak) storage tank 22d.

Please refer to FIG. 4 and FIG. 5 , which are a perspective view and a side view of the sorting mechanism of the people's livelihood container identification and recycling device 2 according to the second embodiment of the present invention. The structure of the first sorting mechanism 3a on the left side is the same as that of the second sorting mechanism 3b on the right side, so Figs. 4 and 5 illustrate the structure of the first sorting mechanism 3a on the left side as an example. As shown in FIG. 4 , the first sorting mechanism 3 a of this embodiment includes a first image capturing module 31 , a second image capturing module 32 , a sorting channel 33 and a sorter 34 .

The sorter 34 includes a first solenoid valve group and a second solenoid valve group; the first solenoid valve group includes a plurality of first solenoid valves 341 , and the first solenoid valve group includes a plurality of second solenoid valves 342 .

The sorting channel 33 includes a first channel 331 , a second channel 332 and a central channel 333 . The central channel 333 is used for placing a container T to be identified, and the first channel 331 and the second channel 332 communicate with the central channel 333 . The first solenoid valves 341 and the second solenoid valves 342 are respectively disposed on the channel ports of the first channel 331 and the second channel 332 to control the opening and closing of the first channel 331 and the second channel 332 . The first channel 331 and the second channel 332 of the sorting channel 33 of the first sorting mechanism 3a on the left pass through the PET container storage tank 22a and the PE container storage tank 22b respectively; and the second sorting mechanism 3b on the right The first channel 331 and the second channel 332 of the sorting channel 33 respectively pass through the metal container storage slot 22c and the carton container storage slot 22d.

As shown in FIG. 5, there is an included angle θ1 between the first channel 331 and the vertical plane V, and an included angle θ2 between the second channel 332 and the vertical plane V, and the included angle θ1 can be equal to the included angle θ2; in this embodiment Among them, the included angle θ1 and the included angle θ2 are about 45°, but not limited thereto. Through the above structure, after the first solenoid valve group or the second solenoid valve group on the first channel 331 or the second channel 332 is opened, the container T can be directly dropped from the first channel 331 or the second channel 332 to the corresponding storage tank.

As shown in FIG. 4 , the central channel 333 has a recovery port 3331A, a side window 3332 , a rear window 3333 , a first arm 3334 and a second arm 3335 . The user can place the container T in the central channel 333 through the recovery port 3331A for identification. The first arm 3334 extends to one side of the central channel 333, and the first image capture module 31 is disposed on the first arm 3334 and faces the side window 3332, so that the first image capture module 31 can capture An image of the neck of the container T placed in the central channel 333 is taken. The second arm 3335 extends to the rear of the central channel 333, and the second image capture module 32 is disposed on the second arm 3335 and faces the rear window 3333, so that the second image capture module 32 can capture Bottom image of the container T placed in the central channel 333.

Through the above structure, the server host 21 (as shown in FIG. 4 ) can be identified according to the identification process of the neck image and the bottom image captured by the first image capturing module 31 and the second image capturing module 32 . Identify the container T, and control the first sorting mechanism 3a or the second sorting mechanism 3b to transport the container T to the corresponding storage tank.

Please refer to FIG. 6A and FIG. 6B , which are the first schematic diagram and the second schematic diagram of the operation state of the sorting mechanism of the civil container identification and recycling device 2 according to the second embodiment of the present invention.

In one embodiment, the livelihood container identification and recycling device 2 can paste the label text and/or graphics of the recyclable container on the recycling ports 3331A and 3331B to indicate the recycling targets of the recycling ports 3331A and 3331B, respectively. As shown in FIG. 6A, when the container T is a PET bottle and the user places the container T into the central channel 333 of the first sorting mechanism 3a on the left side, the first image capturing module 31 and the second image capturing module 31 The capturing module 32 can capture the neck image and the bottom image of the container T, respectively. The servo host 21 can execute the image recognition mechanism of the foregoing embodiment to determine that the container T is a PET container, and control the first solenoid valves 341 to open the first channel 331 to drop the container T into the PET container storage tank 22a.

