CN116380814A - Crisp plum maturity detection equipment based on visual identification - Google Patents

Abstract

The invention discloses crisp plum maturity detection equipment based on visual identification, which comprises a shell, wherein a detection chamber is arranged in the shell, a door capable of opening the detection chamber is arranged on the shell, and an objective table is arranged in the detection chamber; wherein, the objective table upper surface level is provided with a baffle, has the light trap that supplies fragile Li Gezhi on the baffle, and the light trap below is right to being provided with the transmission and detects and use the light source lamp. The invention is designed specifically for crisp Li Tedian and has the advantage of being capable of judging whether the crisp Li Tedian is mature or not more accurately and reliably.

Description

Crispy plum maturity detection equipment based on visual recognition

This application is a divisional application of the patent "A Method for Detecting Ripeness of Crispy Plums Based on Visual Recognition" with application number 202110698288.4 and application date 2021-06-23.

technical field

The invention relates to fruit detection technology, in particular to a visual recognition-based crisp plum maturity detection device.

Background technique

Crispy plum is the collective name for the deboned plums (boneless plums), which are green and bitter when immature, and yellow and sweet when fully ripe. It has the characteristics of rich exocarp color and crisp and sweet flesh. It has good quality and strong adaptability. It is mainly distributed in Southwest my country, including Jiang'an plum, Wushan plum and Bashan plum, and its planting area and output are increasing year by year.

In the process of picking crispy plums, it is very easy for fruit growers to make misjudgments during picking due to inconsistent fruit ripening periods, which will affect the quality of fresh fruits and is not conducive to the storage of fruits; in the process of storage and transportation , overripe phenomenon often occurs, and then causes bad fruit, has a strong impact on the sale of crispy plum, causes bigger economic loss. The current detection methods of fruit maturity include artificial sensory detection, physical and chemical analysis and instrument detection, but there are certain deficiencies in all of them, and it is difficult to distinguish similar qualities. The titration method is usually used in the detection and analysis of sugar content and acidity in crispy plums, and various chemical reagents need to be prepared. The operation is cumbersome, the detection efficiency is low, and on-site non-destructive testing cannot be realized. The size and color of crispy plums are usually detected by human eyes, which is slow in detection speed and consumes manpower and material resources. It cannot achieve objective and accurate results, and it is difficult to achieve standardization and quantification. The detection of the aroma and taste of crispy plums usually adopts the methods of artificial nose smell and mouth taste. External environmental conditions, sensory assessors, and prepared samples will affect the sensory test results individually or synergistically. In maturity detection, ethylene is an important marker, and its highly selective and sensitive detection at low concentrations is crucial for regulating fruit ripening. However, the current detection of ethylene is not yet mature. The current detection method of ethylene content mainly adopts gas chromatography, which has problems such as cumbersome operation and expensive equipment. In addition, judging the maturity of crispy plums only from a single index is not holistic and representative.

CN202110112114.5 discloses a sorting machine for plums, which includes a loading area and several sorting areas arranged in sequence, the loading area and the sorting area are connected by a conveyor belt, and above the sorting area is set There is a visual recognition system, and there is a collection area below; this device flexibly applies visual recognition technology to the plum sorting process, uses equipment linkage and calculation analysis processing, and automatically and accurately classifies and collects plums according to their appearance and color, thereby sorting Plums of different ripeness. The inventive solution is based on taking pictures directly above the plums, and sorting according to the photo identification and color; this is just a conventional judgment method based on the color of the outer surface of the plums, and the judgment accuracy is low.

Therefore, how to develop a more accurate method for detecting maturity in view of the characteristics of crispy plums has become a problem to be considered and solved by those skilled in the art.

Contents of the invention

Aiming at the deficiencies in the prior art above, the technical problem to be solved by the present invention is: how to provide a method for detecting the maturity of crispy plums based on visual recognition that is designed for the characteristics of crispy plums and can more accurately judge whether it is ripe, and a Crispy plum maturity detection equipment based on visual recognition.

In order to solve the problems of the technologies described above, the present invention adopts the following technical solutions:

A method for detecting the maturity of crispy plums based on visual recognition, including the steps of detecting the surface color of crispy plums, that is, using a light source to irradiate the surface of crispy plums, taking photos to obtain its surface image information, using a computer to process the surface image information, and extracting its surface color. The step of comparing and judging the color characteristic parameter and the preset parameter value of the surface color is characterized in that it also includes the color detection step of the crispy plum flesh, that is, using a light source to transmit the crispy plum, taking a photo to obtain the transmitted image information of the flesh, and using a computer to extract its flesh color. The step of comparing and judging the characteristic parameter of pulp color and the qualified preset parameter value of pulp color; when the characteristic parameter of surface color is greater than the preset parameter value of qualified surface color, and at the same time, the characteristic parameter of pulp color is greater than the preset parameter value of qualified pulp color, judging crisp plum Mature.

This is because the surface color of the crispy plums begins to turn yellow after they mature, and usually the more yellow the color, the higher the maturity. However, the change of the surface color of crispy plums is mainly related to the intensity of sunlight. Sometimes the sunlight is too strong, which may cause the inner pulp to turn yellow when the flesh is not yet fully ripe. At the same time, sometimes crisp plums that have not been exposed to the sun, even after the flesh is fully ripe, the surface color change may be relatively indistinct. However, when crispy plums mature, their pulp will definitely become more crystal clear, and the light transmittance of the pulp will increase sharply. Therefore, in this method, the light source transmission method is adopted, so that the light source transmits the crispy plum flesh, and then the transmission image information is taken for detection and judgment. The crispy plums with different maturity levels have completely different transmission brightness, and the crispy plum can be judged more accurately. Mature or not. Then use two methods based on visual recognition at the same time, and combine them for judgment and detection, which can greatly improve the accuracy and reliability of detection.

Further, in the step of detecting the surface color of crispy plums, the crispy plums are placed in a closed detection chamber, and the lighting lamp above the crispy plums is used as a light source for irradiation, and a camera is set above the crispy plums to take pictures for detection.

