CN116087208B - Plastic product detecting system based on image recognition - Google Patents
Plastic product detecting system based on image recognition Download PDFInfo
- Publication number
- CN116087208B CN116087208B CN202310062630.0A CN202310062630A CN116087208B CN 116087208 B CN116087208 B CN 116087208B CN 202310062630 A CN202310062630 A CN 202310062630A CN 116087208 B CN116087208 B CN 116087208B
- Authority
- CN
- China
- Prior art keywords
- detection
- information
- plastic product
- image
- contour
- 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; 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/59—Transmissivity
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/10132—Ultrasound image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Biochemistry (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Geometry (AREA)
- Multimedia (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image detection, and particularly discloses a plastic product detection system based on image recognition, which comprises the following components: the environment light generating module is used for emitting pre-detection environment light and detecting the environment light; the light sensor is provided with a plurality of groups and is used for acquiring the transmittance information of the detection surface of the plastic product in the pre-detection and detection process; the image acquisition module is used for acquiring pre-detection image information and detection image information of the plastic product; the analysis module is used for analyzing according to the pre-detection image information and the transmittance information, obtaining detection environment light parameters and detecting the state of the plastic product according to the detection image information. The system detects the corresponding plastic products through the corresponding detection ambient light, can ensure that the collected images can clearly show the defect state, and further improves the accuracy of plastic product detection.
Description
Technical Field
The invention relates to the technical field of plastic product detection, in particular to a plastic product detection system based on image recognition.
Background
Along with the rapid development of production automation technology, more and more processes in the production process are replaced by machines, so that automation of the production detection process is realized, and for the production process of plastic products, the main processes of the production process are a plastic part injection molding process and an injection molding part size appearance detection process, and due to the characteristics of injection molding parts, size detection is generally performed in a first detection and process spot check mode, and the process is manually detected by quality inspection personnel, and for the detection of the injection molding part appearance, full detection is needed to avoid outflow of injection molding defective parts.
The existing plastic product appearance detection method is gradually converted into machine identification detection from the original manual detection mode, wherein the principle of the machine identification detection is mainly that image information of the surface of a plastic product is collected, and whether the appearance of an injection molding product has defects is judged through processing and analyzing the image information.
Because the types and the colors of the plastic products are various in the production process, the fixed detection system cannot adapt to the detection process of different plastic products, and if a unique detection system or detection strategy is set according to each plastic product, the switching of the detection process is complicated, and the production detection efficiency is affected.
Disclosure of Invention
The invention aims to provide a plastic product detection system based on image recognition, which solves the following technical problems:
how to accurately detect defects of different plastic products through the adaptability of one system.
The aim of the invention can be achieved by the following technical scheme:
a plastic article inspection system based on image recognition, the system comprising:
the environment light generating module is used for emitting pre-detection environment light and detecting the environment light;
the light sensor is provided with a plurality of groups and is used for acquiring the transmittance information of the detection surface of the plastic product in the pre-detection and detection process;
the image acquisition module is used for acquiring pre-detection image information and detection image information of the plastic product;
the analysis module is used for analyzing according to the pre-detection image information and the transmittance information, obtaining detection environment light parameters and detecting the state of the plastic product according to the detection image information.
In one embodiment, the process of detecting ambient light determination includes:
irradiating the plastic product according to a preset pre-detection environment light;
determining the average transmittance of the plastic product according to the transmittance information of the multiple points;
identifying color information of the plastic product in the pre-detection image information;
and determining and detecting ambient light according to the average transmittance and the color information of the plastic product.
In an embodiment, the process of detecting ambient light determination further comprises:
performing RGB component decomposition on the color information of the plastic product, and determining the frequency of the detected ambient light according to the interval where the numerical value of each component is located;
according to the formulaObtaining the illumination intensity Lx of the detected ambient light;
wherein F is R ,F G ,F G RGB component values of the color information, respectively;is the average value of transmittance; l is an illumination intensity quantization function;
and generating detection ambient light according to the detection ambient light frequency and the detection ambient light illumination intensity Lx.