As shown in FIG. 6B , when the container T is a PE bottle and the user places the container T into the center channel 333 of the sorting channel 33 of the first sorting mechanism 3a on the left side, the first image capturing module 31 And the second image capturing module 32 can capture the neck image and bottom image of the container T respectively. The server host 21 can execute the image recognition mechanism of the foregoing embodiment to determine that the container T is a PE container, and control the second solenoid valves 342 to open the second channel 332 to drop the container T into the PE container storage tank 22b.

Please refer to FIG. 7 and FIG. 8 , which are a perspective view and a schematic diagram of a working state of the sorting mechanism of the civil container identification and recycling device 2 according to the second embodiment of the present invention. FIG. 7 and FIG. 8 illustrate another structure of the sorting mechanism of the civilian-living container identification and recovery device 2 . As shown in FIG. 7 , the sorter 34 of the first sorting mechanism 3 a may further include a third solenoid valve 343 and a bottom plate 344 .

The third solenoid valve 343 is disposed on the second arm 3335 and connected to the bottom plate 344 to control the position of the bottom plate 344, and the bottom plate 344 is disposed in the central channel 333 and covers the rear window 3333 of the central channel 333 and faces the container T the end of. In this embodiment, the bottom plate 344 can include a frame and a transparent plate body, and the transparent plate body is arranged in the frame, so that the central part of the bottom plate 344 is still transparent, so the second image capturing module 32 can still capture the image Bottom image of container T. In another embodiment, the bottom plate 344 can also be a hollow frame, so that the second image capturing module 32 can still capture the bottom image of the container T. The structure of the bottom plate 344 can be designed according to actual requirements, and the present invention is not limited thereto.

As shown in FIG. 8, when the user places the container T into the central channel 333 of the first sorting mechanism 3a on the left side, the first image capturing module 31 and the second image capturing module 32 can be respectively Capture the neck image and bottom image of the container T. If the servo host 21 executes the image recognition mechanism of the aforementioned embodiment and determines that the container T cannot be identified or the container T does not belong to the recycling target of the first sorting mechanism 3a on the left side, the servo host 21 controls the third solenoid valve 344 to send the bottom plate 344 to the recycling target. The direction of the recovery port 3331A moves to push the container T, so that the top of the container T is exposed to the recovery port 3331A, thereby reminding the user to retrieve the container.

In addition, the recycling and identification device 2 of the livelihood container may further include a plurality of extrusion mechanisms (not shown in the figure), which may be respectively connected with the first channels 331 and the second channels 332 and disposed in the first channels 331 and the second channels 332 Between the first channel 331 and the second channels 332 and the storage tanks 22a, 22b, 22c, 22d. The pressing mechanisms can squeeze the container T before the container T drops into the storage tanks 22a, 22b, 22c, 22d, so as to reduce the volume of the container T.

Of course, each element of the civilian-living container identification and recovery device 2 in this embodiment, the synergistic relationship of these elements, and the identification method are all examples, and are not limited thereto.

Please refer to Fig. 9A, Fig. 9B and Fig. 9C, which are a flowchart of the method for identifying a livelihood container and a schematic diagram of Hough circle transform according to the second embodiment of the present invention, and please refer to Fig. 11A to Fig. 11G at the same time Figures; Figures 11A to 11G are schematic diagrams of the bottle neck features and bottle bottom features of various containers. Figures 9A and 9B illustrate the identification logic of the first sorting mechanism 3a on the left side of the livelihood container identification and recovery device 2 of the foregoing embodiment, which may include the following steps:

Step S30: Determine whether the neck of the container is tapered? If yes, go to Step S31; if not, go to Step S41. In this step, the servo host 21 (processor) can perform image analysis according to the appearance of the neck of the container, and determine whether the neck of the container is tapered by calculating the ratio of the upper bottom and the lower bottom of the neck of the container, and generate The first analysis result A1. Wherein, if the ratio of the upper bottom to the lower bottom of the neck of the container has a width range value of less than 0.66 (as shown in Figure 11A), the processor 13 has a tapered neck of the container; When the lower base is greater than 0.66, the neck of the container of the processor 13 is not tapered; of course, the above judgment method is an example, and the present invention is not limited thereto.