In this way, the uniformity and stability of the detection light source can be better guaranteed, the interference of sunlight and external light can be avoided, and the reliability of the detection result can be ensured. During implementation, the lighting can be directly above or obliquely above, and the camera can be directly above or obliquely above.

Further, during the color detection step of the crispy plum flesh, the crispy plum is placed on the light-transmitting hole on a horizontally arranged partition in the closed detection chamber, and a light source lamp for transmission detection is set below the light-transmitting hole to irradiate. A camera is set up obliquely above Li for detection.

In this way, the stability of the detection light source can be better ensured, and interference from external light sources can be avoided. At the same time, the setting of the partition ensures the transmission effect. The camera is located at the oblique upper part, because the bright part of the crispy plum is extended upward from the edge of the light transmission hole at the bottom after being transmitted. The higher the maturity of the crispy plum, the brighter area extending upward from the lower end The bigger and the brighter, so the use of the camera at the slant above can better detect the scope of the bright area at the lower part of the brittle plum and improve the detection accuracy. At the same time, based on the size of the bright area of crispy plums, the maturity classification detection of crispy plums can be realized.

Further, in the step of detecting the surface color of the crispy plum, after the camera takes a picture, the image information is transmitted to the computer, and the RGB color extraction technology is used to extract the R value, G value and B value of the crispy plum in the image, and then they are qualified according to the previous settings. The preset parameter values are compared, and when the R value, G value and B value are greater than the corresponding qualified preset parameter values, it is judged that the surface color test is qualified.

This is because the detection of crisp plum surface color is more judged by its surface color. According to the actual detection analysis and comparison, the surface color of more mature crispy plums is more yellow, and the ternary colors of R, G, and B extracted from the image all increase with the maturity of crispy plums, among which the R value increases most obviously, and the G value The degree of increase is next, and the increase of B value is even less. Therefore, in this application, RGB color extraction technology is used in the surface color detection step of crispy plums, and the three primary colors are extracted for judgment respectively, and the ripeness of crispy plums can be judged more accurately by comparing with the threshold value. During implementation, the technology of extracting RGB colors based on pictures is a mature existing technology and will not be introduced in detail here. Qualified preset parameter values for judgment can be obtained by artificially selecting mature brittle plum tests in advance. Of course, during implementation, other image feature extraction techniques can also be used for detection and judgment, such as image feature extraction processing technology characterized by the three elements h, s, and w, but the specific judgment method needs to be verified separately, and will not be introduced in detail here.

Furthermore, in the color detection step of the crispy plum flesh, after the camera takes pictures, the image information is transmitted to the computer, and the watershed algorithm is used for image segmentation processing, and then the image is binarized by an iterative method to realize grayscale processing, and a black and white two-color image is obtained , calculate the proportion of the white part, and then compare it with the qualified preset parameter value set in advance.

In this way, it is because in the color detection step of the crispy plum flesh, the detection is performed according to the brightness difference of the crispy plum after being transmitted by light. Therefore, the proportion of the white area is detected after the image is binarized into black and white, and the proportion of the bright area is obtained. And as a standard for judging whether the pulp is ripe, it is more accurate and reliable. Wherein, the specific steps such as the watershed algorithm and the iterative method belong to mature existing technologies, and will not be introduced in detail here.

In this way, in this application, different image processing algorithms are respectively adopted for the detection step of crispy plum surface color and crispy plum flesh color, so that they are more targeted and can better judge the respective steps. At the same time, different image processing algorithms are used for comprehensive judgment, which also reduces the possibility of misjudgment caused by a single algorithm. The reliability of detection is better improved. At the same time, among the above schemes, the related scheme of the color detection step of the crispy plum flesh was completely proposed by the applicant for the first time, especially the method of detecting the brightness of the crispy plum flesh by light transmission is a very original detection scheme. , this scheme is completely feasible to implement alone, and its independent implementation also has high judgment reliability, and its implementation is relatively simpler and easier.

Further, the method is realized by using the following visual recognition-based crisp plum maturity detection equipment, the visual recognition-based crisp plum maturity detection equipment includes a casing, the inside of the casing is a detection chamber, and the casing is provided with The door of the detection chamber can be opened, and the detection chamber is equipped with a stage inside, and also includes a visual recognition detection system. The camera is installed obliquely above the stage, and the camera is connected to the computer through a communication module; wherein, a partition is arranged horizontally on the upper surface of the stage, and there is a light-transmitting hole on the partition for placing crispy plums. The pair is equipped with a light source lamp for transmission detection.

Like this, can preset in the computer the software module for realizing above-mentioned crisp plum surface color and luster detection step and crisp plum flesh color and luster detection step; Wherein the software module of crisp plum surface color and luster detection step comprises RGB color extraction judgment module, RGB color extraction judgment module uses Extract the R value, G value and B value of crispy plums in the image, and then compare them with the qualified preset parameter values set in advance. When the R value, G value and B value are greater than the corresponding qualified preset parameter values, the judgment surface The color detection is qualified; the software module of the crisp plum flesh color detection step includes an image segmentation processing module and a grayscale processing judgment module. In the processing and judging module, the iterative method is used to realize image binarization and grayscale processing to obtain a black and white two-color image, calculate the proportion of the white part, and then compare it with the pre-set qualified preset parameter value, which is greater than the qualified preset The parameter value is to judge that the color of the crispy plum flesh is qualified. Then, relying on the illuminating lamp as the light source, turning on the illuminating lamp independently, relying on the camera to take images, and realizing the above steps of detecting the surface color of crispy plums. Then turn off the light, turn on the light source lamp for transmission detection separately, rely on the camera to take images, and realize the above-mentioned steps of detecting the color of crispy plum flesh. Therefore, the device can realize two different mechanisms for judging the maturity of crispy plums based on image detection and recognition technology, and can judge the maturity of crispy plums very conveniently, accurately and reliably. During implementation, the size of the light-transmitting hole is based on the crisp plums that can be placed on it and facilitates the light to penetrate the crisp plums and shoot out, usually about 2-3cm in diameter.

