CN117593297B - Jig identification and counting system and method based on image processing - Google Patents
Jig identification and counting system and method based on image processing Download PDFInfo
- Publication number
- CN117593297B CN117593297B CN202410070576.9A CN202410070576A CN117593297B CN 117593297 B CN117593297 B CN 117593297B CN 202410070576 A CN202410070576 A CN 202410070576A CN 117593297 B CN117593297 B CN 117593297B
- Authority
- CN
- China
- Prior art keywords
- jig
- camera
- image
- micro
- processing module
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 15
- 230000004927 fusion Effects 0.000 claims abstract description 17
- 239000000725 suspension Substances 0.000 claims abstract description 14
- 238000005286 illumination Methods 0.000 claims abstract 2
- 238000003860 storage Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 7
- 230000001678 irradiating effect Effects 0.000 claims description 7
- 230000001174 ascending effect Effects 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Image Input (AREA)
Abstract
The invention relates to a jig identification counting system and method based on image processing, comprising a conveying frame for conveying jigs, wherein a support column is arranged at the side part of the conveying frame, and a first camera is connected with the support column through a connecting beam; the system also comprises a light mechanism, wherein the light mechanism comprises a linear motor, a suspension bracket and a square fixed frame, the first camera is positioned right above the fixed frame, the four inner side walls of the fixed frame are respectively provided with a strip-shaped irradiation lamp, the linear motor is fixedly connected with the top of the support column, an output shaft of the linear motor is fixedly connected with the upper end of the suspension bracket, and the lower end of the suspension bracket is fixedly connected with the fixed frame; the system further comprises a control device for controlling the carriage, the linear motor, the illumination lamp and the first camera. The system can realize automatic identification of the jig, and reduces the manual workload; in addition, the system adopts the technical means of identifying the dark area after image fusion and superposition, can eliminate the influence of the height of the protruding part on the surface of the jig on the identification accuracy, and has higher accuracy.
Description
Technical Field
The invention relates to the technical field of jig production management, in particular to a jig identification and counting system and method based on image processing.
Background
The jig is a tool for assisting in controlling the position or the action, and can be divided into a process assembly jig, a project test jig and a circuit board test jig.
In order to realize fine production management, the production quantity of various jigs needs to be counted in the jig production process. In the prior art, the identification code is posted on the jig by manpower, and then the identification and the counting of the jig are realized by code scanning; or automatically identifying and counting the jigs on the assembly line by an image identification technology. The former approach requires human involvement, is prone to error and is inefficient. While the latter approach may enable automatic identification, it has significant drawbacks.
The existing image recognition and counting method is that an image is shot right above a jig through a camera, then the outline of the jig and the protruding part on the surface of the jig in the image are recognized, and only the outline shape of the jig body and the shape and the position of the protruding part can be recognized in the mode.
In practice, for the same type of jig, there are also a plurality of models under the same type, and generally, the contour formation of the same type of jig is the same or similar. For the same kind of jigs with different models, the protruding parts on the surfaces of the jigs may have height differences. Obviously, the accuracy of the existing image recognition technology for recognizing the jig is easily interfered by the height of the protruding part of the jig, and the accuracy is required to be improved.
Disclosure of Invention
Based on the above expression, the invention provides a jig identification and counting system and method based on image processing, which can identify a jig more accurately and efficiently.
The technical scheme for solving the technical problems is as follows:
The jig identification and counting system based on image processing comprises a conveying frame for conveying jigs, wherein a support is arranged on the side part of the conveying frame, a first camera is connected with the support through a connecting beam and is positioned right above the conveying frame, and the first camera is used for shooting jig images on the conveying frame and outputting image data; the system also comprises a light mechanism, wherein the light mechanism comprises a linear motor, a suspension bracket and a square fixed frame, the fixed frame covers the periphery of the first camera, the first camera is positioned right above the fixed frame, the four inner side walls of the fixed frame are provided with long strip-shaped irradiation lamps, the first irradiation lamp, the second irradiation lamp, the third irradiation lamp and the fourth irradiation lamp are sequentially arranged in the anticlockwise direction, the linear motor is fixedly connected with the top of the support column, an output shaft of the linear motor is fixedly connected with the upper end of the suspension bracket, and the lower end of the suspension bracket is fixedly connected with the fixed frame; a photoelectric sensor is arranged on the side part of the conveying frame; the system also comprises a control device for controlling the conveying frame, the linear motor, the illuminating lamp and the first camera, wherein the photoelectric sensor is connected with the control device.