Step S31: Determine whether the bottom of the container is circular? If yes, go to Step S32a; if not, go to Step S32b. In this step, the server host 21 (processor) can perform Hough circle transformation and voting mechanism on the bottom image M2 of the container to generate a cumulative coordinate plane, and then according to the cumulative weight (please the inventor add the definitions of four nouns: text or Any formula can be used. The prior art also needs to be provided.) Determine whether the bottom of the container is circular (as shown in Figure 11B) or non-circular (as shown in Figure 11C), and generate a second analysis result A2. In more detail, the Hough circle transform is a feature extraction method, which has been widely used in various image processing programs. It can find features in an object to determine the shape of the object. The Hough circle transform performs voting (ie voting mechanism) in the parameter space to determine the shape of the object, which is determined by the local maxima (ie cumulative weights) in the accumulated space (ie the accumulated coordinate plane). A circle can be described by three parameters, including the center coordinates (a, b) and the radius r, as shown in the following formula (1):

f((x, y), (a, b, r))=(xa) ² +(yb) ² -r ² =0……………………………………..(1)

Following the method of line detection, a point (x, y) on the image space can be mapped to a circular cone on the three-dimensional parameter space (a, b, r), as shown in Figure 9C; where r1 and r2 is two points on the coordinate axis r. If two points in image space lie on the same circle trajectory, then the two cones in parameter space will intersect at a point (a', b', c'). The use of the accumulator is similar to the Hough transform of line detection. The following is an example of the program fragment of the Hough transform algorithm of circle detection: for(i=0; i>nr; i++)for (j=0; j>nc; j++) { if (edge_image[i] > 0) // This is an edge pixel { x = j; y = i; // populate the accumulator array for(a= 0;a>max_a;a++)for(b=0;b>max_b;b++) //For each circle center,execute: { r = (int) sqrt((x-a)*(x-a) + (y-b)*(y-b)); if ((r>0)&&(r>max_r))accumulator[r][a][b]++; } } }

Since the Hough circle transform is well known to those with ordinary knowledge in the art, it will not be repeated here.

Step S32a: Determine whether the bottom of the container is transparent? If yes, go to Step S33a; if not, go to Step S33b. In this step, the server host 21 (processor) can perform image segmentation to convert the bottom image M2 of the container into a binary image, and compare the binary image with a predetermined critical gray value to determine the bottom of the container Whether it is transparent, and produces the third analysis result A3. Among them, if the bottom image M2 is completely white (as shown in Figure 11D), the server host 21 (processor) determines that the bottom of the container is non-transparent; if the bottom image M2 is mixed with different colors (as shown in Figure 11E) ), the server 21 (processor) judges whether the bottom of the container is transparent or translucent; of course, the above judgment method is an example, and the present invention is not limited thereto.

Step S32b: Determine whether the bottom of the container is transparent? If yes, go to Step S33a; if not, go to Step S50.

Step S33a: It is judged that the container is a PET container. In this step, the servo host 21 (processor) can determine that the PET container is the recycling target of the first sorting mechanism 3a on the left, and control the first sorting mechanism 3a to transport the container to the PET container storage tank 22a.

Step S33b: Determine whether the bottom of the container contains line structure features? If yes, go to Step S34a; if not, go to Step S34b. In this step, the server host 21 (processor) can directly analyze the bottom image M2 of the container to determine whether the bottom of the container has structural features and generate a fourth analysis result A4. Since the servo host 21 (processor) has judged that the neck of the container is conical and the bottom of the container is round and opaque; therefore, in this step, the servo host 21 (processor) judges whether the bottom of the container has a long strip shape Structural features of protrusions (ie, line structural features). If the bottom of the container has a wired structure feature, the server host 21 (processor) determines that the container is a PE container; if the bottom of the container has a wireless structure feature, the server host 21 (processor) determines that the container is a metal container. Since the PE container is manufactured by extrusion hollow forming technology, the bottom of the PE container will have a line structure feature (ie, the parting line, as shown in Figure 11F).

Step S34a: It is judged that the container is a PE container. In this step, the servo host 21 (processor) can determine that the PE container is the recycling target of the first sorting mechanism 3a on the left, and control the first sorting mechanism 3a to transport the container to the PE container storage tank 22b.