Further, a closed light source installation chamber is provided under the partition, and a light source lamp for transmission detection is installed in the light source installation chamber. In this way, it can be ensured that the light transmitted through the light source for detection only passes through the light-transmitting hole.

Further, a plurality of light-transmitting holes are arranged in an array on the separator. In this way, the detection of a batch of crispy plums can be realized at one time. When the specified proportion (for example, 90%) of the crispy plums in a batch of crispy plums meets the detection requirements, it can be judged that the batch of crispy plums is mature. In this way, it is possible to more conveniently and quickly realize the judgment of the ripeness of crispy plums in batches. It has more practical significance to guide production and application.

Further, a light source lamp for transmission detection is installed at the center position below each light transmission hole, each light source lamp for transmission detection is arranged in parallel, and a detection switch is also arranged in series in the circuit branch where each light source lamp for transmission detection is located. , the detection switch is used to connect the circuit branch after detecting that an object is placed on the light-transmitting hole.

In this way, after the crispy plums are placed on each light-transmitting hole, the detection switch controls the corresponding light source lamp for transmission detection below to turn on, so as to realize the detection of the crispy plums on the light-transmitting holes. In this way, the light source lamp for transmission detection under the light transmission hole that is not placed will not be turned on to cause interference, so the detection accuracy can be better guaranteed. During specific implementation, the detection switch may be a piezoelectric switch, a contact switch, or a proximity switch installed on the light-transmitting hole.

Further, each light source lamp for transmission detection is provided with a cone-shaped reflecting lampshade, and the large-diameter end of the reflecting lampshade faces upwards and connects with the corresponding light-transmitting hole.

In this way, it is further ensured that the light of each light source lamp for transmission detection only acts on the light-transmitting hole above it, improving its lighting effect, avoiding mutual interference, and better improving detection reliability.

Further, the light source lamp for transmission detection is an LED light bulb. This is cheap and easy to set up.

Further, it also includes an odor identification and detection system, the odor identification and detection system includes a sensor array module, the sensor array module is located inside the detection chamber or communicated with the detection chamber, the sensor array module is provided with ethylene sensors, aldehyde gas One or more of sensors, alcohol gas sensors, ester gas sensors and phenol gas sensors, each sensor on the sensor array module is connected to a computer.

In this way, it is because mature crispy plums will volatilize characteristic gases such as ethylene, aldehydes, alcohols, esters, and phenols; The content of each component in the output gas is detected, compared and judged. If the corresponding gas content exceeds the preset threshold, the judgment is mature. The preset threshold can be determined by prior experiments. Then it can better assist in realizing the accurate judgment of crisp plum maturity. The sensor array module integrates a variety of gas sensors, which can better help realize the multi-level grading identification of crispy plums, so as to facilitate grading storage or transportation. For example, higher gas detection components of esters and phenols indicate better maturity, while higher gas detection components of aldehydes and alcohols indicate that crispy plums may be too ripe for storage or transportation, and need to be eaten as soon as possible.

Further, the odor identification and detection system also includes an airflow hood arranged above the object stage, the airflow hood is in the shape of a cone bucket, the upper end of the airflow hood is connected to a gas detection chamber through an air suction pipeline, and an air pump and an air pump are installed on the air suction pipeline. The one-way valve leading to the gas detection chamber, the sensor array module is arranged in the gas detection chamber.

In this way, by means of pumping, the gas volatilized by the brittle plums on the stage is sucked into the gas detection chamber, so as to realize the enrichment of the collected gas, increase the content ratio of the volatile component gas, greatly shorten the detection time and improve the detection sensitivity and precision.

Further, a heating device is provided in the detection chamber, and an oxygen supply device is connected to the detection chamber, and the oxygen supply device communicates with the detection chamber through an oxygen supply pipeline.

In this way, by supplying oxygen to the detection chamber while heating to increase its temperature (usually heated to about 35-50 degrees), the ripening environment of crispy plums can be simulated and its ripening effect can be enlarged (usually mainly by increasing the oxygen concentration). maturation effect). The detected crispy plums can volatilize characteristic gases more quickly, greatly shortening the time required for odor identification and detection.

It can be seen that based on the above-mentioned crispy plum maturity detection equipment after adding a heating device and an oxygen supply device, the present invention also discloses a method for accelerating the ripening of crispy plums; In the ripening space (that is, the detection room of crisp plum maturity testing equipment); then the ambient temperature of the ripening space is increased through the heating device, and the oxygen content of the ripening space is increased through the oxygen supply device to simulate the ripening environment of crispy plums and expand Its ripening effect (usually mainly by increasing the oxygen concentration to expand its ripening effect), accelerates the respiratory ripening process of crispy plums, and realizes the natural simulated ripening of crispy plums. In this way, compared with the ripening method relying on various ripening agents in the prior art, not only the ripening method is natural, scientific, fast and efficient, but also there is no artificial reagent residue, which ensures the natural green safety of fruit food and meets the current requirements. Advocate the development needs of green food and organic food. At the same time, in the process of ripening crispy plums, the ripening method can also realize the real-time detection of the ripeness of crispy plums based on the above-mentioned equipment, which ensures the reliability and stability of the ripening process and avoids the difficulty of transportation caused by catalytic overripe And sales are even hard to eat.

Further, a water storage chamber is provided at the bottom of the housing, and water is stored in the water storage chamber, and the heating device is arranged inside or adjacent to the water storage chamber, and the upper end of the water storage chamber communicates with the detection chamber. .

In this way, the water in the water storage chamber can be evaporated depending on the temperature of the heating device, so that the water evaporates into the detection chamber and the humidity of the detection chamber is increased. Because crispy plums can ripen better in a high-heat, humid and oxygen-rich environment, it can better simulate the environmental conditions required for crispy plum ripening and improve the ripening effect. In the process of detecting the maturity of crispy plums and ripening crispy plums, the time required can be better shortened and the efficiency of equipment use can be improved. The heating device preferably adopts an electric heating device to facilitate control.