As a preferable scheme: the control device comprises an image acquisition module, a micro-processing module, a signal acquisition module, a conveying control module, a motor driving module and a light driving module, wherein the output end of a first camera is connected with the input end of the image acquisition module; the micro-processing module is internally provided with a storage unit, an image processing unit, a comparison unit and a counting unit.
As a preferable scheme: manually placing the jig on a conveying frame, conveying the jig by the conveying frame, detecting the jig by a photoelectric sensor when the jig passes by the photoelectric sensor, feeding back a trigger signal to a micro-processing module, sending a pause signal to a conveying control module after the micro-processing module receives the trigger signal, and controlling a traction motor of the conveying frame to pause after the conveying control module receives the pause signal, wherein the conveying belt is paused at the current position; after the conveyor belt is suspended, the micro-processing module sends a control signal to the light driving module, at the moment, the light driving module controls the first irradiation lamp to be lightened at a first height position, the first irradiation lamp irradiates the jig from the right, the right edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera to shoot a first image of the jig; the micro-processing module sends an ascending signal to the motor driving module, the motor driving module receives the ascending signal and then drives the linear motor to act, so that the linear motor drives the fixed frame to ascend to a second height, the micro-processing module controls the second irradiation lamp to light up after the fixed frame ascends to the second height, the second irradiation lamp irradiates the jig from above, the upper edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera to shoot a second image of the jig; then the micro-processing module controls the linear motor to drive the fixed frame to rise to a third height, when the fixed frame rises to the third height, the micro-processing module controls the third irradiation lamp to light, the third irradiation lamp irradiates the jig from the left, the left edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera to shoot a third image of the jig; then the micro-processing module controls the linear motor to drive the fixed frame to rise to a fourth height, and after the fixed frame rises to the fourth height, the micro-processing module controls the fourth irradiation lamp to illuminate, the fourth irradiation lamp irradiates the jig from below, the lower edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera to shoot a fourth image of the jig; after the four groups of images are shot, the micro-processing module controls the conveyer belt to continue to run; the image processing unit fuses the four groups of images while the conveyor belt resumes operation to obtain a fused image; the image processing unit identifies and extracts the upper, lower, left and right edge contours of the fusion image, and identifies and extracts the number, distribution and black depth of dark areas in the fusion image; the comparison unit compares the outline and the identification characteristic of the jig in the fusion image with the outline and the identification characteristic of the jig stored in the storage unit in advance, and outputs the corresponding jig model after the comparison is successful, and the counting unit performs classification counting according to the result output by the comparison unit.
As a preferable scheme: a second camera is arranged on the conveying frame and positioned in front of the first camera through a fixing frame, the second camera is positioned right above the conveying frame and faces the conveying frame, and the output end of the second camera is connected with the input end of the image acquisition module; a manipulator is arranged at the side edge of the conveying frame and positioned between the first camera and the second camera, the control device further comprises a manipulator driving module for controlling the manipulator to move, and the manipulator driving module is connected with the micro-processing module; in the process of conveying the jig, the jig passes through a second camera, the second camera shoots an image of the jig and transmits image data to a micro-processing module, an image processing unit identifies and extracts the outline of one side of the jig in the image shot by the second camera, and the image processing unit calculates an included angle between the side and the frame of an image picture, wherein the included angle is the deviation angle of the jig; the micro-processing module feeds back the deviation angle to the manipulator driving module, and the manipulator driving module converts the deviation angle into action parameters of the manipulator; when the conveying belt is suspended, the manipulator clamps the jig according to the deviation angle and the action parameter of the jig below the manipulator, and rotates the jig by a corresponding angle, so that the jig is aligned.
As a preferable scheme: the camera is characterized in that the first camera is movably connected with the connecting beam, the main body of the first camera is fixedly connected with the connecting beam, a pair of guide rods of vertical lines are fixed on the connecting beam, the guide rods penetrate through the movable beam, the movable beam can move up and down along the guide rods, threaded holes are formed in the movable beam, adjusting bolts are arranged on the connecting beam, the adjusting bolts are rotatably connected with the connecting beam, and the adjusting bolts are screwed into the threaded holes and are matched with the threaded holes.