Step S34b: It is determined that the container is a non-recycling target. In this step, the server host 21 (processor) can determine that the container is not the recovery target of the first sorting mechanism 3a on the left, and controls the first sorting mechanism 3a to push the container out of the recovery port 3331A, indicating that the container cannot be processed. recycling, thereby reminding the user to retrieve the container.

Step S41: Determine whether the bottom of the container is circular? If yes, go to Step S42a; if not, go to Step S42b.

Step S42a: Determine whether the bottom of the container is transparent? If yes, go to Step S43a; if not, go to Step S43b.

Step S42b: It is determined that the container is a non-recycling target. In this step, the server host 21 (processor) can determine that the container cannot be identified, and generate a corresponding control signal C according to the identification result, and control the first sorting mechanism 3a to push the container out of the recovery port 3331A, indicating that the container cannot be recycled , thereby reminding the user to retrieve the container.

Step S43a: It is judged that the container is a PET container. In this step, the servo host 21 (processor) can determine that the PET container is the recycling target of the first sorting mechanism 3a on the left, and control the first sorting mechanism 3a to transport the container to the PET container storage tank 22a.

Step S43b: Determine whether the bottom of the container contains line structure features? If yes, go to Step S44a; if not, go to Step S44b.

Step S44a: It is judged that the container is a PE container. In this step, the servo host 21 (processor) can determine that the PE container is the recycling target of the first sorting mechanism 3a on the left, and control the first sorting mechanism 3a to transport the container to the PE container storage tank 22b.

Step S44b: It is determined that the container is a non-recycling target. In this step, the server host 21 (processor) can determine that the container is not the recycling target of the first sorting mechanism 3a on the left, and controls the first sorting mechanism 3a to push out the recycling port 3331A, indicating that the container cannot be recycled, Thereby, the user is reminded to retrieve the container.

Step S50: It is determined that the container is a non-recycling target. In this step, the server host 21 (processor) can determine that the container cannot be identified, and generate a corresponding control signal C according to the identification result, and control the first sorting mechanism 3a to push the container out of the recovery port 3331A, indicating that the container cannot be recycled , thereby reminding the user to retrieve the container.

In another embodiment, if the first sorting mechanism 3a is used for recycling PET containers and PVC containers, a step may be added after step S32a and step S32 to determine whether the bottom of the container has structural features and generate a fourth analysis result A4 . Since the servo host 21 (processor) has judged that the neck of the container is conical and the bottom of the container is transparent; therefore, in this step, the servo host 21 (processor) judges whether the bottom of the container is a point-like protrusion (ie, a point-like protrusion). structural features). If the bottom of the container has some structural features, the server host 21 (processor) determines that the container is a PET container. If the bottom of the container has no point structure feature, the server host 21 (processor) determines that the container is a PVC container. Since the PET container is manufactured by injection blow molding, the bottom of the PET container will have some structural features (as shown in Figure 11G).

Please refer to FIG. 10A and FIG. 10B , which are flowcharts of a method for identifying a livelihood container according to the second embodiment of the present invention. Figures 10A and 10B illustrate the identification logic of the second sorting mechanism 3b on the right side of the livelihood container identification and recovery device 2 of the foregoing embodiment, which may include the following steps:

Step S60: Determine whether the neck of the container is tapered? If yes, go to Step S61; if not, go to Step S71.

Step S61: Determine whether the bottom of the container is circular? If yes, go to Step S62a; if not, go to Step S62b.

Step S62a: Determine whether the bottom of the container is transparent? If yes, go to Step S63a; if not, go to Step S63b.

Step S62b: Determine whether the bottom of the container is transparent? If yes, go to Step S63a; if not, go to Step S63c.

Step S63a: It is determined that the container is a non-recycling target. In this step, the server host 21 (processor) can determine that the container is not the recycling target of the second sorting mechanism 3b on the right, and control the second sorting mechanism 3b to push out the recycling port 3331B, indicating that the container cannot be recycled, Thereby, the user is reminded to retrieve the container.

Step S63b: Determine whether the bottom of the container contains line structure features? If yes, go to Step S64a; if not, go to Step S64b.