In one embodiment, the process of detecting the state of the plastic product according to the detected image information includes:
graying treatment is carried out on the detected image information to obtain a gray image;
acquiring outline information of the detected image by adopting a combined edge recognition algorithm;
comparing the contour information with a standard contour, and obtaining non-coincident contour information according to a comparison result;
and carrying out feature analysis on the non-coincident profile information, and judging the appearance state of the plastic product according to an analysis result.
In one embodiment, the combined edge recognition algorithm is:
recognizing the gray level image by adopting a first edge detection algorithm to obtain first contour information;
adjusting image parameters of the gray level image to obtain an adjusted gray level image;
identifying the adjusted gray level image by adopting a second edge detection algorithm to obtain second contour information;
and comparing the first contour information with the second contour information, and fine-tuning the contour information position in the second contour information according to the position information in the first contour information to obtain the contour information of the detection image.
In one embodiment, the image parameter adjustment process for the gray scale image is as follows:
by a function g ex =v (x×ln (1+r)) to adjust the gray scale image;
wherein r is the gray value of the input image, g ex For outputting the gray value of the image, x is an adjustment coefficient, and v is a gray value conversion function.
In one embodiment, the process of performing feature analysis on non-coincident profile information is:
acquiring the size characteristic of each contour region, wherein the size characteristic comprises the longest diagonal length, the shortest diagonal length, the perimeter and the area of the contour;
and determining the characteristic value of each contour area according to the size characteristic of each contour area, and judging the state of the plastic product according to the size of the characteristic value of each contour area.
In one embodiment, the contour region feature value obtaining method includes:
by the formula f=a 1 *M/Z+A 2 *L S /σ*L L Calculating to obtain a contour region characteristic value F;
wherein M is the area value of the region; z is the perimeter value of the area; l (L) L Is the longest diagonal length of the contour; l (L) S Is the shortest diagonal length; sigma is a length ratio reference coefficient; a is that 1 、A 2 Is a preset coefficient.
In one embodiment, the process of determining the state of the plastic product according to the magnitude of the profile area feature value includes:
the contour region characteristic value F is matched with a preset threshold value F 1 、F 2 And (3) performing comparison:
if F > F 1 ThenJudging that the plastic product has a circular concave fault;
if F is less than F 2 Judging that the plastic product has crack faults;
if F is E [ F 1 ，F 2 ]Judging that the plastic product has the abnormal concave fault.
The invention has the beneficial effects that:
(1) According to the invention, the transparency information of the plastic product is obtained through the ambient light generating module and the light sensor, the corresponding detection ambient light parameter is obtained through the combination of the collected pre-detection image information and the transparency information, and the corresponding plastic product is detected through the corresponding detection ambient light, so that the collected image can clearly show the defect state, and the accuracy of plastic product detection is improved.
(2) According to the invention, the first contour information is compared with the second contour information, and the contour information position in the second contour information is finely adjusted according to the position information in the first contour information, so that the advantages of the two algorithms can be integrated, and the accuracy of the edge position is ensured on the basis of obtaining a contour with more round and continuous edges.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a schematic block diagram of a plastic product inspection system based on image recognition according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, in one embodiment, there is provided a plastic article inspection system based on image recognition, the system comprising:
the environment light generating module is used for emitting pre-detection environment light and detecting the environment light;
the light sensor is provided with a plurality of groups and is used for acquiring the transmittance information of the detection surface of the plastic product in the pre-detection and detection process;
the image acquisition module is used for acquiring pre-detection image information and detection image information of the plastic product;
the analysis module is used for analyzing according to the pre-detection image information and the transmittance information, obtaining detection environment light parameters and detecting the state of the plastic product according to the detection image information.
Through above-mentioned technical scheme, this embodiment adopts the mode of automatic judgement to come the automated inspection environment that corresponds according to the state of plastic products, specifically, at first obtains the transmittance information of plastic products through ambient light generation module and light sensor to combine the transmittance information to obtain corresponding detection ambient light parameter through the preliminary examination image information of gathering, detect the plastic products that corresponds through corresponding detection ambient light, can guarantee that the image of gathering can be comparatively clear show the state of defect, and then improve the accuracy that plastic products detected.
It should be noted that, in the above scheme, the image capturing manner is implemented by an industrial camera, and meanwhile, the hardware device for implementing the embodiment may be implemented by a prior art in the field, which is not further described herein.