The jig identification and counting method based on image processing is suitable for the jig identification and counting system:
Placing the jig on a conveying frame, conveying the jig by the conveying frame, and controlling the conveying belt to be suspended when the jig moves below the first camera; controlling a first irradiation lamp to irradiate the jig from the right at a first height position, irradiating the right edge of the jig and shadows on the surface of the jig, and simultaneously controlling a first camera to shoot a first image of the jig; controlling a second irradiation lamp to irradiate the jig from above at a second height, irradiating the upper edge of the jig and shadows on the surface of the jig, and simultaneously controlling the first camera to shoot a second image of the jig; then, a third irradiation lamp is controlled to irradiate the jig from the left at a third height, the left edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, a first camera is controlled to shoot a third image of the jig; then, a fourth irradiation lamp is controlled to irradiate the jig from the lower part at a fourth height, the lower edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the first camera is controlled to shoot a fourth image of the jig; after the four groups of images are shot, the conveyer belt is controlled to continue to run, the four groups of images are fused while the conveyer belt resumes to run, a fused image is obtained, the upper, lower, left and right edge contours of the fused image are identified and extracted, and the number, distribution and black depth of dark areas in the fused image are identified and extracted; and comparing the outline and the identification characteristic of the jig in the fusion image with the outline and the identification characteristic of the jig stored in the storage unit in advance, outputting the corresponding jig model after the comparison is successful, and classifying and counting the jigs according to the comparison result.
Compared with the prior art, the technical scheme of the application has the following beneficial technical effects:
Through the mode, the automatic identification jig can be realized, manual code scanning identification is not needed, the manual workload can be reduced, and the system can ensure the accuracy of identification and has high working efficiency and reliability. In addition, compared with a common mode of shooting a single image right above, the system adopts a technical means of identifying a dark area after image fusion and superposition, can eliminate the influence of the height of the protruding part on the surface of the jig on the identification accuracy, and has higher accuracy and wider application range.
Drawings
FIG. 1 is a schematic diagram of a fixture;
FIG. 2 is a schematic diagram of a system;
Fig. 3 is an enlarged view of a portion a in fig. 2;
Fig. 4 is a schematic diagram of a control device.
In the drawings, the list of components represented by the various numbers is as follows:
1. A jig body; 2. a boss; 3. a carriage; 4. a conveyor belt; 5. a fixing frame; 6. a second camera; 7. a manipulator; 8. a support post; 9. a connecting beam; 10. a first camera; 11. a linear motor; 12. a suspension bracket; 13. a fixed frame; 14. a radiation lamp; 15. a photoelectric sensor; 16. a guide rod; 17. a movable beam; 18. a threaded hole; 19. an adjusting bolt; 20. and a limiting ring.
Detailed Description
Embodiment one:
Referring to fig. 2 and 3, a jig recognition and counting system based on image processing includes a carriage 3 for transporting jigs, a vertical support column 8 is fixed at a side portion of the carriage 3, a connecting beam 9 extending transversely is fixed on the support column 8, a first camera 10 is fixed at an end portion of the connecting beam 9, the first camera 10 is located right above the carriage 3, and the first camera 10 is used for photographing jig images on the carriage 3 and outputting image data.
The system also comprises a light mechanism which comprises a linear motor 11, a suspension bracket 12 and a square fixed frame 13. The periphery of the first camera 10 is covered by the fixed frame 13, the first camera 10 is located right above the fixed frame 13, and the four inner side walls of the fixed frame 13 are provided with strip-shaped irradiation lamps 14 (a first irradiation lamp, a second irradiation lamp, a third irradiation lamp and a fourth irradiation lamp in turn along the anticlockwise direction). The linear motor 11 is fixedly connected with the top of the support column 8, an output shaft of the linear motor 11 is fixedly connected with the upper end of the suspension bracket 12, and the lower end of the suspension bracket 12 is fixedly connected with the fixed frame 13.
The suspension bracket 12 can be driven to lift by controlling the linear motor 11 to move, so that the fixed frame 13 is driven to lift synchronously.