Step S63c: It is determined that the container is a carton container. In this step, the servo host 21 (processor) can determine that the carton container is the recycling target of the second sorting mechanism 3b on the right, and control the second sorting mechanism 3b to transport the container to the carton container storage slot 22d.

Step S64a: It is determined that the container is a non-recycling target. In this step, the server host 21 (processor) can determine that the container is not the recycling target of the second sorting mechanism 3b on the right, and control the second sorting mechanism 3b to push out the recycling port 3331B, indicating that the container cannot be recycled, Thereby, the user is reminded to retrieve the container.

Step S64b: It is determined that the container is a metal container. In this step, the servo host 21 (processor) can determine that the metal container is the recycling target of the second sorting mechanism 3b on the right, and control the second sorting mechanism 3b to transport the container to the metal container storage tank 22c.

Step S71: Determine whether the bottom of the container is circular? If yes, go to Step S72a; if not, go to Step S72b.

Step S72a: Determine whether the bottom of the container is transparent? If yes, go to Step S73a; if not, go to Step S73b.

Step S72b: Determine whether the bottom of the container is transparent? If yes, go to Step S73c; if not, go to Step S73d.

Step S73a: It is determined that the container is a non-recycling target. In this step, the server host 21 (processor) can determine that the container is not the recycling target of the second sorting mechanism 3b on the right, and control the second sorting mechanism 3b to push out the recycling port 3331B, indicating that the container cannot be recycled, Thereby, the user is reminded to retrieve the container.

Step S73b: Determine whether the bottom of the container contains line structure features? If yes, go to Step S74a; if not, go to Step S74b.

Step S73c: It is determined that the container is a non-recycling target. In this step, the server host 21 (processor) can determine that the container is not the recycling target of the second sorting mechanism 3b on the right, and control the second sorting mechanism 3b to push out the recycling port 3331B, indicating that the container cannot be recycled, Thereby, the user is reminded to retrieve the container.

Step S73d: It is judged that the container is a carton container. In this step, the servo host 21 (processor) can determine that the carton container is the recycling target of the second sorting mechanism 3b on the right, and control the second sorting mechanism 3b to transport the container to the carton container storage slot 22d.

Step S74a: It is determined that the container is a non-recycling target. In this step, the server host 21 (processor) can determine that the container is not the recycling target of the second sorting mechanism 3b on the right, and control the second sorting mechanism 3b to push out the recycling port 3331B, indicating that the container cannot be recycled, Thereby, the user is reminded to retrieve the container.

Step S74b: It is determined that the container is a metal container. In this step, the servo host 21 (processor) can determine that the metal container is the recycling target of the second sorting mechanism 3b on the right, and control the second sorting mechanism 3b to transport the container to the metal container storage tank 22c.

Of course, each step of the method for identifying a livelihood container in this embodiment is for illustration only, and the sequence and yield of these steps can be adjusted according to requirements, but not limited thereto.

To sum up, the identification and recycling device for livelihood containers of the present invention completes the sorting and recycling of livelihood containers by means of human-machine cooperation, so that the manpower required for recycling and sorting of livelihood containers can be effectively reduced, so that the identification and recycling device for livelihood containers is more suitable for the future. demand.

In addition, the identification and recycling device of the livelihood container of the present invention adopts the image recognition method to identify the characteristic information of the bottle body and/or the characteristic information of the bottle bottom of the container, so that a faster identification speed can be achieved, and thus the recycling process can be effectively simplified.

Furthermore, according to the embodiment of the present invention, the image recognition program of the civil container identification and recycling device adopts a simple and accurate identification logic; compared with the existing civil container recycling automatic sorting device, the civil container identification and recycling device of the present invention does not need to be complicated. The training mechanism also does not require additional training equipment and operating equipment, so the manufacturing cost of the identification and recovery devices 1 and 2 for the livelihood containers can be greatly reduced.

It can be seen that the present invention has indeed achieved the desired enhancement effect under the breakthrough of the previous technology, and it is not easy for those who are familiar with the technology to think about it. Yuan has filed a patent application in accordance with the law, and I implore your bureau to approve this invention patent application, so as to encourage creation, and to be grateful.