As one embodiment of the present invention, the process of detecting ambient light determination includes:
irradiating the plastic product according to a preset pre-detection environment light;
determining the average transmittance of the plastic product according to the transmittance information of the multiple points;
identifying color information of the plastic product in the pre-detection image information;
and determining and detecting ambient light according to the average transmittance and the color information of the plastic product.
According to the technical scheme, the plastic product is irradiated according to the preset fixed pre-detection environment light, the average transmittance of the plastic product is determined according to the multi-point transmittance information, and then the color information of the plastic product is obtained through the identification of the pre-detection image information; according to the average transmittance and the color information of the plastic product, the detection environment light is determined, and the accuracy of plastic product detection can be improved.
As an embodiment of the present invention, the process of detecting ambient light determination further includes:
performing RGB component decomposition on the color information of the plastic product, and determining the frequency of the detected ambient light according to the interval where the numerical value of each component is located;
according to the formulaObtaining the illumination intensity Lx of the detected ambient light;
wherein F is R ,F G ,F G RGB component values of the color information, respectively;is the average value of transmittance; l is an illumination intensity quantization function;
and generating detection ambient light according to the detection ambient light frequency and the detection ambient light illumination intensity Lx.
According to the technical scheme, in the embodiment, the color information of the plastic product is subjected to RGB component decomposition, and comparison is performed according to the interval where the numerical value of each component is located, and as the interval of each color component is divided in advance, the frequency of the detected ambient light can be correspondingly obtained according to the distribution state of each color component in each color component interval; at the same time, by obtaining the average value of the transmittanceAnd combining RGB component values F of color information R ,F G ,F G Furthermore, the illumination intensity Lx of the ambient light is obtained through the illumination intensity quantization function L, so that the detection ambient light is generated according to the detection ambient light frequency and the detection ambient light illumination intensity Lx, the condition matching of the detection environment and the plastic product can be ensured, and the obtained detection image information can be further obtainedThe defect state can be clearly displayed.
It should be noted that the illumination intensity quantization function L is set according to the combination of the plurality of sets of test data, which is not described in detail herein.
As one embodiment of the present invention, the process of detecting the state of the plastic product according to the detected image information is as follows:
graying treatment is carried out on the detected image information to obtain a gray image;
acquiring outline information of the detected image by adopting a combined edge recognition algorithm;
comparing the contour information with a standard contour, and obtaining non-coincident contour information according to a comparison result;
and carrying out feature analysis on the non-coincident profile information, and judging the appearance state of the plastic product according to an analysis result.
Through the technical scheme, the embodiment provides a method for processing the detected image information, firstly, the image is subjected to gray processing, then the contour information of the detected image is obtained by adopting a combined edge recognition algorithm, the contour information is compared with a standard contour, non-coincident contour information is obtained according to a comparison result, and obviously, the non-coincident contour information reflects the abnormal condition of a plastic product, so that the appearance state of the plastic product can be judged according to an analysis result by carrying out feature analysis on the non-coincident contour information, and the judgment of the surface defect type of the plastic product is realized.
As an embodiment of the present invention, the combined edge recognition algorithm is:
recognizing the gray level image by adopting a first edge detection algorithm to obtain first contour information;
adjusting image parameters of the gray level image to obtain an adjusted gray level image;
identifying the adjusted gray level image by adopting a second edge detection algorithm to obtain second contour information;
and comparing the first contour information with the second contour information, and fine-tuning the contour information position in the second contour information according to the position information in the first contour information to obtain the contour information of the detection image.
Through the technical scheme, the embodiment provides an implementation mode of a combined edge recognition algorithm, and a first edge detection algorithm is adopted to recognize a gray level image to obtain first contour information; then, adjusting image parameters of the gray level image to obtain an adjusted gray level image, wherein the first edge detection algorithm and the second edge detection algorithm adopt different edge detection algorithms, and the first edge detection algorithm can adopt an algorithm with better anti-noise effect, such as a Canndy algorithm by utilizing the characteristics of the different edge detection algorithms; the second edge detection algorithm can be used for carrying out a smoother continuous algorithm, such as a Robert algorithm, on the recognition result, so that the first contour information obtained through the first edge detection algorithm has better position accuracy, then the noise of the image is reduced by carrying out image parameter adjustment on the gray image, and the second contour information obtained through the second edge detection algorithm has better contour smoothness, so that the position of the contour information in the second contour information is finely adjusted according to the position information in the first contour information by comparing the first contour information with the second contour information, further the advantages of the two algorithms can be combined, and the accuracy of the edge position is ensured on the basis of obtaining a contour with softer continuous edge.