A photoelectric sensor 15 is mounted on the side of the carriage 3, the photoelectric sensor 15 is used for detecting a jig on the carriage 3, the photoelectric sensor 15 is arranged near the lower part of the first camera 10, and when the jig on the carriage 3 enters the shooting range of the first camera 10, the photoelectric sensor 15 is triggered and outputs a trigger signal.
Referring to fig. 4, the system further includes a control device including a signal receiving unit for image acquisition module, a micro-processing module, a signal acquisition module transmission control module, a motor driving module and a light driving module, wherein the output end of the first camera 10 is connected with the input end of the image acquisition module, the output end of the image acquisition module is connected with the data receiving end of the micro-processing module, the output end of the photoelectric sensor 15 is connected with the input end of the signal acquisition module, the output end of the signal acquisition module is connected with the signal receiving end of the micro-processing module, the signal input end of the light driving module is connected with the signal output end of the micro-processing module, and the driving signal output end of the light driving module is connected with the irradiation lamp 14.
The signal input end of the motor driving module is connected with the signal output end of the micro-processing module, and the driving signal output end of the motor driving module is connected with the driving end of the linear motor 11.
The signal input end of the conveying control module is connected with the signal output end of the micro-processing module, and the output end of the conveying control module is connected with the traction motor of the conveying frame 3.
The micro-processing module is internally provided with a storage unit, an image processing unit, a comparison unit and a counting unit. Wherein the storage unit is used for storing image data; the image processing unit is used for processing the image to extract the outline and the identification characteristic of the jig; the comparison unit is used for comparing the outline of the jig with the outline and the identification characteristic preset by the identification characteristic so as to judge the type and the model of the jig and outputting a comparison result; the counting unit is used for counting according to the comparison result output by the comparison unit.
The working principle of the system is as follows:
in the initial state, the square frame is located at its lowest position, i.e. at a first height.
After the system operates, the jig is manually placed on the conveying frame 3, the conveying frame 3 conveys the jig to move, and when the jig passes through the photoelectric sensor 15, the photoelectric sensor 15 detects the jig and feeds a trigger signal back to the micro-processing module. The micro-processing module receives the trigger signal and then sends a pause signal to the conveying control module, and the conveying control module controls the traction motor of the conveying frame 3 to pause after receiving the pause signal, so that the conveying belt 4 is paused at the current position.
After the conveyor belt 4 is suspended, the micro-processing module sends a control signal to the light driving module, at the moment, the light driving module controls the first irradiation lamp to be turned on (the other three groups of irradiation lamps are turned off), the first irradiation lamp irradiates the jig from the right, the right edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera 10 to shoot a first image of the jig; the micro-processing module sends an ascending signal to the motor driving module, the motor driving module receives the ascending signal and then drives the linear motor 11 to act, so that the linear motor 11 drives the fixed frame 13 to ascend to a second height, when the fixed frame 13 ascends to the second height, the micro-processing module controls the second irradiation lamp to be turned on (the other three groups of irradiation lamps are turned off), the second irradiation lamp irradiates the jig from above, the upper edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera 10 to shoot a second image of the jig; then the micro-processing module controls the linear motor 11 to drive the fixed frame 13 to rise to a third height, when the fixed frame 13 rises to the third height, the micro-processing module controls the third irradiation lamp to be turned on (the other three groups of irradiation lamps are turned off), the third irradiation lamp irradiates the jig from the left, the left edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera 10 to shoot a third image of the jig; then the micro-processing module controls the linear motor 11 to drive the fixed frame 13 to rise to the fourth height, when the fixed frame 13 rises to the fourth height, the micro-processing module controls the fourth irradiation lamp to be turned on (the other three groups of irradiation lamps are turned off), the fourth irradiation lamp irradiates the jig from the lower part, the lower edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera 10 to shoot a fourth image of the jig.
After the four groups of images are shot, the micro-processing module controls the conveyer belt 4 to continue to run. And the image processing unit fuses the four groups of images while the conveyor belt 4 resumes operation, so as to obtain a fused image. In the fusion image, shadows generated by irradiating the surface of the jig from different directions are mutually overlapped, so that black depths of different dark areas of the fusion image are different. In the fused image, the number and distribution of dark areas and the black depth of each dark area can be used as the identification characteristic of each jig.