The foregoing is exemplary rather than limiting. Any other equivalent modifications or changes without departing from the spirit and scope of the present invention should be included in the appended patent application scope.

1, 2: Identification and recycling device for livelihood containers 11, 31: The first image capture module 12, 32: The second image capture module 13: Processor 14: Controller 20: Box 21: Servo host 22a: Metal container storage tank 22b: Carton container storage slot 22c: PET container storage tank 22d: PE container storage tank 3a: First sorting agency 3b: Second sorting agency 33: Sorting channel 331: first channel 332: Second channel 333: Central Passage 1331A, 1331B, 3331A, 3331B: Recovery port 3332: Side Windows 3333: Rear window 3334: First Arm 3335: Second Arm 34: Sorter 341: The first solenoid valve 342: Second solenoid valve 343: The third solenoid valve 344: Bottom Plate T: container M1: Neck Image M2: Bottom image A1: The first analysis result A2: The second analysis result A3: The third analysis result A4: Fourth analysis result C: Control signal S21~S27, S30~S31, S32a/b~S34a/b, S41, S42a/b, S43a/b, S44a/b, S50, S60~S61, S62a/b, S63a/b/c, S64a/b, S71, S72a/b, S73a/b/c/d, S74a/b: step flow V: vertical plane θ1, θ2: included angle

Fig. 1 is a block diagram of the identification and recycling device for civil-use containers according to the first embodiment of the present invention.

Fig. 2 is a flow chart of a method for identifying a livelihood container according to the first embodiment of the present invention.

Fig. 3 is a perspective view of a second embodiment of a civilian container identification and recycling device of the present invention.

Fig. 4 is a perspective view of the sorting mechanism of the identification and recycling device for civil-service containers according to the second embodiment of the present invention.

Fig. 5 is a side view of the sorting mechanism of the identification and recycling device for the livelihood containers according to the second embodiment of the present invention.

Figures 6A and 6B are the first schematic diagram and the second schematic diagram of the operation state of the sorting mechanism of the civil life container identification and recycling device according to the second embodiment of the present invention.

FIG. 7 is a perspective view of the sorting mechanism of the identification and recycling device for the livelihood containers according to the second embodiment of the present invention.

FIG. 8 is a schematic diagram of the operation state of the sorting mechanism of the identification and recycling device for civil containers according to the second embodiment of the present invention.

Figures 9A to 9B are flowcharts of a method for identifying a livelihood container according to the second embodiment of the present invention.

FIG. 9C is a schematic diagram of the Hough circle transform of the method for identifying the livelihood container according to the second embodiment of the present invention.

Figures 10A to 10B are flowcharts of a method for identifying a livelihood container according to the second embodiment of the present invention.

Figures 11A to 11G are schematic diagrams of the bottle neck features and bottle bottom features of various containers.

1: People's livelihood container identification and recycling device

11: The first image capture module

12: The second image capture module

13: Processor

14: Controller

3a: First sorting agency

3b: Second sorting agency

1311A, 1311B: Recycling port

M1: Neck Image

M2: Bottom image

A1: The first analysis result

A2: The second analysis result

A3: The third analysis result

A4: Fourth analysis result

C: Control signal

Claims (35)