As one embodiment of the present invention, the process of adjusting the image parameters of the gray-scale image is as follows:
by a function g ex =v (x×ln (1+r)) to adjust the gray scale image;
wherein r is the gray value of the input image, g ex For outputting the gray value of the image, x is an adjustment coefficient, and v is a gray value conversion function.
Through the technical scheme, the embodiment provides the method for adjusting the image parameters of the gray image, and gray can be concentrated in a low-brightness area and converted into a mode of dividing the low-brightness area into a high-brightness area by utilizing a curve form of a logarithmic function, so that the edge characteristics of the gray image are clearer and more obvious; wherein x is an adjustment coefficient, and v is a gray value conversion function, according to user settings, for adjusting the degree of image adjustment, and the obtained gray value can be converted to a range between [0, 255 ].
As one embodiment of the present invention, the process of performing feature analysis on non-coincident profile information is as follows:
acquiring the size characteristic of each contour region, wherein the size characteristic comprises the longest diagonal length, the shortest diagonal length, the perimeter and the area of the contour;
and determining the characteristic value of each contour area according to the size characteristic of each contour area, and judging the state of the plastic product according to the size of the characteristic value of each contour area.
According to the technical scheme, the embodiment provides a method for carrying out feature analysis on non-coincident profile information, the size features of each profile area are obtained, the feature value of each profile area is determined according to the size features of each profile area, and the state of a plastic product is judged according to the size of the feature value of the profile area; where the dimensional features include the longest diagonal length, shortest diagonal length, perimeter, and area of the outline, which reflect the general features of the shape of each region.
As one embodiment of the present invention, the contour region feature value obtaining method includes:
by the formula f=a 1 *M/Z+A 2 *L S /σ*L L Calculating to obtain a contour region characteristic value F;
wherein M is the area value of the region; z is the perimeter value of the area; l (L) L Is the longest diagonal length of the contour; l (L) S Is the shortest diagonal length; sigma is a length ratio reference coefficient; a is that 1 、A 2 Is a preset coefficient.
Through the above technical solution, this embodiment provides a method for obtaining a profile feature value according to the longest diagonal length, the shortest diagonal length, the perimeter and the area of the profile, by the formula f=a 1 *M/Z+A 2 *L S /σ*L L Calculating to obtain a contour region characteristic value F, wherein M/Z and L S /σ*L L The larger the number of (c) the more the shape of the profile tends to be circular, becauseThis is expressed by the formula f=a 1 *M/Z+A 2 *L S /σ*L L And calculating to obtain a contour region characteristic value F, and further helping to judge the specific defect type of the surface of the plastic product according to the size of the contour region characteristic value F.
The preset coefficient A 1 、A 2 The settings are selected based on empirical data and are not described in detail herein.
As one embodiment of the present invention, the process of determining the state of the plastic product according to the magnitude of the profile area feature value includes:
the contour region characteristic value F is matched with a preset threshold value F 1 、F 2 And (3) performing comparison:
if F > F 1 Judging that the plastic product has a circular concave fault;
if F is less than F 2 Judging that the plastic product has crack faults;
if F is E [ F 1 ，F 2 ]Judging that the plastic product has the abnormal concave fault.
Through the above technical solution, in this embodiment, the profile area characteristic value F is compared with the preset threshold value F 1 、F 2 And (3) performing comparison: if F > F 1 Indicating that the shape of the defect area tends to be circular, and judging that the plastic product has a circular concave fault; if F is less than F 2 Indicating that the shape of the defective area tends to be a narrow and thin structure, and thus judging that the plastic product has crack failure; if F is E [ F 1 ，F 2 ]It is stated that the defective area shape tends to be intermediate between the two, and thus it is judged that the plastic article has a anisotropic dent failure.