Further, the bottom of the water storage chamber is arranged obliquely and a drain switch valve is arranged at the lower side.

In this way, when there is no need for ripening, it is convenient to discharge the water stored in the water storage chamber through the drain switch valve, so as to prevent damage to parts caused by excessive humidity inside the equipment.

Further, a temperature sensor, an oxygen concentration sensor, and a humidity sensor are also provided in the detection chamber, and the temperature sensor, the oxygen concentration sensor, and the humidity sensor are respectively connected to a computer, and the computer is respectively connected to a heating device, an oxygen supply device, and installed on the upper end of the water storage chamber. It is connected with the switch control valve at the communication position of the detection chamber and realizes the control.

In this way, the temperature, humidity and oxygen concentration data in the detection chamber can be detected and monitored in real time, and controlled to a suitable degree for ripening, so as to ensure the stability and reliability of the ripening process.

Further, a turbulent fan is also arranged above the object platform.

The circumventing fan can well ensure that the temperature, humidity and oxygen concentration in the detection air are in a balanced state, so that the batches of crispy plums used for detection or ripening can be ripened more evenly.

Furthermore, a storage space is provided at the lower part of the stage, and a storage frame is placed in the storage space in a drawable manner, and holes are densely arranged on the storage frame.

In this way, when the device is used for ripening crispy plums in batches, the storage frame can be used to store crispy plums, and the quantity of crispy plums to be processed in batches can be increased.

Further, a thermal insulation layer is also provided on the outer side of the housing.

In this way, heat insulation can be achieved, which is conducive to maintaining the internal ripening environment.

Furthermore, a crisp plum deboning detection device is also provided in the detection chamber for detecting the degree of deboning of the crisp plum.

This is because crispy plums, also known as boneless plums, have the characteristic that after ripening, the pulp and core will separate to form a hollow shape. Usually, the more mature the crispy plums, the more obvious the effect of boneless plums. At the same time, consumers are usually more willing to Buying crispy plums with more obvious deboning effect not only tastes better, but also makes it easier to separate and spit out the core completely, so crispy plums with more obvious deboning are of higher quality. Therefore, after detecting the maturity of crispy plums, the degree of deboning of crispy plums can be detected to better assist in the realization of product grading and sorting.

Further, the deboned crispy plum detection device includes a horizontally arranged mesh orifice plate, an air blowing channel is arranged under the mesh orifice plate, a blower is arranged under the air blast channel, and an upward blocking member is arranged around the mesh orifice plate.

In this way, the blower blows air through the air blowing channel, and evenly guides the strong air flow to act on the mesh orifice plate. During detection, the crisp plums are placed on the mesh orifice plate. Crisp plums with a high degree of deboning have larger internal space and lower relative density, and are easier to be blown upward by the blower. Therefore, adjusting the air flow speed can be blown away from the mesh orifice according to whether the crispy plums can be blown away from the mesh or even the mesh. The height of the orifice plate is used to judge the degree of deboning of crispy plums. Then realize the grading and sorting of crispy plums. At the same time, it is very convenient and quick and does not damage the crispy plums. Among them, the blocking piece can prevent crisp plums from being blown out of the mesh orifice plate. As another method, during implementation, it is also possible to use an aqueous solution with a good density to detect the degree of deboning of crispy plums by re-selection, but this method has poor reliability and is inconvenient to operate, and it is not conducive to later storage or storage of crispy plums after they are wet. edible.

Further, the blocking member is a vertically arranged cloth with a height of 3-8cm.

In this way, the 3-8cm height cloth is used to form the blocking part. The cloth is flexible, and it is in a soft state when it is not blown, which is convenient for the placement of crispy plums. plum.

Further, the cloth divides the mesh orifice into strips with a width of 4-7 cm and a length several times the width.

In this way, the next or two brittle plums can be accommodated and prevented in the width direction, and the air flow can be concentrated and blown upward to detect the brittle plums in the width direction, and the interference to the force of the brittle plums by the blocking member itself can be avoided to the greatest extent (if If three or more crispy plums can be placed in the width direction, it is obvious that the crispy plums in the middle and the crispy plums on both sides will have different upward force effects, and the sides will be disturbed by the surrounding cloth), which can be better Guarantee the force balance of brittle plums and improve the reliability of detection.

Further, meshes are densely covered on the surrounding cloth, and the meshes increase from bottom to top.

The more upward and outward the air current is lost, the greater the upward supporting force of the brittle plum is. Therefore, it can better assist in judging the degree of deboning of crispy plums according to the blown height, and more accurately assist in the grading of crispy plums.

In summary, the present invention is specially designed for the characteristics of crispy plums, and has the advantage of being able to judge whether it is ripe more accurately and reliably.

Description of drawings

Fig. 1 is the structural representation of crisp plum maturity detection equipment when the present invention is implemented.

Fig. 2 is a schematic diagram showing the internal structure after removing the front door and the panel in Fig. 1 .

FIG. 3 is a schematic diagram of a partition on the upper surface of a separate stage in FIG. 2 .

FIG. 4 is an enlarged schematic diagram of a single point A in FIG. 2 .

Fig. 5 is a schematic diagram of the individual shroud in Fig. 2 .

Figure 6 is a comparison of photos obtained after camera shooting, image segmentation processing, and image binarization grayscale processing in the color detection step of crispy plum flesh for three types of crispy plums with different maturity levels.

Detailed ways

The present invention will be further described in detail below in conjunction with the accompanying drawings.

The best implementation mode: a method for detecting the maturity of crispy plums based on visual recognition, including the step of detecting the surface color of crispy plums, that is, using a light source to irradiate the surface of crispy plums, taking photos to obtain its surface image information, and using a computer to analyze the surface image information. Processing, the step of extracting its surface color characteristic parameters and the qualified preset parameter value of the surface color for comparison and judgment, which also includes the step of detecting the color of the crispy plum flesh, that is, using the light source to transmit the crispy plum, taking photos to obtain the transmitted image information of the flesh, using A step in which the computer extracts the characteristic parameter of the pulp color and the qualified preset parameter value of the pulp color for comparison and judgment; Judging crisp plum ripeness.

