CN120163819B - Aluminum bar intelligent cutting method and system based on machine vision - Google Patents
Aluminum bar intelligent cutting method and system based on machine visionInfo
- Publication number
- CN120163819B CN120163819B CN202510638521.8A CN202510638521A CN120163819B CN 120163819 B CN120163819 B CN 120163819B CN 202510638521 A CN202510638521 A CN 202510638521A CN 120163819 B CN120163819 B CN 120163819B
- Authority
- CN
- China
- Prior art keywords
- cross
- sectional image
- edge
- detected
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/20—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring workpiece characteristics, e.g. contour, dimension, hardness
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/44—Analysis of texture based on statistical description of texture using image operators, e.g. filters, edge density metrics or local histograms
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Mechanical Engineering (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Robotics (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to an intelligent aluminum bar cutting method and system based on machine vision, comprising the steps of collecting a cross section image to be detected and a standard cross section image after aluminum bar cutting; the method comprises the steps of obtaining gradient directions of pixel points in a cross-section image to be detected, marking the pixel points belonging to the same gradient direction as a set, sorting the pixel points based on the number of the pixel points in each set from large to small, analyzing stability and quality of a cutting edge by calculating edge texture consistency and edge regularity degree of the image to be detected, evaluating similarity between the cross-section image to be detected and a standard cross-section image by cosine similarity, judging that the cutting state is abnormal if the similarity is lower than a set threshold value, stopping aluminum bar cutting work, and avoiding unqualified cutting. The invention solves the production problems caused by uneven cutting, defects or equipment faults.
Description
Technical Field
The invention relates to the technical field of image data processing. More particularly, the invention relates to an intelligent aluminum bar cutting method and system based on machine vision.
Background
With the continuous development of modern manufacturing industry, the cutting process of aluminum bars plays a vital role in a plurality of fields, especially in the processing of high-precision aluminum products. Conventional aluminum bar cutting methods generally rely on manual operations or mechanical control based on fixed parameters, and have problems of cutting accuracy and efficiency, particularly when faced with complex cutting environments, surface flaws or dimensional changes, the cutting quality is prone to instability. Therefore, how to realize high-efficiency, accurate and automatic aluminum bar cutting becomes a technical problem to be solved urgently in the industry.
Conventional aluminum bar cutting methods typically rely on manual operations or fixed length cutting based on mechanical control. The problems of low precision, poor efficiency, poor adaptability to cutting environment and the like exist in the methods, and particularly in mass production, the stability and consistency of the cutting process are difficult to ensure. In order to improve the precision and efficiency of aluminum bar cutting, machine vision technology has been gradually applied to intelligent cutting systems for aluminum bars. The machine vision system acquires image information of the aluminum bar through the camera equipment and analyzes the image information by using an image processing algorithm, so that real-time monitoring and feedback of the cutting process are realized.
The patent application document with the publication number of CN114619152A discloses an intelligent cutting system for aluminum veneer production and manufacturing. According to the method, the comprehensive sharpness and the regularity of the slag dipping area are calculated when the aluminum veneer is cut, and the laser focus position is adjusted in real time, so that the production efficiency is improved, interference caused by misalignment of focuses is avoided, intelligent control of laser focus parameters before production is realized, and the production efficiency is improved. However, the above-mentioned technical solution relies on a specific algorithm to implement intelligent cutting, and does not fully consider the limitation of the algorithm in a complex environment, thereby causing production problems caused by uneven cutting, defects or equipment failure.
Disclosure of Invention
In order to solve the production problems caused by uneven cutting, defects and equipment failure proposed in the background art described above, the present invention provides solutions in various aspects as follows.