The image processing unit recognizes and extracts the upper, lower, left and right edge contours of the fusion image, and recognizes and extracts the number, distribution and black depth of dark areas in the fusion image.
The comparison unit compares the outline and the identification characteristic of the jig in the fusion image with the outline and the identification characteristic of the jig stored in the storage unit in advance, and outputs the corresponding jig model after the comparison is successful, and the counting unit performs classification counting according to the result output by the comparison unit.
When the next set of jigs is detected by the photoelectric sensor 15, the above steps are repeated.
Through the mode, the automatic identification jig can be realized, manual code scanning identification is not needed, the manual workload can be reduced, and the system can ensure the accuracy of identification and has high working efficiency and reliability.
In addition, compared with a common mode of shooting a single image right above, the system adopts a technical means of identifying a dark area after image fusion and superposition, can eliminate the influence of the height of the protruding part 2 on the surface of the jig on the identification accuracy, and has wider application range.
Considering that in the process of conveying the jig, a worker may have a larger deviation in the direction of the jig due to the fact that the worker is placed on the conveying frame 3 without standardization, so that a larger included angle exists between the irradiation lamp 14 and the central axis of the jig when the jig moves to the lower side of the first camera 10, and when the irradiation lamp 14 irradiates the jig, shadows generated by the convex part 2 on the surface of the jig may be obviously distorted, so that adverse effects on subsequent processing and recognition are caused.
Referring to fig. 2, a second camera 6 is further mounted on the carriage 3 in front of the first camera 10 through a fixing frame 5, the second camera 6 is located right above the carriage 3 and faces the carriage 3, and an output end of the second camera 6 is connected with an input end of the image acquisition module.
In addition, a robot 7 is provided between the first camera 10 and the second camera 6 at the side of the carriage 3. The control device in this embodiment further includes a manipulator 7 driving module for controlling the movement of the manipulator 7, where the manipulator 7 driving module is connected with the microprocessor module.
In the process of conveying the jig, the jig passes through the second camera 6, the second camera 6 shoots an image of the jig and transmits image data to the micro-processing module, the image processing unit identifies and extracts the outline of one edge of the jig in the image shot by the second camera 6, and the image processing unit calculates an included angle between the edge and the frame of the image picture, wherein the included angle is the deviation angle of the jig.
The micro-processing module feeds back the deviation angle to the driving module of the manipulator 7, and the driving module of the manipulator 7 converts the deviation angle into the action parameters of the manipulator 7. When a certain jig moves below the first camera 10, the next group of jigs positioned at the rear of the jig just moves below the manipulator 7, and when the conveyor belt 4 is suspended, the manipulator 7 clamps the jig according to the deviation angle and the action parameter of the jig below the manipulator and rotates the jig by a corresponding angle, so that the jig is straightened; at the next beat of the conveyor belt 4, the jig moves under the first camera 10.
By the aid of the method, the shadow area in the image can be effectively prevented from being distorted, and accuracy of subsequent image processing and recognition is guaranteed.
Referring to fig. 2 and 3, in this embodiment, the first camera 10 is movably connected to the connection beam 9, specifically: the main body of the first camera 10 is fixedly connected with a movable beam 17, a pair of vertical guide rods 16 are fixed on a connecting beam 9, the guide rods 16 penetrate through the movable beam 17, so that the movable beam 17 can move up and down along the guide rods 16, a threaded hole 18 is formed in the movable beam 17, an adjusting bolt 19 is arranged on the connecting beam 9, the adjusting bolt 19 is rotatably connected with the connecting beam 9, and the adjusting bolt 19 is screwed into the threaded hole 18 and is matched with the threaded hole 18; the movable beam 17 can be driven to move up and down by screwing the adjusting bolt 19, so that the height position of the first camera 10 is changed, and the system debugging requirement is met. A pair of stopper rings 20 for preventing upward and downward movement thereof are installed on the adjusting bolt 19.