This is because the surface color of the crispy plums begins to turn yellow after they mature, and usually the more yellow the color, the higher the maturity. However, the change of the surface color of crispy plums is mainly related to the intensity of sunlight. Sometimes the sunlight is too strong, which may cause the inner pulp to turn yellow when the flesh is not yet fully ripe. At the same time, sometimes crisp plums that have not been exposed to the sun, even after the flesh is fully ripe, the surface color change may be relatively indistinct. However, when crispy plums mature, their pulp will definitely become more crystal clear, and the light transmittance of the pulp will increase sharply. Therefore, in this method, the light source transmission method is adopted, so that the light source transmits the crispy plum flesh, and then the transmission image information is taken for detection and judgment. The crispy plums with different maturity levels have completely different transmission brightness, and the crispy plum can be judged more accurately. Mature or not. Then use two methods based on visual recognition at the same time, and combine them for judgment and detection, which can greatly improve the accuracy and reliability of detection.

Among them, in the step of detecting the surface color of the crispy plums, the crispy plums are placed in a closed detection chamber, and the lighting lamp above the crispy plums is used as a light source for irradiation, and a camera is installed above the crispy plums for detection.

In this way, the uniformity and stability of the detection light source can be better guaranteed, the interference of sunlight and external light can be avoided, and the reliability of the detection result can be ensured. During implementation, the lighting can be directly above or obliquely above, and the camera can be directly above or obliquely above.

Wherein, during the color detection step of the crispy plum flesh, the crispy plum is placed on a light-transmitting hole on a horizontally arranged partition in a closed detection chamber, and a light source lamp for transmission detection is set below the light-transmitting hole to irradiate. A camera is set up obliquely above for detection.

In this way, the stability of the detection light source can be better ensured, and interference from external light sources can be avoided. At the same time, the setting of the partition ensures the transmission effect. The camera is located at the oblique upper part, because the bright part of the crispy plum is extended upward from the edge of the light transmission hole at the bottom after being transmitted. The higher the maturity of the crispy plum, the brighter area extending upward from the lower end The bigger and the brighter, so the use of the camera at the slant above can better detect the scope of the bright area at the lower part of the brittle plum and improve the detection accuracy. At the same time, based on the size of the bright area of crispy plums, the maturity classification detection of crispy plums can be realized.

Among them, in the step of detecting the surface color of crispy plums, after the camera takes a picture, the image information is transmitted to the computer, and the RGB color extraction technology is used to extract the R value, G value and B value of the crispy plums in the image, and then they are compared with the pre-set qualified presets. Set the parameter values for comparison, and when the R value, G value and B value are all greater than the corresponding qualified preset parameter values, it is judged that the surface color test is qualified.

This is because the detection of crisp plum surface color is more judged by its surface color. According to the actual detection analysis and comparison, the surface color of more mature crispy plums is more yellow, and the ternary colors of R, G, and B extracted from the image all increase with the maturity of crispy plums, among which the R value increases most obviously, and the G value The degree of increase is next, and the increase of B value is even less. Therefore, in this application, RGB color extraction technology is used in the surface color detection step of crispy plums, and the three primary colors are extracted for judgment respectively, and the ripeness of crispy plums can be judged more accurately by comparing with the threshold value. During implementation, the technology of extracting RGB colors based on pictures is a mature existing technology and will not be introduced in detail here. Qualified preset parameter values for judgment can be obtained by artificially selecting mature brittle plum tests in advance. Of course, during implementation, other image feature extraction techniques can also be used for detection and judgment, such as image feature extraction processing technology characterized by the three elements h, s, and w, but the specific judgment method needs to be verified separately, and will not be introduced in detail here.

Among them, in the color detection step of the crispy plum flesh, after the camera takes pictures, the image information is transmitted to the computer, and the watershed algorithm is used for image segmentation processing, and then the image is binarized by an iterative method to realize grayscale processing, and a black and white two-color image is obtained. Calculate the proportion of the white part, and then compare it with the qualified preset parameter value set in advance. If it is greater than the qualified preset parameter value, it is judged that the color of the crispy plum flesh is qualified.

In this way, it is because in the color detection step of the crispy plum flesh, the detection is performed according to the brightness difference of the crispy plum after being transmitted by light. Therefore, the proportion of the white area is detected after the image is binarized into black and white, and the proportion of the bright area is obtained. And as a standard for judging whether the pulp is ripe, it is more accurate and reliable. Wherein, the specific steps such as the watershed algorithm and the iterative method belong to mature existing technologies, and will not be introduced in detail here. Referring to Figure 6, there are three kinds of crispy plums with different maturity levels. In the color detection step of crispy plum flesh, from left to right are the photo comparison pictures obtained after camera shooting, image segmentation processing, and image binarization grayscale processing. . Three kinds of crispy plums with different maturity levels are low-ripe at the top, medium-ripe at the middle and high-ripe at the bottom. The photo on the left is the photo taken by the camera, the photo in the middle is the photo after image segmentation, and the photo on the right is the photo after image binarization and grayscale processing. Among them, the left and middle photos were originally in the original color of crispy plum, but the color was canceled due to the processing requirements of the declaration text format. It can be seen from Figure 6 that the more mature crispy plums, the larger the proportion of white shiny areas after image binarization, and the distinction is very obvious. Therefore, as a criterion for judging whether the pulp is ripe, it has high accuracy and can be well assisted in the realization of Grading and sorting.

In this way, in this application, different image processing algorithms are respectively adopted for the detection step of crispy plum surface color and crispy plum flesh color, so that they are more targeted and can better judge the respective steps. At the same time, different image processing algorithms are used for comprehensive judgment, which also reduces the possibility of misjudgment caused by a single algorithm. The reliability of detection is better improved. At the same time, among the above schemes, the related scheme of the color detection step of the crispy plum flesh was completely proposed by the applicant for the first time, especially the method of detecting the brightness of the crispy plum flesh by light transmission is a very original detection scheme. , this scheme is completely feasible to implement alone, and its independent implementation also has high judgment reliability, and its implementation is relatively simpler and easier.