In a first aspect, the invention provides an intelligent aluminum bar cutting method based on machine vision, which comprises the steps of collecting a cross-sectional image to be detected and a standard cross-sectional image after aluminum bar cutting, obtaining gradient directions of pixel points in the cross-sectional image to be detected, recording the pixel points belonging to the same gradient direction as a set, sorting the pixel points from large to small based on the number of the pixel points in each set, and calculating edge texture consistency of the cross-sectional image to be detected:In which, in the process,To be with natural constantAs a function of the base of the exponentiation,For the total number of pixels in the cross-sectional image to be detected,To order the number of pixels in the first set,To order the number of pixels in the second set,Calculating the degree of regularity of each edge in the cross-sectional image to be detected, wherein the degree of regularity represents the fluctuation degree of the edge, and calculating the similarity between the cross-sectional image to be detected and the standard cross-sectional image:In which, in the process,For cosine similarity between feature vectors of the cross-sectional image to be detected and the standard cross-sectional image,For the average of all edge regularity in the cross-sectional image to be detected,And if the similarity is smaller than a set threshold value, judging the cutting state as abnormal, and stopping the cutting work of the aluminum bar.
According to the technical scheme, through comprehensively analyzing the multidimensional characteristics of the cross-sectional image of the aluminum bar after cutting, accurate assessment of the cutting state is realized, quality fluctuation can be sensitively identified, and cutting operation is automatically stopped when the cutting state is abnormal. The scheme not only can monitor the quality change in the aluminum bar cutting process in real time, but also can effectively avoid production problems caused by uneven cutting, defects and equipment faults, and improves the cutting precision, efficiency and production safety.
Further, the firstThe degree of regularity of the individual edges is noted as,In which, in the process,Is the firstThe curvature of the individual edges of the strip,Is the firstThe polar difference of the abscissa of all pixel points on each edge,Is the firstThe difference in the ordinate of all pixels on each edge,Is the diameter of the cross-sectional image,In order to take the function of the minimum value,For edge texture consistency of the cross-sectional image to be detected,To be with natural constantAn exponential function of the base.
According to the technical scheme, the regularity and the smoothness of the edges are effectively evaluated by calculating the regularity of each edge. The consistency consideration of the global structure of the image is further enhanced, and the edge quality evaluation is ensured to be not only dependent on local characteristics, but also to consider the smoothness and uniformity of the whole texture. The curvature and the extremely bad influence are weighted through the exponential function, so that the subtle change of the edge shape can be reflected more sensitively, and particularly when the edge is irregular or has defects, the numerical value of the regularity can be obviously reduced, and the fluctuation of the cutting quality can be effectively identified.
Further, the firstThe degree of regularity of the individual edges is noted as,In which, in the process,Is the firstThe curvature of the individual edges of the strip,Is the firstStandard deviation of the abscissa of all pixel points on each edge,Is the firstStandard deviation of the ordinate of all pixels on each edge,Is the diameter of the cross-sectional image,For edge texture consistency of the cross-sectional image to be detected,To be with natural constantAn exponential function of the base.
According to the technical scheme, the edge regularity is evaluated by combining the curvature of the edge and the standard deviation of pixel distribution, so that the edge regularity and smoothness can be accurately quantized. By calculating the degree of dispersion of the abscissa of each edge, the system can reflect the bending degree and fluctuation of the edge, thereby revealing the irregularity in the cutting process. The introduction of edge texture consistency further enhances the consideration of global structural consistency of the image, so that the evaluation is not limited to local features, but also covers the overall cutting quality. By weighting these factors, edge irregularities and potential defects can be identified more sensitively, and especially when the edge shape is abnormal, the regularity value is significantly reduced, thereby effectively detecting problems in the cutting process.
Further, a CCD camera or a CMOS camera is used for collecting the cross-sectional image to be detected and the standard cross-sectional image after the aluminum bar is cut.
Further, the method further comprises the steps of carrying out image graying and median filtering on the cross-sectional image to be detected and the standard cross-sectional image.
Further, a Sobel operator is utilized to obtain the gradient direction of each pixel point in the cross-section image to be detected.
According to the technical scheme, the Sobel operator is used for obtaining the gradient direction of each pixel point in the cross-section image to be detected, so that the edge information in the image can be effectively extracted. The Sobel operator can highlight the region with larger change in the image, especially the edge part, by calculating the gradient value of each pixel point, thereby accurately identifying the details and the irregularity in the cutting process. The extraction of the gradient direction is not only beneficial to identifying the direction and the shape of the edge, but also provides a basis for subsequent edge detection and image analysis, and effectively improves the evaluation accuracy of the cutting quality of the aluminum bar.