Embodiment two:
a jig identification counting method based on image processing specifically comprises the following steps:
Placing the jig on a conveying frame, conveying the jig by the conveying frame, and controlling the conveying belt to be suspended when the jig moves below the first camera; controlling a first irradiation lamp to irradiate the jig from the right at a first height position, irradiating the right edge of the jig and shadows on the surface of the jig, and simultaneously controlling a first camera to shoot a first image of the jig; controlling a second irradiation lamp to irradiate the jig from above at a second height, irradiating the upper edge of the jig and shadows on the surface of the jig, and simultaneously controlling the first camera to shoot a second image of the jig; then, a third irradiation lamp is controlled to irradiate the jig from the left at a third height, the left edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, a first camera is controlled to shoot a third image of the jig; then, a fourth irradiation lamp is controlled to irradiate the jig from the lower part at a fourth height, the lower edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the first camera is controlled to shoot a fourth image of the jig; after the four groups of images are shot, the conveyer belt is controlled to continue to run, the four groups of images are fused while the conveyer belt resumes to run, a fused image is obtained, the upper, lower, left and right edge contours of the fused image are identified and extracted, and the number, distribution and black depth of dark areas in the fused image are identified and extracted; and comparing the outline and the identification characteristic of the jig in the fusion image with the outline and the identification characteristic of the jig stored in the storage unit in advance, outputting the corresponding jig model after the comparison is successful, and classifying and counting the jigs according to the comparison result.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (4)
1. A jig identification counting system based on image processing is characterized in that: the device comprises a conveying frame for conveying jigs, wherein a support is arranged on the side part of the conveying frame, a first camera is connected with the support through a connecting beam and is positioned right above the conveying frame, and the first camera is used for shooting jig images on the conveying frame and outputting image data; the system also comprises a light mechanism, wherein the light mechanism comprises a linear motor, a suspension bracket and a square fixed frame, the fixed frame covers the periphery of the first camera, the first camera is positioned right above the fixed frame, the four inner side walls of the fixed frame are provided with long strip-shaped irradiation lamps, the first irradiation lamp, the second irradiation lamp, the third irradiation lamp and the fourth irradiation lamp are sequentially arranged in the anticlockwise direction, the linear motor is fixedly connected with the top of the support column, an output shaft of the linear motor is fixedly connected with the upper end of the suspension bracket, and the lower end of the suspension bracket is fixedly connected with the fixed frame; a photoelectric sensor is arranged on the side part of the conveying frame; the system also comprises a control device for controlling the conveying frame, the linear motor, the illumination lamp and the first camera, wherein the photoelectric sensor is connected with the control device; the control device comprises an image acquisition module, a micro-processing module, a signal acquisition module, a conveying control module, a motor driving module and a light driving module, wherein the output end of a first camera is connected with the input end of the image acquisition module; the micro-processing module is internally provided with a storage unit, an image processing unit, a comparison unit and a counting unit; manually placing the jig on a conveying frame, conveying the jig by the conveying frame, detecting the jig by a photoelectric sensor when the jig passes by the photoelectric sensor, feeding back a trigger signal to a micro-processing module, sending a pause signal to a conveying control module after receiving the feedback signal by the micro-processing module, and controlling a traction motor of the conveying frame to pause after receiving the pause signal by the conveying control module, wherein the conveying belt is paused at the current position; after the conveyor belt is suspended, the micro-processing module sends a control signal to the light driving module, at the moment, the light driving module controls the first irradiation lamp to be lightened at a first height position, the first irradiation lamp irradiates the jig from the right, the right edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera to shoot a first image of the jig; the micro-processing module sends an ascending signal to the motor driving module, the motor driving module receives the ascending signal and then drives the linear motor to act, so that the linear motor drives the fixed frame to ascend to a second height, the micro-processing module controls the second irradiation lamp to light up after the fixed frame ascends to the second height, the second irradiation lamp irradiates the jig from above, the upper edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera to shoot a second image of the jig; then the micro-processing module controls the linear motor to drive the fixed frame to rise to a third height, when the fixed frame rises to the third height, the micro-processing module controls the third irradiation lamp to light, the third irradiation lamp irradiates the jig from the left, the left edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera to shoot a third image of the jig; then the micro-processing module controls the linear motor to drive the fixed frame to rise to a fourth height, and after the fixed frame rises to the fourth height, the micro-processing module controls the fourth irradiation lamp to illuminate, the fourth irradiation lamp irradiates the jig from below, the lower edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the micro-processing module controls the first camera to shoot a fourth image of the jig; after the four groups of images are shot, the micro-processing module controls the conveyer belt to continue to run; the image processing unit fuses the four groups of images while the conveyor belt resumes operation to obtain a fused image; the image recognition unit recognizes and extracts the upper, lower, left and right edge contours of the fusion image, and recognizes and extracts the number, distribution and black depth of dark areas in the fusion image; the comparison unit compares the outline and the identification characteristic of the jig in the fusion image with the outline and the identification characteristic of the jig stored in the storage unit in advance, and outputs the corresponding jig model after the comparison is successful, and the counting unit performs classification counting according to the result output by the comparison unit.