In this embodiment, the method is realized by using a crisp plum maturity detection device based on visual recognition, and the crisp plum maturity detection device based on visual recognition is shown in Figure 1-5, including a housing 1, and the inside of the housing 1 is The detection chamber 2, the housing 1 is provided with a door 3 capable of opening the detection chamber, the detection chamber 2 is provided with a stage 4 inside, and also includes a visual recognition detection system, the visual recognition detection system includes a set above the stage The lighting lamp 5, the lighting lamp 5 is used as a light source, and the visual recognition detection system also includes a camera 6 arranged obliquely above the stage, and the camera 6 is connected to the computer 7 through a communication module; wherein, a partition is horizontally arranged on the upper surface of the stage 8. There is a light-transmitting hole 9 on the partition 8 for placing crispy plums, and a light source lamp 10 for transmission detection is arranged directly below the light-transmitting hole 9 .

Like this, can preset in the computer the software module for realizing above-mentioned crisp plum surface color and luster detection step and crisp plum flesh color and luster detection step; Wherein the software module of crisp plum surface color and luster detection step comprises RGB color extraction judgment module, RGB color extraction judgment module uses Extract the R value, G value and B value of crispy plums in the image, and then compare them with the qualified preset parameter values set in advance. When the R value, G value and B value are greater than the corresponding qualified preset parameter values, the judgment surface The color detection is qualified; the software module of the crisp plum flesh color detection step includes an image segmentation processing module and a grayscale processing judgment module. In the processing and judging module, the iterative method is used to realize image binarization and grayscale processing to obtain a black and white two-color image, calculate the proportion of the white part, and then compare it with the pre-set qualified preset parameter value, which is greater than the qualified preset The parameter value is to judge that the color of the crispy plum flesh is qualified. Then, relying on the illuminating lamp as the light source, turning on the illuminating lamp independently, relying on the camera to take images, and realizing the above steps of detecting the surface color of crispy plums. Then turn off the light, turn on the light source lamp for transmission detection separately, rely on the camera to take images, and realize the above-mentioned steps of detecting the color of crispy plum flesh. Therefore, the device can realize two different mechanisms for judging the maturity of crispy plums based on image detection and recognition technology, and can judge the maturity of crispy plums very conveniently, accurately and reliably. During implementation, the size of the light-transmitting hole is based on the crisp plums that can be placed on it and facilitates the light to penetrate the crisp plums and shoot out, usually about 2-3cm in diameter.

Wherein, a closed light source installation chamber is arranged under the partition, and the light source lamp 10 for transmission detection is installed in the light source installation chamber. In this way, it can be ensured that the light transmitted through the light source for detection only passes through the light-transmitting hole.

Wherein, a plurality of light-transmitting holes 9 are arranged in an array on the partition. In this way, the detection of a batch of crispy plums can be realized at one time. When the specified proportion (for example, 90%) of the crispy plums in a batch of crispy plums meets the detection requirements, it can be judged that the batch of crispy plums is mature. In this way, it is possible to more conveniently and quickly realize the judgment of the ripeness of crispy plums in batches. It has more practical significance to guide production and application.

Wherein, a light source lamp 10 for transmission detection is installed in the middle position below each light transmission hole 9, and each light source lamp 10 for transmission detection is arranged in parallel, and a light source lamp 10 for transmission detection is also arranged in series in each circuit branch where each light source lamp is located. The detection switch 11 is used to connect the circuit branch after detecting that an object is placed on the light-transmitting hole.

In this way, after the crispy plums are placed on each light-transmitting hole, the detection switch controls the corresponding light source lamp for transmission detection below to turn on, so as to realize the detection of the crispy plums on the light-transmitting holes. In this way, the light source lamp for transmission detection under the light transmission hole that is not placed will not be turned on to cause interference, so the detection accuracy can be better guaranteed. During specific implementation, the detection switch may be a piezoelectric switch, a contact switch, or a proximity switch installed on the light-transmitting hole.

Wherein, each light source lamp 10 for transmission detection is provided with a cone-shaped reflector lampshade 12 outside, and the large-diameter end of the reflector lampshade 12 faces upwards and connects with the corresponding light-transmitting hole 9 .

In this way, it is further ensured that the light of each light source lamp for transmission detection only acts on the light-transmitting hole above it, improving its illumination effect, avoiding mutual interference, and better improving detection reliability.

Wherein, the light source lamp 10 for transmission detection is an LED light bulb. This is cheap and easy to set up.

Wherein, it also includes an odor identification and detection system, the odor identification and detection system includes a sensor array module 17, the sensor array module 17 is located inside the detection chamber or communicates with the detection chamber, the sensor array module is provided with ethylene sensors, aldehydes One or more of gas sensors, alcohol gas sensors, ester gas sensors and phenol gas sensors, each sensor on the sensor array module is connected to a computer.

In this way, it is because mature crispy plums will volatilize characteristic gases such as ethylene, aldehydes, alcohols, esters, and phenols; The content of each component in the output gas is detected, compared and judged. If the corresponding gas content exceeds the preset threshold, the judgment is mature. The preset threshold can be determined by prior experiments. Then it can better assist in realizing the accurate judgment of crisp plum maturity. The sensor array module integrates a variety of gas sensors, which can better help realize the multi-level grading identification of crispy plums, so as to facilitate grading storage or transportation. For example, higher gas detection components of esters and phenols indicate better maturity, while higher gas detection components of aldehydes and alcohols indicate that crispy plums may be too ripe for storage or transportation, and need to be eaten as soon as possible.

Wherein, the odor identification and detection system also includes an air flow cover 13 arranged above the loading platform, the air flow cover is in the shape of a cone bucket, and the upper end of the air flow cover 13 is connected to a gas detection chamber 14 through an air extraction pipeline, and the air extraction pipeline is equipped with An air pump 15 and a one-way valve 16 leading to the gas detection chamber, the sensor array module 17 is arranged in the gas detection chamber.