Further, the feature vectors of the cross-sectional image to be detected and the standard cross-sectional image are extracted by utilizing a scale invariant feature transformation algorithm or a directional gradient histogram algorithm.
According to the technical scheme, the image feature vector is extracted by using the scale-invariant feature transformation or the direction gradient histogram algorithm, so that the description and recognition capability of the image local feature can be effectively improved. The feature vectors extracted by the two methods not only enhance the stability and accuracy of similarity calculation between the image to be detected and the standard image, but also can be better adapted to image changes under different cutting states, thereby providing a reliable basis for accurate evaluation of cutting quality and helping to find potential quality problems in time in the production process.
In a second aspect, the invention provides an intelligent cutting system for aluminum bars based on machine vision, comprising a memory and a processor, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent cutting method for aluminum bars based on machine vision is realized.
The invention has the beneficial effects that:
According to the invention, the quality of the aluminum bar after cutting is accurately estimated by combining a machine vision technology, and the cutting state is adjusted in real time. The method can effectively identify possible defects and irregularities in the cutting process by utilizing image acquisition, gradient analysis, texture consistency calculation and edge regularity evaluation. By comparing the similarity between the image to be detected and the standard image, the system can sensitively detect tiny cutting deviation and timely discover uneven cutting, cracks or other quality problems. In addition, the image features are extracted by adopting the scale invariant feature transformation and the directional gradient histogram algorithm, so that the system can still keep stable and high-efficiency in the face of different cutting states or external interference. The implementation of the scheme not only improves the monitoring precision of the cutting quality, but also can effectively avoid the production waste caused by equipment failure or improper cutting, and ensures the stability and safety of the production process.
Drawings
Fig. 1 is a flow chart schematically showing an intelligent cutting method of aluminum bars based on machine vision according to an embodiment of the invention;
fig. 2 is a gray image schematically showing a cross section of an aluminum bar after cutting according to an embodiment of the present invention;
fig. 3 is a block diagram schematically illustrating a machine vision-based intelligent aluminum bar cutting system in accordance with an embodiment of the present invention.
Detailed Description
An embodiment of an intelligent aluminum bar cutting method based on machine vision.
As shown in fig. 1, a machine vision-based intelligent aluminum bar cutting method flowchart of an embodiment of the invention comprises the following steps:
s1, collecting a cross section image to be detected and a standard cross section image after cutting an aluminum bar.
In one embodiment, in order to ensure accurate contrast between the cross-sectional image of the cut aluminum bar and the standard cross-sectional image, image acquisition is first performed using a CCD camera or a CMOS camera. The high-resolution cameras can capture fine surface features of the aluminum bar after cutting, and clear and accurate image data are provided for subsequent detection. Compared with the traditional camera, the CCD and CMOS camera have excellent performance in a low illumination environment, can reduce image noise, and improve the quality and stability of acquired images, thereby providing reliable original data for accurate analysis.
Then, graying treatment is carried out on the cross-sectional image to be detected and the standard cross-sectional image. This step converts the color image into a gray scale image, which makes the brightness information of the image more prominent, and reduces unnecessary color information interference, facilitating subsequent analysis. The gray level image can better reflect the tiny defects or irregularities on the aluminum bar cutting surface through the change of the gray level value, and the efficiency and the accuracy of image analysis are improved.
As shown in fig. 2, the cross-section gray scale image of the aluminum bar of the embodiment of the invention after cutting.
After the graying process, median filtering process is performed to effectively remove noise, especially salt and pepper noise, in the image. Median filtering can preserve edge information of an image while smoothing noise regions by replacing current pixel values with median values in pixel neighbors. This has a remarkable effect on improving the image quality, especially when processing an image with high noise. For example, if sparks or smoke generated during cutting affects the quality of the image, median filtering can effectively reduce the interference of these noises with the analysis results, thereby ensuring the sharpness and stability of the image.
S2, acquiring gradient directions of all pixel points in the cross-sectional image to be detected, marking the pixel points belonging to the same gradient direction as a set, and sequencing the set.