A device for identifying and recycling people's livelihood containers, comprising: a first image capturing module for capturing a neck image of a container; a second image capturing module for capturing a bottom image of the container; at least one sorting mechanism is connected with a plurality of storage tanks; a processor that analyzes the neck image to determine whether the neck of the container is tapered and generates a first analysis result, and analyzes the bottom image to determine whether the bottom of the container is circular and generates a second analysis As a result, the bottom image is further analyzed to determine whether the bottom of the container is transparent and a third analysis result is generated, thereby generating a control signal according to the first analysis result, the second analysis result and the third analysis result; and A controller controls the sorting mechanism to deliver the container to the corresponding storage tank according to the control signal. The identification and recycling device for livelihood containers according to claim 1, wherein the processor determines whether the neck of the container is tapered according to a ratio of an upper bottom to a lower bottom of the neck image, and generates the first analysis result . The civilian container identification and recycling device as claimed in claim 1, wherein the processor performs a Hough transform and a voting mechanism on the bottom image to generate a cumulative coordinate plane, and then judges whether the bottom of the container is a circle and produce this second analysis result. The recognizing and recycling device for livelihood containers according to claim 1, wherein the processor performs an image segmentation to convert the bottom image into a binary image, and judges whether the bottom of the container is transparent according to a predetermined critical gray value And generate the third analysis result. The civil container identification and recycling device as claimed in claim 1, wherein the processor further analyzes the bottom image to determine whether the bottom of the container contains a structural feature and generates a fourth analysis result, whereby according to the first analysis result, The second analysis result, the third analysis result and the fourth analysis result generate the control signal. The identification and recycling device for livelihood containers according to claim 5, wherein the structural feature includes one or more of a one-point structural feature and a first-line structural feature. The livelihood container identification and recovery device as claimed in claim 1, wherein the sorting mechanism comprises at least one first solenoid valve and at least one second solenoid valve, and the first solenoid valve and the second solenoid valve are disposed on the second container of the container side. The livelihood container identification and recycling device as claimed in claim 7, wherein the sorting mechanism further comprises at least a third solenoid valve and a bottom plate, the third solenoid valve is connected with the bottom plate to control the position of the bottom plate, and the bottom plate is provided with at the end of the container. The people's livelihood container identification and recycling device as claimed in claim 7, wherein the sorting mechanism further comprises a sorting channel, and the sorting channel includes a first channel, a second channel and a central channel, and the central channel is used for placing In the container, the first channel and the second channel are respectively connected to the storage tanks, and the first solenoid valve and the second solenoid valve are respectively disposed on the channel openings of the first channel and the second channel. The livelihood container identification and recycling device according to claim 9, wherein the central channel has a recycling port, and the container is placed on the central channel through the recycling port. The livelihood container identification and recycling device as claimed in claim 9, wherein the central channel has a side window, a rear window, a first arm and a second arm, and the first image capture module is disposed in the first One arm is on the side window, and the second image capturing module is arranged on the second arm and facing the rear window. A device for identifying and recycling people's livelihood containers, comprising: At least one sorting mechanism includes at least one first solenoid valve and at least one second solenoid valve and a sorting channel, the sorting channel includes a first channel, a second channel and a central channel, the first channel and the second channel is respectively communicated with a plurality of storage tanks, the central channel is used for placing a container, the first solenoid valve and the second solenoid valve are respectively arranged on the channel ports of the first channel and the second channel; a first image capturing module for capturing a neck image of the container; a second image capturing module for capturing a bottom image of the container; a processor that analyzes the neck image and the bottom image to generate a control signal; and A controller controls the first solenoid valve or the second solenoid valve to open the first channel or the second channel according to the control signal, so as to transport the container to the corresponding storage tank. The livelihood container identification and recovery device as claimed in claim 12, wherein the central channel has a recovery opening, and the container is placed on the central channel through the recovery opening. The household container identification and recycling device as claimed in claim 12, wherein the central channel has a side window, a rear window, a first arm and a second arm, and the first image capture module is disposed on the first One arm is on the side window, and the second image capturing module is arranged on the second arm and facing the rear window. The identification and recovery device for livelihood containers according to claim 14, wherein the sorting mechanism comprises at least a third solenoid valve and a bottom plate, the third solenoid valve is disposed on the second arm and connected to the bottom plate to control the The position of the bottom plate, and the bottom plate is arranged in the central channel and faces the rear end of the container. The livelihood container identification and recycling device of claim 12, wherein the processor analyzes the neck image to determine whether the neck of the container is tapered to generate a first analysis result, and analyzes the bottom image to determine the bottom of the container Whether it is circular and generates a second analysis result, and analyzes the bottom image to determine whether the bottom of the container is transparent and generates a third analysis result, and then according to the first analysis result, the second analysis result and the first analysis result Three analysis results generate a control signal. The civil container identification and recycling device as claimed in claim 16, wherein the processor further analyzes the bottom image to determine whether the bottom of the container contains a structural feature and generates a fourth analysis result, whereby according to the first analysis result, The second analysis result, the third analysis result and the fourth analysis result generate the control signal. The livelihood container identification and recycling device as claimed in claim 17, wherein the structural feature includes one or more of a one-point structural feature and a first-line structural feature. A method for identifying a people's livelihood container, comprising: capturing a neck image of a container; capturing a bottom image of the container; analyzing the neck image to determine whether the neck of the container is tapered and generating a first analysis result; analyzing the bottom image to determine whether the bottom of the container is circular and generating a second analysis result; analyzing the bottom image to determine whether the bottom of the container is transparent and generating a third analysis result; and The type of the container is determined according to the first analysis result, the second analysis result and the third analysis result. The method for identifying a livelihood container according to claim 19, wherein the step of analyzing the neck image to determine whether the neck of the container is tapered and generating the first analysis result further comprises: Calculate the ratio of the upper bottom to the lower bottom of one of the neck images. The method for identifying a livelihood container according to claim 19, wherein the step of analyzing the bottom image to determine whether the bottom of the container is circular and generating the second analysis result further comprises: The bottom image is subjected to a Hough circle transform and a voting mechanism to generate a cumulative coordinate plane, and a cumulative weight is calculated. The method for identifying a livelihood container according to claim 19, wherein the step of analyzing the bottom image to determine whether the bottom of the container is transparent and generating the third analysis result further comprises: An image segmentation is performed to convert the bottom image into a binary image to obtain a predetermined critical gray value. The method for identifying the livelihood container as described in claim 19, further comprising: Analyze the bottom image to determine whether the bottom of the container contains a structural feature and generate a fourth analysis result, thereby judging according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result The kind of container. The method for identifying a livelihood container according to claim 23, wherein the structural feature includes one or more of a one-point structural feature and a first-line structural feature. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is tapered, the second analysis result shows that the bottom of the container is circular, the third analysis result shows that the bottom of the container is transparent, and the fourth analysis result shows that the bottom of the container is transparent The bottom of the container does not have this structural feature, and it is judged that the container is a polyvinyl chloride container. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is conical, the second analysis result shows that the bottom of the container is circular, the third analysis result shows that the bottom of the container is opaque, and the fourth analysis result shows that the bottom of the container is opaque. The bottom of the container has the structural feature, and it is judged that the container is a polyethylene container. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is conical, the second analysis result shows that the bottom of the container is circular, the third analysis result shows that the bottom of the container is opaque, and the fourth analysis result shows that the bottom of the container is opaque. The bottom of the container does not have this structural feature, and it is judged that the container is a metal container. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is conical, the second analysis result shows that the bottom of the container is not circular, the third analysis result shows that the bottom of the container is transparent, and the fourth analysis result shows The bottom of the container has the structural feature, and it is judged that the container is a polyethylene terephthalate container. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is conical, the second analysis result shows that the bottom of the container is not circular, the third analysis result shows that the bottom of the container is transparent, and the fourth analysis result shows The bottom of the container does not have the structural feature, and it is judged that the container is a polyvinyl chloride container. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is tapered, the second analysis result shows that the bottom of the container is not circular, and the third analysis result shows that the bottom of the container is opaque, it is impossible to determine the type of the container. Identify. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is not conical, the second analysis result shows that the bottom of the container is circular, and the third analysis result shows that the bottom of the container is transparent, it is impossible to judge the type of the container. Identify. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is not tapered, the second analysis result shows that the bottom of the container is circular, the third analysis result shows that the bottom of the container is opaque, and the fourth analysis result shows The bottom of the container has the structural feature, and it is judged that the container is a polyethylene container. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is not tapered, the second analysis result shows that the bottom of the container is circular, the third analysis result shows that the bottom of the container is opaque, and the fourth analysis result shows The bottom of the container does not have the structural feature, and it is judged that the container is a metal container. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is not tapered, the second analysis result shows that the bottom of the container is not circular, and the third analysis result shows that the bottom of the container is transparent, the type of the container is determined. Unrecognized. The method for identifying a livelihood container according to claim 23, wherein the step of judging the type of the container according to the first analysis result, the second analysis result, the third analysis result and the fourth analysis result further comprises: When the first analysis result shows that the neck of the container is not conical, the second analysis result shows that the bottom of the container is not circular, and the third analysis result shows that the bottom of the container is opaque, the container is judged to be a carton container.

Images