2. The image processing-based jig recognition and counting system according to claim 1, characterized in that: a second camera is arranged on the conveying frame and positioned in front of the first camera through a fixing frame, the second camera is positioned right above the conveying frame and faces the conveying frame, and the output end of the second camera is connected with the input end of the image acquisition module; a manipulator is arranged at the side edge of the conveying frame and positioned between the first camera and the second camera, the control device further comprises a manipulator driving module for controlling the manipulator to move, and the manipulator driving module is connected with the micro-processing module; in the process of conveying the jig, the jig passes through a second camera, the second camera shoots an image of the jig and transmits image data to a micro-processing module, the image processing module recognizes and extracts the outline of one side of the jig in the image shot by the second camera, and the image processing module calculates an included angle between the side and the frame of an image picture, wherein the included angle is the deviation angle of the jig; the micro-processing module feeds back the deviation angle to the manipulator driving module, and the manipulator driving module converts the deviation angle into action parameters of the manipulator; when the conveying belt is suspended, the manipulator clamps the jig according to the deviation angle and the action parameter of the jig below the manipulator, and rotates the jig by a corresponding angle, so that the jig is aligned.
3. The image processing-based jig recognition and counting system according to claim 1, characterized in that: the camera is characterized in that the first camera is movably connected with the connecting beam, the main body of the first camera is fixedly connected with the connecting beam, a pair of guide rods of vertical lines are fixed on the connecting beam, the guide rods penetrate through the movable beam, the movable beam can move up and down along the guide rods, threaded holes are formed in the movable beam, adjusting bolts are arranged on the connecting beam, the adjusting bolts are rotatably connected with the connecting beam, and the adjusting bolts are screwed into the threaded holes and are matched with the threaded holes.
4. The jig identification and counting method based on image processing is applicable to the jig identification and counting system as set forth in claim 1, and is characterized in that:
Placing the jig on a conveying frame, conveying the jig by the conveying frame, and controlling the conveying belt to be suspended when the jig moves below the first camera; controlling a first irradiation lamp to irradiate the jig from the right at a first height position, irradiating the right edge of the jig and shadows on the surface of the jig, and simultaneously controlling a first camera to shoot a first image of the jig; controlling a second irradiation lamp to irradiate the jig from above at a second height, irradiating the upper edge of the jig and shadows on the surface of the jig, and simultaneously controlling the first camera to shoot a second image of the jig; then, a third irradiation lamp is controlled to irradiate the jig from the left at a third height, the left edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, a first camera is controlled to shoot a third image of the jig; then, a fourth irradiation lamp is controlled to irradiate the jig from the lower part at a fourth height, the lower edge of the jig and the shadow on the surface of the jig are irradiated, and meanwhile, the first camera is controlled to shoot a fourth image of the jig; after the four groups of images are shot, the conveyer belt is controlled to continue to run, the four groups of images are fused while the conveyer belt resumes to run, a fused image is obtained, the upper, lower, left and right edge contours of the fused image are identified and extracted, and the number, distribution and black depth of dark areas in the fused image are identified and extracted; and comparing the outline and the identification characteristic of the jig in the fusion image with the outline and the identification characteristic of the jig stored in the storage unit in advance, outputting the corresponding jig model after the comparison is successful, and classifying and counting the jigs according to the comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410070576.9A CN117593297B (en) | 2024-01-18 | 2024-01-18 | Jig identification and counting system and method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410070576.9A CN117593297B (en) | 2024-01-18 | 2024-01-18 | Jig identification and counting system and method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117593297A CN117593297A (en) | 2024-02-23 |