In one embodiment, the gradient direction of each pixel point in the cross-sectional image to be detected can be obtained by using a Sobel operator, and the Sobel operator can obtain the gradient value and direction of each pixel point by calculating the gradient in the horizontal direction and the vertical direction.
Next, pixels belonging to the same gradient direction are grouped into one set. Since the cutting process produces regular edges or textures, pixels of the same gradient direction generally represent the same area on the cut surface. For example, all pixels associated with horizontal or vertical edges will have similar gradient directions, belonging to the same set. For this purpose, an angle threshold may be set, and pixels differing by less than a certain angle value in the gradient direction may be grouped, and the threshold may be set between 5 degrees and 10 degrees, although it is also possible to set the threshold according to the actual situation.
Grouping the pixel points according to the gradient direction to obtain each set, and sorting the pixel points from large to small based on the number of the pixel points in each set to obtain a sorted set.
And S3, calculating the edge texture consistency and the regularity degree of each edge of the cross-sectional image to be detected.
In one embodiment, edge texture consistency of the cross-sectional image to be detected is calculated,In which, in the process,To be with natural constantAs a function of the base of the exponentiation,For the total number of pixels in the cross-sectional image to be detected,To order the number of pixels in the first set,To order the number of pixels in the second set,The average value of the number of the pixel points in the rest sets;
by calculating the edge texture consistency of the cross-sectional image to be detected, the structural regularity of the edge region in the image can be quantified. Specifically, parameters involved in the formula reflect the distribution condition of textures of different areas in the image by sequencing the pixel point sets and processing the pixel point sets by combining the difference of the pixel point numbers. And conversely, if the texture consistency is weaker, the edge texture consistency is smaller, which means that more obvious uneven cutting, cracks or other defects exist in the image.
Calculating the regularity of each edge in the cross-sectional image to be detected, and then obtaining the firstThe degree of regularity of the individual edges is noted as,In which, in the process,Is the firstThe curvature of the individual edges of the strip,Is the firstThe polar difference of the abscissa of all pixel points on each edge,Is the firstThe difference in the ordinate of all pixels on each edge,Is the diameter of the cross-sectional image,In order to take the function of the minimum value,For edge texture consistency of the cross-sectional image to be detected,To be with natural constantAn exponential function of the base.
By calculating the degree of regularity of each edge in the cross-sectional image to be detected, the regularity and smoothness of the edges can be quantified, and then accurate assessment of cutting quality can be provided. Specifically, parameters such as curvature, range, image diameter and the like introduced in the formula can comprehensively consider the bending degree and the distribution range of the edge shape, and the regularity of the edge shape can be further adjusted through an exponential function. And the introduction of the edge texture consistency provides a global consistency reference for the calculation, so that the detection result is ensured to be more stable and reliable. When the edge is of higher regularity, it is indicated that the edge is regular and smooth in shape and the cutting process is ideal, whereas if the edge is of lower regularity, it may indicate that there is uneven cutting or other quality problems.
In another embodiment, the firstThe degree of regularity of the individual edges is noted as,In which, in the process,Is the firstThe curvature of the individual edges of the strip,Is the firstStandard deviation of the abscissa of all pixel points on each edge,Is the firstStandard deviation of the ordinate of all pixels on each edge,Is the diameter of the cross-sectional image,For edge texture consistency of the cross-sectional image to be detected,To be with natural constantAn exponential function of the base.
By calculating the regularity of the edge, the regularity of the edge shape is effectively quantified. Similar to the previous solution, the formula combines the curvature of the edge, the standard deviation of the abscissa, and the image diameter, which can reflect the stability and consistency of the edge shape. The standard deviation is used as a discrete degree index of the edge pixel coordinates, whether the edge has obvious bending or irregularity can be estimated, and meanwhile, the influence of curvature and coordinate dispersion on the regularity can be further enhanced through exponential function adjustment.
And S4, calculating the similarity between the cross-section image to be detected and the standard cross-section image, and if the similarity is smaller than a set threshold value, judging the cutting state as abnormal and stopping the cutting work of the aluminum bar.
The set threshold value may be 0.8, which may be determined according to actual situations.