In this way, by means of pumping, the gas volatilized by the brittle plums on the stage is sucked into the gas detection chamber, so as to realize the enrichment of the collected gas, increase the content ratio of the volatile component gas, greatly shorten the detection time and improve the detection sensitivity and precision.

Wherein, a heating device 18 is also provided in the detection chamber, and an oxygen supply device 19 is also connected in the detection chamber 2, and the oxygen supply device 19 communicates with the detection chamber 2 through an oxygen supply pipeline.

In this way, by supplying oxygen to the detection chamber while heating to increase its temperature (usually heated to about 35-50 degrees), the ripening environment of crispy plums can be simulated and its ripening effect can be enlarged (usually mainly by increasing the oxygen concentration). maturation effect). The detected crispy plums can volatilize characteristic gases more quickly, greatly shortening the time required for odor identification and detection.

It can be seen that based on the above-mentioned crispy plum maturity detection equipment after adding a heating device and an oxygen supply device, the present invention also discloses a method for accelerating the ripening of crispy plums; In the ripening space (that is, the detection room of crisp plum maturity testing equipment); then the ambient temperature of the ripening space is increased through the heating device, and the oxygen content of the ripening space is increased through the oxygen supply device to simulate the ripening environment of crispy plums and expand Its ripening effect (usually mainly by increasing the oxygen concentration to expand its ripening effect), accelerates the respiratory ripening process of crispy plums, and realizes the natural simulated ripening of crispy plums. In this way, compared with the ripening method relying on various ripening agents in the prior art, not only the ripening method is natural, scientific, fast and efficient, but also there is no artificial reagent residue, which ensures the natural green safety of fruit food and meets the current requirements. Advocate the development needs of green food and organic food. At the same time, in the process of ripening crispy plums, the ripening method can also realize the real-time detection of the ripeness of crispy plums based on the above-mentioned equipment, which ensures the reliability and stability of the ripening process and avoids the difficulty of transportation caused by catalytic overripe And sales are even hard to eat.

Wherein, a water storage chamber 20 is also provided at the bottom of the housing 1, and water is stored in the water storage chamber 20. The heating device 18 is arranged inside or adjacent to the water storage chamber 20, and the upper end of the water storage chamber and Detection chamber connectivity settings.

In this way, the water in the water storage chamber can be evaporated depending on the temperature of the heating device, so that the water evaporates into the detection chamber and the humidity of the detection chamber is increased. Because crispy plums can ripen better in a high-heat, humid and oxygen-rich environment, it can better simulate the environmental conditions required for crispy plum ripening and improve the ripening effect. In the process of detecting the maturity of crispy plums and ripening crispy plums, the time required can be better shortened and the efficiency of equipment use can be improved. The heating device preferably adopts an electric heating device to facilitate control.

Wherein, the bottom of the water storage chamber 20 is arranged obliquely and a drain switch valve is arranged at the lower side.

In this way, when there is no need for ripening, it is convenient to discharge the water stored in the water storage chamber through the drain switch valve, so as to prevent damage to parts caused by excessive humidity inside the equipment.

Wherein, a temperature sensor, an oxygen concentration sensor and a humidity sensor (not shown in the figure) are also arranged in the detection chamber, and the temperature sensor, the oxygen concentration sensor and the humidity sensor are respectively connected to the computer 7, and the computer is respectively connected to the heating device 18 and the oxygen supply device 19 And the switch control valve installed at the upper end of the water storage chamber and the communication position of the detection chamber is connected to realize the control.

In this way, the temperature, humidity and oxygen concentration data in the detection chamber can be detected and monitored in real time, and controlled to a suitable degree for ripening, so as to ensure the stability and reliability of the ripening process.

Wherein, a turbulent fan 21 is also arranged above the stage 4 .

The circumventing fan can well ensure that the temperature, humidity and oxygen concentration in the detection air are in a balanced state, so that the batches of crispy plums used for detection or ripening can be ripened more evenly.

Wherein, a storage space is provided at the lower part of the stage 4, and a storage frame 22 is placed in the storage space in a drawable manner, and holes are densely arranged on the storage frame.

In this way, when the device is used for ripening crispy plums in batches, the storage frame can be used to store crispy plums, and the quantity of crispy plums to be processed in batches can be increased.

Wherein, an insulating layer is also provided on the outer side of the casing 1 .

In this way, heat insulation can be achieved, which is conducive to maintaining the internal ripening environment.

Wherein, a crisp plum deboning detection device is also arranged in the detection chamber 2 for realizing the detection of the deboning degree of the crisp plum.

This is because crispy plums, also known as boneless plums, have the characteristic that after ripening, the pulp and core will separate to form a hollow shape. Usually, the more mature the crispy plums, the more obvious the effect of boneless plums. At the same time, consumers are usually more willing to Buying crispy plums with more obvious deboning effect not only tastes better, but also makes it easier to separate and spit out the core completely, so crispy plums with more obvious deboning are of higher quality. Therefore, after detecting the maturity of crispy plums, the degree of deboning of crispy plums can be detected to better assist in the realization of product grading and sorting.

Wherein, the deboned detection device for crisp plums includes a mesh orifice plate 23 arranged horizontally, an air blast channel 24 is arranged below the mesh orifice plate, a blower 25 is arranged below the air blast channel, and an upward blocking member 26 is arranged around the mesh orifice plate.

In this way, the blower blows air through the air blowing channel, and evenly guides the strong air flow to act on the mesh orifice plate. During detection, the crisp plums are placed on the mesh orifice plate. Crisp plums with a high degree of deboning have larger internal space and lower relative density, and are easier to be blown upward by the blower. Therefore, adjusting the air flow speed can be blown away from the mesh orifice according to whether the crispy plums can be blown away from the mesh or even the mesh. The height of the orifice plate is used to judge the degree of deboning of crispy plums. Then realize the grading and sorting of crispy plums. At the same time, it is very convenient and quick and does not damage the crispy plums. Among them, the blocking piece can prevent crisp plums from being blown out of the mesh orifice plate. As another method, during implementation, it is also possible to use an aqueous solution with a good density to detect the degree of deboning of crispy plums by gravity selection, but this method has poor reliability and is inconvenient to operate, and it is not conducive to later storage or storage of crispy plums. edible.

Wherein, the blocking member 26 is a cloth with a height of 3-8 cm arranged vertically.

In this way, the 3-8cm height cloth is used to form the blocking part. The cloth is flexible, and it is in a soft state when it is not blown, which is convenient for the placement of crispy plums. plum.

Among them, the surrounding cloth divides the mesh orifice plate into long strips with a width of 4-7 cm and a length that is several times the width.

In this way, the next or two brittle plums can be accommodated and prevented in the width direction, and the air flow can be concentrated and blown upward to detect the brittle plums in the width direction, and the interference to the force of the brittle plums by the blocking member itself can be avoided to the greatest extent (if If three or more crispy plums can be placed in the width direction, it is obvious that the crispy plums in the middle and the crispy plums on both sides will have different upward force effects, and the sides will be disturbed by the surrounding cloth), which can be better Guarantee the force balance of brittle plums and improve the reliability of detection.

Wherein, the surrounding cloth is densely covered with meshes 27 and the meshes are enlarged from bottom to top.

The more upward and outward the air current is lost, the greater the upward supporting force of the brittle plum is. Therefore, it can better assist in judging the degree of deboning of crispy plums according to the blown height, and more accurately assist in the grading of crispy plums.

Claims (10)

1. A crisp plum maturity detection device based on visual recognition, comprising a housing, the inside of the housing is a detection chamber, the housing is provided with a door capable of opening the detection chamber, and the detection chamber is provided with a loading platform, It is characterized in that it also includes a visual recognition detection system. The visual recognition detection system includes a lighting lamp installed above the stage, and the lighting lamp is used as a light source. The visual recognition detection system also includes a camera installed obliquely above the stage. The camera passes through the communication module It is connected with the computer; wherein, a baffle is horizontally arranged on the upper surface of the stage, and there is a light-transmitting hole on the baffle for placing crispy plums, and a light source lamp for transmission detection is arranged directly below the light-transmitting hole. 2. The crisp plum maturity detection device based on visual recognition as claimed in claim 1, wherein the light-transmitting hole is 2-3 cm in diameter. 3. The crisp plum maturity detection device based on visual recognition as claimed in claim 1, wherein a closed light source setting chamber is arranged under the partition, and a light source lamp for transmission detection is installed in the light source setting chamber. 4. The crisp plum maturity detection device based on visual recognition according to claim 1, characterized in that a plurality of light-transmitting holes are arranged in an array on the partition. 5. The crisp plum maturity detection device based on visual recognition as claimed in claim 1, wherein a light source lamp for transmission detection is installed at the center position below each light transmission hole, and each light source lamp for transmission detection is connected in parallel. It is provided that a detection switch is arranged in series in the circuit branch where each light source lamp for transmission detection is located, and the detection switch is used to connect the circuit branch after detecting that an object is placed on the light-transmitting hole. 6. The crisp plum maturity detection device based on visual recognition as claimed in claim 1, wherein a cone-shaped reflector lampshade is arranged outside each light source lamp for transmission detection, and the large-diameter end of the reflector lampshade is upward and corresponds to The transparent holes are connected. 7. The crisp plum maturity detection device based on visual recognition as claimed in claim 1, further comprising a smell recognition detection system, the smell recognition detection system comprising a sensor array module, the sensor array module is located in the detection chamber Inside the chamber or communicated with the detection chamber, the sensor array module is provided with one or more of ethylene sensors, aldehyde gas sensors, alcohol gas sensors, ester gas sensors and phenol gas sensors, and each of the sensor array modules The sensors are connected to a computer. 8. the crisp plum maturity detection equipment based on visual recognition as claimed in claim 7, is characterized in that, described odor recognition detection system also comprises an airflow cover that is arranged on the loading platform top, and airflow cover is cone bucket shape, The upper end of the airflow hood is connected to a gas detection chamber through an air extraction pipeline, and an air pump and a check valve leading to the gas detection chamber are installed on the air extraction pipeline, and the sensor array module is arranged in the gas detection chamber. 9. The crisp plum maturity detection equipment based on visual recognition as claimed in claim 8, wherein a heating device is also arranged in the detection chamber, and an oxygen supply device is also connected in the detection chamber, and the oxygen supply device passes through the The oxygen pipeline communicates with the detection chamber; A water storage chamber is also provided at the bottom of the housing, and water is stored in the water storage chamber. The heating device is arranged inside or adjacent to the water storage chamber, and the upper end of the water storage chamber is connected to the detection chamber; The detection chamber is also provided with a temperature sensor, an oxygen concentration sensor and a humidity sensor. The temperature sensor, the oxygen concentration sensor and the humidity sensor are respectively connected to the computer. The switch control valve at the communication position of the chamber is connected and controlled. 10. The crisp plum maturity detection equipment based on visual recognition as claimed in claim 1, wherein the computer is preset with a software module for realizing the crisp plum surface color detection step and the crisp plum flesh color detection step; The software module of the plum surface color detection step includes an RGB color extraction and judgment module, which is used to extract the R value, G value and B value of crisp plums in the image, and then compare them with the qualified preset parameter values set in advance , when the R value, G value and B value are greater than the corresponding qualified preset parameter value, it is judged that the surface color detection is qualified; the software module of the crisp plum flesh color detection step includes an image segmentation processing module and a grayscale processing judgment module, and the image segmentation processing module In the image segmentation process, the watershed algorithm is used to separate the bright part from the rest; in the grayscale processing judgment module, the iterative method is used to realize image binarization and grayscale processing to obtain a black and white two-color image, and the white part is calculated The proportion is compared with the pre-set qualified preset parameter value, and if it is greater than the qualified preset parameter value, it is judged that the color of the crispy plum flesh is qualified.

Images