| CN117593297B true CN117593297B (en) | 2024-04-19 |
Family
ID=89916924
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410070576.9A Active CN117593297B (en) | 2024-01-18 | 2024-01-18 | Jig identification and counting system and method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117593297B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104441526A (en) * | 2014-09-24 | 2015-03-25 | 上海智觉光电科技有限公司 | Online mold monitoring and protecting system and method based on contour matching |
| CN108401142A (en) * | 2018-05-09 | 2018-08-14 | 冶金自动化研究设计院 | A kind of workpiece counting device on assembly line and method |
| CN110971796A (en) * | 2019-11-28 | 2020-04-07 | 南昌大学 | Ultra-fast camera based on SiPM and imaging method thereof |
| CN111781489A (en) * | 2020-07-02 | 2020-10-16 | 广德王氏智能电路科技有限公司 | Automatic PCB defect inspection equipment |
| CN113220924A (en) * | 2021-04-13 | 2021-08-06 | 广东汇博机器人技术有限公司 | Product model visual identification method and visual identification system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012023639A1 (en) * | 2010-08-17 | 2012-02-23 | 엘지전자 주식회사 | Method for counting objects and apparatus using a plurality of sensors |
-
2024
- 2024-01-18 CN CN202410070576.9A patent/CN117593297B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104441526A (en) * | 2014-09-24 | 2015-03-25 | 上海智觉光电科技有限公司 | Online mold monitoring and protecting system and method based on contour matching |
| CN108401142A (en) * | 2018-05-09 | 2018-08-14 | 冶金自动化研究设计院 | A kind of workpiece counting device on assembly line and method |
| CN110971796A (en) * | 2019-11-28 | 2020-04-07 | 南昌大学 | Ultra-fast camera based on SiPM and imaging method thereof |
| CN111781489A (en) * | 2020-07-02 | 2020-10-16 | 广德王氏智能电路科技有限公司 | Automatic PCB defect inspection equipment |
| CN113220924A (en) * | 2021-04-13 | 2021-08-06 | 广东汇博机器人技术有限公司 | Product model visual identification method and visual identification system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117593297A (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107336991B (en) | Feeder apparatus | |
| US7337533B2 (en) | Device for mounting component | |
| CN106423894A (en) | Automatic wheel hub appearance sorting device, sorting method and sorting system based on machine vision | |
| CN108355921A (en) | A kind of dispensing detection all-in-one machine and its dispensing detection method | |
| US20120293648A1 (en) | Component mounting system, image recognition data preparation apparatus, and image recognition data preparation method | |
| CN115646826B (en) | External surface detection system and detection method thereof | |
| CN109000564A (en) | A kind of keycap assembling method for testing performance and automatic detection device | |
| CN117593297B (en) | Jig identification and counting system and method based on image processing | |
| CN205344134U (en) | Take laser marking detection device of CIS scanning | |
| CN111570298A (en) | Bad piece removing device for mask | |
| CN214150485U (en) | Integrated detection equipment | |
| CN107966118A (en) | A kind of plane of motion detection device and its detection method | |
| CN112083013A (en) | Integrated visual detection equipment | |
| CN215868286U (en) | Machine vision teaching experiment platform of linear array scanning type | |
| CN109699130A (en) | A kind of high-efficient automatic PCB implanted device | |
| CN210952729U (en) | Detection device for visual artificial intelligence equipment | |
| CN212633466U (en) | Bad piece removing device for mask | |
| CN114501980A (en) | Device and method for detecting pins of special-shaped components and automatically plugging in components | |
| CN113218950A (en) | LED module appearance detection equipment and detection process thereof | |
| CN116760972B (en) | Automatic focusing detection method and equipment for lens module | |
| CN219124455U (en) | Capping machine for circuit board | |
| JPH09116297A (en) | Illuminator for illuminating recognizing mark of packaging device and method for adjusting illumination for recognizing mark | |
| CN112329898A (en) | Automatic anti-fake bar code collecting method for production line | |
| CN211392823U (en) | Laser etching pre-magnetizing detection device | |
| JPH06112691A (en) | Installing apparatus for component |
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 |