In one embodiment, the similarity between the cross-sectional image to be detected and the standard cross-sectional image is calculated,In which, in the process,For cosine similarity between feature vectors of the cross-sectional image to be detected and the standard cross-sectional image,For the average of all edge regularity in the cross-sectional image to be detected,Is the average value of all edge regularity in the standard cross-sectional image;
By calculating the similarity between the cross-section image to be detected and the standard cross-section image, the accurate assessment of the aluminum bar cutting quality is realized. The calculation of the similarity combines two parts of information, namely, firstly, cosine similarity between feature vectors of an image to be detected and a standard image, wherein the similarity can reflect the matching degree of the two images on the whole feature, and secondly, the local cutting quality of the two images is compared through edge regularity. The average value of the edge regularity can effectively capture the smoothness and consistency of the cut edges in the image, thereby providing fine granularity information of the cut quality. Particularly, the sensitivity of the cutting precision and the quality difference is enhanced by introducing an exponential function to weight the edge regularity difference in the formula, so that the change of the similarity value is more obvious when the quality fluctuation is larger, and the quick identification of potential anomalies is ensured.
And extracting the feature vectors of the cross-section image to be detected and the standard cross-section image by using a scale invariant feature transformation algorithm or a directional gradient histogram algorithm, so that the adaptability of the image to scale and rotation changes is further enhanced. The SIFT algorithm can efficiently describe the uniqueness of the image by extracting the key points and the local texture features around the key points, and particularly has strong robustness to feature changes under complex cutting forms, while the HOG algorithm can effectively capture the changes of edges and local shapes by capturing gradient information of the image, and is excellent in local feature changes in the image.
If the similarity is smaller than the set threshold, the system can automatically judge that the cutting state is abnormal and timely trigger an alarm for stopping the cutting operation. The mechanism can not only avoid the quality problem of the aluminum bar caused by uneven cutting, cracks or defects, but also effectively avoid the production waste caused by equipment failure or improper operation.
According to the scheme, the accurate monitoring and control of the aluminum bar cutting process are realized through the intelligent cutting method based on machine vision. By collecting the cross-section image to be detected and the standard image, carrying out gradient direction analysis, edge texture consistency evaluation and regularity calculation on the images, the system can comprehensively analyze the cutting quality of the aluminum bar and detect the irregularity and fluctuation of the edge. By combining with similarity analysis of images, the system can accurately identify abnormal conditions in the cutting process and judge whether an unqualified cutting state exists or not according to a set threshold value, so that automatic stop is realized. The method improves the image quality and reduces noise interference through image graying and filtering treatment, improves the accuracy of edge detection and image feature matching through Sobel operator and feature extraction algorithm, and enhances the adaptability of the system to different cutting conditions. In the whole, the scheme of the invention improves the intelligent level of the aluminum bar cutting process, ensures the stability and production efficiency of the cutting quality, reduces human intervention, and optimizes the safety and reliability in the cutting process.
Machine vision-based aluminum bar intelligent cutting system embodiment:
As shown in fig. 3, the structural block diagram of the intelligent cutting system for aluminum bars based on machine vision according to the embodiment of the invention comprises a processor and a memory.
The invention further provides an intelligent aluminum bar cutting system based on machine vision. As shown in fig. 3, the system comprises a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent aluminum bar cutting method based on machine vision is realized.
The intelligent aluminum bar cutting system based on machine vision further comprises other components such as a communication interface and the like which are well known to those skilled in the art, and the arrangement and the functions of the intelligent aluminum bar cutting system are known in the art, so that the intelligent aluminum bar cutting system is not repeated.
In the context of this patent, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (ENHANCED DYNAMIC Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid storage cube HMC (Hybrid Memory Cube), or the like, or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device. Any of the applications or modules described herein may be implemented by computer-readable/executable instructions stored on or otherwise maintained by such a computer-readable medium.
In the description of the present specification, the meaning of "a plurality", "a number" or "a plurality" is at least two, for example, two, three or more, etc., unless explicitly defined otherwise.