The preset threshold F is set 1 、F 2 The selective setting is based on historical empirical data and is not described in further detail herein.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (5)
1. A plastic article inspection system based on image recognition, the system comprising:
the environment light generating module is used for emitting pre-detection environment light and detecting the environment light;
the light sensor is provided with a plurality of groups and is used for acquiring the transmittance information of the detection surface of the plastic product in the pre-detection and detection process;
the image acquisition module is used for acquiring pre-detection image information and detection image information of the plastic product;
the analysis module is used for analyzing according to the pre-detection image information and the transmittance information to obtain detection environment light parameters and detecting the state of the plastic product according to the detection image information;
the process of detecting ambient light determination includes:
irradiating the plastic product according to a preset pre-detection environment light;
determining the average transmittance of the plastic product according to the transmittance information of the multiple points;
identifying color information of the plastic product in the pre-detection image information;
determining detection ambient light according to the average transmittance and the color information of the plastic product;
the process of detecting ambient light determination further comprises:
performing RGB component decomposition on the color information of the plastic product, and determining the frequency of the detected ambient light according to the interval where the numerical value of each component is located;
according to the formulaObtaining the illumination intensity Lx of the detected ambient light;
wherein F is R ,F G ,F G RGB component values of the color information, respectively;is the average value of transmittance; l is the light intensity quantization functionA number;
generating detection ambient light according to the detection ambient light frequency and the detection ambient light illumination intensity Lx;
the process for detecting the state of the plastic product according to the detected image information comprises the following steps:
graying treatment is carried out on the detected image information to obtain a gray image;
acquiring outline information of the detected image by adopting a combined edge recognition algorithm;
comparing the contour information with a standard contour, and obtaining non-coincident contour information according to a comparison result;
performing feature analysis on the non-coincident profile information, and judging the appearance state of the plastic product according to an analysis result;
the combined edge recognition algorithm is as follows:
recognizing the gray level image by adopting a first edge detection algorithm to obtain first contour information;
adjusting image parameters of the gray level image to obtain an adjusted gray level image;
identifying the adjusted gray level image by adopting a second edge detection algorithm to obtain second contour information;
and comparing the first contour information with the second contour information, and fine-tuning the contour information position in the second contour information according to the position information in the first contour information to obtain the contour information of the detection image.
2. The plastic product inspection system based on image recognition according to claim 1, wherein the process of adjusting the image parameters of the gray scale image is:
by a function g ex =v (x×ln (1+r)) to adjust the gray scale image;
wherein r is the gray value of the input image, g ex For outputting the gray value of the image, x is an adjustment coefficient, and v is a gray value conversion function.
3. The plastic product inspection system based on image recognition according to claim 2, wherein the process of performing feature analysis on the non-coincident profile information is:
acquiring the size characteristic of each contour region, wherein the size characteristic comprises the longest diagonal length, the shortest diagonal length, the perimeter and the area of the contour;
and determining the characteristic value of each contour area according to the size characteristic of each contour area, and judging the state of the plastic product according to the size of the characteristic value of each contour area.
4. A plastic product inspection system based on image recognition according to claim 3, wherein the contour region feature value obtaining method comprises:
by the formula f=a 1 *M/Z+A 2 *L S /σ*L L Calculating to obtain a contour region characteristic value F;
wherein M is the area value of the region; z is the perimeter value of the area; l (L) L Is the longest diagonal length of the contour; l (L) S Is the shortest diagonal length; sigma is a length ratio reference coefficient; a is that 1 、A 2 Is a preset coefficient.
5. The plastic product inspection system based on image recognition according to claim 4, wherein the process of judging the state of the plastic product according to the magnitude of the feature value of the contour area comprises the following steps:
the contour region characteristic value F is matched with a preset threshold value F 1 、F 2 And (3) performing comparison:
if F > F 1 Judging that the plastic product has a circular concave fault;
if F is less than F 2 Judging that the plastic product has crack faults;
if F is E [ F 1 ，F 2 ]Judging that the plastic product has the abnormal concave fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310062630.0A CN116087208B (en) | 2023-01-20 | 2023-01-20 | Plastic product detecting system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310062630.0A CN116087208B (en) | 2023-01-20 | 2023-01-20 | Plastic product detecting system based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116087208A CN116087208A (en) | 2023-05-09 |
| CN116087208B true CN116087208B (en) | 2023-09-29 |
Family
ID=86205995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310062630.0A Active CN116087208B (en) | 2023-01-20 | 2023-01-20 | Plastic product detecting system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116087208B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116703429B (en) * | 2023-08-07 | 2023-12-15 | 深圳市磐锋精密技术有限公司 | Intelligent charging tray access system based on Internet of things |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113588672A (en) * | 2021-09-29 | 2021-11-02 | 武汉绿色塑料包装有限公司 | Quality detection method for plastic product |
| CN114972356A (en) * | 2022-08-03 | 2022-08-30 | 海门市腾飞橡塑厂 | Plastic product surface defect detection and identification method and system |
| CN115201212A (en) * | 2022-09-19 | 2022-10-18 | 江苏华彬新材料有限公司 | Plastic product defect detection device based on machine vision |
| CN115311270A (en) * | 2022-10-11 | 2022-11-08 | 南通至顺聚氨酯材料有限公司 | Plastic product surface defect detection method |
| CN115456652A (en) * | 2022-09-29 | 2022-12-09 | 广东格林精密部件股份有限公司 | Tracing method for defective products of precision injection molding parts based on artificial intelligence |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114719966A (en) * | 2020-12-22 | 2022-07-08 | 富泰华工业（深圳）有限公司 | Light source determination method and device, electronic equipment and storage medium |
-
2023
- 2023-01-20 CN CN202310062630.0A patent/CN116087208B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113588672A (en) * | 2021-09-29 | 2021-11-02 | 武汉绿色塑料包装有限公司 | Quality detection method for plastic product |
| CN114972356A (en) * | 2022-08-03 | 2022-08-30 | 海门市腾飞橡塑厂 | Plastic product surface defect detection and identification method and system |
| CN115201212A (en) * | 2022-09-19 | 2022-10-18 | 江苏华彬新材料有限公司 | Plastic product defect detection device based on machine vision |
| CN115456652A (en) * | 2022-09-29 | 2022-12-09 | 广东格林精密部件股份有限公司 | Tracing method for defective products of precision injection molding parts based on artificial intelligence |
| CN115311270A (en) * | 2022-10-11 | 2022-11-08 | 南通至顺聚氨酯材料有限公司 | Plastic product surface defect detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116087208A (en) | 2023-05-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115082683B (en) | Injection molding defect detection method based on image processing | |
| US9582872B2 (en) | Optical film defect detection method and system thereof | |
| EP3556576B1 (en) | Process and system for the detection of defects in a tyre | |
| CN113570605B (en) | Defect detection method and system based on liquid crystal display panel | |
| CN115018844B (en) | Plastic film quality evaluation method based on artificial intelligence | |
| CN116087208B (en) | Plastic product detecting system based on image recognition | |
| JP2005277395A5 (en) | ||
| CN106442556A (en) | Device and method for detecting surface defects of perforated plate workpiece | |
| CN114494210A (en) | Plastic film production defect detection method and system based on image processing | |
| CN116912261B (en) | Plastic mold injection molding surface defect detection method | |
| CN111179362B (en) | Test paper color uniformity detection method based on dynamic illumination correction algorithm | |
| CN114387272A (en) | Cable bridge defective product detection method based on image processing | |
| CN116703911B (en) | LED lamp production quality detecting system | |
| CN111161237A (en) | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof | |
| CN111739012A (en) | Camera module white spot detecting system based on turntable | |
| CN113820319A (en) | Textile surface defect detection device and method | |
| CN113019973A (en) | Online visual inspection method for manufacturing defects of ring-pull cans | |
| CN106093051A (en) | Paper roll tangent plane burr detection method based on machine vision and device | |
| JP2012159376A (en) | Surface defect detector and surface defect detection method | |
| CN116519640A (en) | Method for measuring surface glossiness of silica gel key based on machine vision system | |
| US10241000B2 (en) | Method for checking the position of characteristic points in light distributions | |
| JP2003123073A (en) | Defect detection method | |
| CN111693533B (en) | Workpiece surface quality detection method and device and appearance machine | |
| CN114166849B (en) | Method for detecting defects of printed carbon lines and moisture-sensitive film of humidity sensor | |
| Campos et al. | Inspection of bottles crates in the beer industry through computer vision |
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 |