While various embodiments of the present invention have been shown and described herein, it will be obvious to those skilled in the art that such embodiments are provided by way of example only. Many modifications, changes, and substitutions will now occur to those skilled in the art without departing from the spirit and scope of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in practicing the invention.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510638521.8A CN120163819B (en) | 2025-05-19 | 2025-05-19 | Aluminum bar intelligent cutting method and system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510638521.8A CN120163819B (en) | 2025-05-19 | 2025-05-19 | Aluminum bar intelligent cutting method and system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120163819A CN120163819A (en) | 2025-06-17 |
| CN120163819B true CN120163819B (en) | 2025-08-22 |
Family
ID=96004330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510638521.8A Active CN120163819B (en) | 2025-05-19 | 2025-05-19 | Aluminum bar intelligent cutting method and system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120163819B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118864472A (en) * | 2024-09-26 | 2024-10-29 | 陕西新宝磁性材料有限公司 | A production quality detection method for magnetic materials |
| CN119379660A (en) * | 2024-11-18 | 2025-01-28 | 南兴装备股份有限公司 | Plate texture consistency recognition method and system based on deep learning |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7003161B2 (en) * | 2001-11-16 | 2006-02-21 | Mitutoyo Corporation | Systems and methods for boundary detection in images |
| JP4714647B2 (en) * | 2006-07-31 | 2011-06-29 | 日本放送協会 | Cut point detection device and cut point detection program |
| CN213531030U (en) * | 2020-11-13 | 2021-06-25 | 四川正泰晟坤铝业有限公司 | Aluminum plate cutting feed arrangement |
| CN119458633A (en) * | 2025-01-16 | 2025-02-18 | 深圳市汇星龙科技有限公司 | Automatic positioning method for cutting screen of cutting machine based on visual analysis |
-
2025
- 2025-05-19 CN CN202510638521.8A patent/CN120163819B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118864472A (en) * | 2024-09-26 | 2024-10-29 | 陕西新宝磁性材料有限公司 | A production quality detection method for magnetic materials |
| CN119379660A (en) * | 2024-11-18 | 2025-01-28 | 南兴装备股份有限公司 | Plate texture consistency recognition method and system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120163819A (en) | 2025-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111539938B (en) | Method, system, medium and electronic terminal for detecting curvature of rolled strip steel strip head | |
| CN117173187A (en) | An intelligent detection system for valve faults | |
| CN119693358B (en) | Connector surface defect detection method and system based on image processing | |
| CN119295735B (en) | Image recognition method and system for contact rust | |
| CN119417817B (en) | Paint defect detection method and system based on machine vision | |
| CN119228779A (en) | A method and system for detecting cigarette package appearance defects based on deep learning | |
| CN116128873A (en) | Bearing retainer detection method, device and medium based on image recognition | |
| Tang et al. | Surface inspection system of steel strip based on machine vision | |
| Lei et al. | Boundary recognition of ship planar components from point clouds based on trimmed delaunay triangulation | |
| CN120163819B (en) | Aluminum bar intelligent cutting method and system based on machine vision | |
| CN119919387B (en) | Method, system, product and medium for detecting surface flaws of optical film | |
| CN119228795A (en) | A method and system for nondestructive testing of the surface of spindle parts | |
| CN117173185B (en) | Method and device for detecting area of rolled plate, storage medium and computer equipment | |
| TWI812002B (en) | Cutting tool image detecting method | |
| CN119091193A (en) | A real-time image recognition scratch detection system and method based on deformation network | |
| CN118587496A (en) | Automatic identification system and method of parts processing accuracy based on computer vision | |
| CN117474916A (en) | Image detection method, electronic equipment and storage medium | |
| CN117314901A (en) | A scale-adaptive neural network system for chip detection | |
| CN120411116B (en) | A method and system for detecting shell defects based on machine vision | |
| CN120976216B (en) | Casting surface defect detection method and system | |
| CN119090816B (en) | A screw locking quality detection method and system based on machine vision | |
| CN119338807B (en) | Laser processing heat distribution calculation method | |
| CN120495224B (en) | Image Recognition-Based Method for Detecting Printing Accuracy of Color and Pattern Designs on Color-Coated Steel Sheets | |
| CN119313656B (en) | Ocean metal corrosion degree detection method based on image processing | |
| CN118864516B (en) | Method and system for visualizing surface area ash of pipe body |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |