CN114387271B - Air conditioner plastic water pan grid glue shortage detection method and system based on angular point detection - Google Patents
Air conditioner plastic water pan grid glue shortage detection method and system based on angular point detection Download PDFInfo
- Publication number
- CN114387271B CN114387271B CN202210285635.5A CN202210285635A CN114387271B CN 114387271 B CN114387271 B CN 114387271B CN 202210285635 A CN202210285635 A CN 202210285635A CN 114387271 B CN114387271 B CN 114387271B
- Authority
- CN
- China
- Prior art keywords
- grid
- pixel
- analysis
- points
- degree
- 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
Images
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
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- 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
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, in particular to a method and a system for detecting the glue shortage of grids of a plastic water pan of an air conditioner based on angular point detection. The method detects grid corner points in the water pan image. And classifying according to the coordinates of the grid corner points to obtain a plurality of grid corner point groups and corresponding grid vertex areas. Mesh analysis regions between mesh vertex regions are obtained. And obtaining pixel points of grid line categories in the grid analysis region by utilizing the pixel value characteristics, and obtaining the analysis confidence of the grid analysis region according to the number of the pixel points of the grid line categories and the average pixel difference between the grid line categories and other categories. And obtaining the pixel mutation degree according to the pixel difference between each pixel point in the grid analysis region and other pixel points in the neighborhood range, and obtaining the gel shortage degree of the grid analysis region by combining the analysis confidence. The invention utilizes the pixel characteristics of the gel deficiency to combine with the confidence coefficient of each area to obtain the gel deficiency degree with strong reference to realize accurate and simple gel deficiency detection.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a system for detecting the glue shortage of grids of a plastic water pan of an air conditioner based on angular point detection.
Background
The plastic water pan of the air conditioner outdoor unit can guide out the frosted water, the water pan of the air conditioner outdoor unit is hung on the air conditioner outdoor unit, and therefore the air conditioner water pan is required to have supporting force with a certain bottom, wherein the plastic water pan of the air conditioner is provided with an additional grid at the bottom of the water pan to provide bottom supporting force, so that the plastic water pan is not easy to deform, and the service life is prolonged.
In the production process of the plastic water pan of the air conditioner, the condition that the bottom grid of the product is in glue shortage can occur, so that the bottom supporting force of the water pan is uneven, and deformation easily occurs, so that the product is unqualified. Therefore, the glue shortage detection of the bottom grid needs to be carried out after the plastic water receiving tray of the air conditioner is processed.
In the prior art, the grid is subjected to glue deficiency detection through a threshold segmentation method, the grid is easily interfered by noise and illumination, a gray threshold needs to be manually set, and the grid lines are subjected to glue deficiency detection through Hough line detection.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a method and a system for detecting the glue shortage of grids of a plastic water pan of an air conditioner based on angular point detection, and the adopted technical scheme is as follows:
the invention also provides an air conditioner plastic water pan grid glue shortage detection method based on angular point detection, which comprises the following steps:
acquiring a grid image of the water receiving tray; acquiring grid angular points in the grid image of the water receiving tray; classifying the grid corner points according to the coordinate information of the grid corner points to obtain a plurality of grid corner point groups;
obtaining a circular grid vertex area according to the coordinate information of the grid corner points in the grid corner point group; taking a direction perpendicular to a connecting line between circle centers of adjacent grid vertex areas as a reference direction; taking a straight line which passes through the circle center and takes the direction as the reference direction as a reference straight line; constructing a grid analysis area between the grid vertex areas according to the intersection point of the reference straight line and the grid vertex area;
dividing the pixel points in the grid analysis area into two pixel point categories according to the pixel values; taking the class with the pixel average value of the pixel point class similar to the pixel average value of the grid vertex area as the grid line class; obtaining the analysis confidence of the grid analysis region according to the number of the pixel points of the grid line category and the average pixel difference between the pixel point categories;
obtaining pixel mutation degrees according to pixel differences between each pixel point in the grid analysis region and other pixel points in a preset neighborhood range; obtaining the gel shortage degree of the grid analysis region according to the pixel mutation degree and the analysis confidence; and judging whether the glue shortage occurs or not according to the glue shortage degree.
Further, the obtaining of the grid image of the water pan comprises:
collecting an initial water pan grid image; and removing and graying the background in the initial grid image of the water receiving tray to obtain the grid image of the water receiving tray only containing the grid gray information of the water receiving tray.
Further, the classifying the grid corner points according to the coordinate information of the grid corner points to obtain a plurality of grid corner point groups includes:
and classifying the grid corner points by using a mean shift algorithm according to the coordinate information to obtain a plurality of grid corner point groups.
Further, the obtaining of the circular mesh vertex area according to the coordinate information of the mesh corner point group includes:
and performing circle fitting on the grid corner point group by using a random sampling consistency algorithm according to the coordinate information to obtain the grid vertex area.
Further, the obtaining of the analysis confidence of the grid analysis region according to the number of the pixel points of the grid line category and the average pixel difference between the pixel point categories includes:
obtaining the number proportion of the pixel points of the grid line category in the grid analysis area; and taking the ratio of the number ratio to the average pixel difference between the pixel point categories as the analysis confidence.
Further, the obtaining of the pixel mutation degree according to the pixel difference between each pixel point in the grid analysis region and other pixel points in the preset neighborhood range includes:
and accumulating the pixel difference of each pixel point in the grid analysis region and other pixel points in the eight neighborhood range of the pixel point to obtain the pixel mutation degree.
Further, the obtaining of the degree of gel missing of the grid analysis region according to the degree of pixel mutation and the analysis confidence degree includes:
and multiplying the normalized analysis confidence coefficient by the pixel mutation degree to obtain the gel shortage degree.
Further, the judging whether the glue shortage occurs according to the glue shortage degree comprises:
and if the glue shortage degree is greater than a preset degree threshold value, determining that the corresponding grid analysis area has glue shortage.
The invention also provides an air conditioner plastic water pan grid glue deficiency detection system based on angular point detection, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize any step of the air conditioner plastic water pan grid glue deficiency detection method based on angular point detection.
The invention has the following beneficial effects:
the embodiment of the invention obtains the angular points in the grid image of the water pan by using an angular point detection method, and determines an accurate grid analysis area according to the positions and the distribution of the angular points. Continuous and uniformly distributed grid line type pixel points exist in the grid analysis area, according to the characteristics, firstly, the analysis confidence coefficient is used for representing the reference of the current grid analysis area, then, the pixel mutation is used for representing the pixel change characteristics in the grid analysis area, and further, the defect degree of the grid analysis area with strong reference is obtained. Whether the grid analysis area has the defect can be judged according to the defect degree.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for detecting the lack of glue in a grid of a plastic water pan of an air conditioner based on angular point detection according to an embodiment of the present invention;
fig. 2 is a schematic view of a water pan grid according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects of the present invention adopted to achieve the predetermined invention purpose, the following detailed description will be given to the specific implementation, structure, features and effects of the method and system for detecting the grid glue shortage of the plastic water pan of the air conditioner based on the angular point detection, which are provided by the present invention, in combination with the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a method and a system for detecting the grid glue shortage of an air conditioner plastic water pan based on angular point detection.
Referring to fig. 1, a flow chart of a method for detecting glue shortage of a plastic water pan grid of an air conditioner based on corner detection according to an embodiment of the present invention is shown, where the method includes:
step S1: acquiring a grid image of the water receiving tray; acquiring grid angular points in a grid image of the water receiving tray; and classifying the grid corner points according to the coordinate information of the grid corner points to obtain a plurality of grid corner point groups.
In the process of producing the water pan, the water pan can be placed on a production line, a camera is installed on the production line to collect image information, and it needs to be explained that the sampling rate of the camera and the movement speed of the production line need to be controlled in the image collection process, so that the camera can collect clear and complete information of the water pan.
In order to facilitate subsequent analysis of the image, the background in the initial water-receiving tray grid image needs to be removed and grayed, and a water-receiving tray grid image only containing water-receiving tray grid gray information is obtained.
It should be noted that, the operation of removing the background information may adopt a neural network to segment the image, or other image processing manners, or may also adopt a manual setting of the region of interest to segment the image, and may be set by itself according to a specific task, which is not limited herein.
The corner point is a type of point having a specific characteristic, and in a region, no matter how the moving direction of the region is changed, a point having a large change in pixel value exists in the region, and the point is the corner point. Referring to fig. 2, a schematic diagram of a water-receiving tray grid according to an embodiment of the present invention is shown, where the water-receiving tray grid can be viewed as a plurality of grids with a certain width and plastic adhesive tapes distributed crosswise, and because of the width, a plurality of corner points should exist at a vertex of one grid.
In the embodiment of the invention, a grid image of the water receiving tray is processed by using a Harris corner detection algorithm, and a plurality of grid corners can be obtained after processing.
One grid vertex corresponds to a plurality of corner points, and the corner points are close in distance, so that the grid corner points can be classified according to coordinate information of the grid corner points to obtain a plurality of grid corner point groups, and each grid corner point group represents one grid vertex.
Preferably, the grid corner points are classified by using a mean shift algorithm according to the coordinate information to obtain a plurality of grid corner point groups.
Step S2: obtaining a circular grid vertex area according to coordinate information of grid corners in the grid corner group; taking the direction perpendicular to the connecting line between the circle centers of the adjacent grid vertex areas as a reference direction; taking a straight line which passes through the center of a circle and takes the direction as a reference straight line; and constructing a mesh analysis area between the mesh vertex areas according to the intersection points of the reference straight lines and the mesh vertex areas.
The grid corners in the grid corner group can form a region representing grid vertices, so that fitting can be performed according to coordinate information of each grid corner in the grid corner group to obtain a circular grid vertex region.
Preferably, according to the coordinate information, a random sampling consistency algorithm is used for carrying out circle fitting on the grid corner point group to obtain a grid vertex area. The random sample consensus algorithm is an iterative method for estimating the parameters of a mathematical model, i.e. the parameters of the circular equations of the vertex regions of the mesh, in a set of observed data containing outliers.
It should be noted that, in the circle fitting process, the radius of the mesh vertex area may be specifically set according to the type of the water pan, the height of the camera, and the like, and in the embodiment of the present invention, the radius of the mesh vertex area is set to be 2.
The direction perpendicular to the connecting line between the circle centers of the adjacent grid vertex areas is taken as a reference direction, namely, each two adjacent grid vertex areas correspond to one reference direction. And constructing a grid analysis area between the grid vertex areas according to the intersection points of the reference straight line and the grid vertex areas by taking the straight line passing through the circle center and taking the direction as the reference straight line. The grid analysis area is a rectangular area, and two categories of grid line pixel points and pixel points at the bottom of the water receiving tray exist in the area.
Step S3: dividing the pixel points in the grid analysis area into two pixel point categories according to the pixel values; taking the class with the pixel average value of the pixel point class similar to the pixel average value of the grid vertex area as the grid line class; and obtaining the analysis confidence of the grid analysis region according to the number of the pixel points of the grid line type and the average pixel difference between the pixel point types.
As can be seen from fig. 2, there is a pixel difference between the grid lines and the bottom of the water receiving tray, so that the grid line pixels in the grid analysis region and the pixels at the bottom of the water receiving tray can be distinguished according to the pixel characteristics.
The pixel points in the grid analysis region are divided into two pixel point categories according to the pixel values, namely, the pixel point category with a high pixel value and the pixel point category with a low pixel value. In the embodiment of the invention, the automatic threshold segmentation is realized by utilizing an information entropy threshold segmentation method so as to obtain two types of pixel point categories with the pixel difference as obvious as possible.
Because the grid line pixel points can be regarded as being formed by extending grid vertex pixel points, the pixel value characteristics of the grid pixel points and the grid vertex pixel points are the same. Therefore, the class with the pixel average value of the pixel point class similar to the pixel average value of the grid vertex area is taken as the grid line class.
The pixel mutation exists on the grid lines due to the glue shortage of the grid lines, so that when the pixel mutation of the grid lines is analyzed, the grid line pixel points in the grid analysis area need to be ensured to be as many as possible, namely, the more the grid line pixel points are, the stronger the referential of the corresponding grid analysis area is, and the higher the confidence of the grid analysis area is.
And obtaining the number proportion of the pixel points of the grid line type in the grid analysis area. And taking the ratio of the number ratio to the average pixel difference between the pixel point categories as an analysis confidence. The larger the number ratio is, the more grid pixel points in the grid analysis area are, and the stronger the analysis confidence coefficient is; the smaller the average pixel difference is, the smaller the difference between the pixel differences between the two pixel point categories is proved to be, the two pixel categories may be both grid line pixel points, and the more grid pixel points are in the grid analysis area, the stronger the analysis confidence is.
Step S4: obtaining pixel mutation degrees according to pixel differences between each pixel point in the grid analysis region and other pixel points in a preset neighborhood range; obtaining the gel-lacking degree of the grid analysis region according to the pixel mutation degree and the analysis confidence coefficient; and judging whether the glue shortage occurs or not according to the glue shortage degree.
And analyzing the pixel characteristics among all pixel points in the grid analysis area, and evaluating the pixel mutation degree of the pixels in the current grid analysis area. The bigger the pixel mutation degree is, explains the starved condition of having taken place on the current grid line, and defective pixel point has caused great pixel fluctuation, specifically includes:
and accumulating the pixel difference of each pixel point in the grid analysis region and other pixel points in the eight neighborhood range of the pixel point to obtain the pixel mutation degree.
And combining the analysis confidence coefficient of the grid analysis area, and multiplying the normalized analysis confidence coefficient by the mutation degree of the pixels to obtain the degree of the gel shortage. The analysis confidence coefficient represents the referential of the current grid analysis region, the analysis confidence coefficient is used as the weight of the pixel mutation degree, the obtained gel-lacking degree has accurate referential, and whether the gel-lacking condition occurs in the corresponding grid analysis region can be judged according to the gel-lacking degree. And if the glue shortage degree is greater than the preset degree threshold value, determining that the corresponding grid analysis area has glue shortage. In the embodiment of the present invention, the degree threshold is set to 5.
The staff can carry out the investigation and repair to the water tray according to the position in the grid analysis region that takes place the starved condition.
In summary, the embodiments of the present invention detect grid corner points in a water tray image. And classifying according to the coordinates of the grid corner points to obtain a plurality of grid corner point groups. Each set of corner points may be fitted to a grid vertex region. Mesh analysis regions between mesh vertex regions are obtained. And obtaining pixel points of grid line categories in the grid analysis region by utilizing the pixel value characteristics, and obtaining the analysis confidence of the grid analysis region according to the number of the pixel points of the grid line categories and the average pixel difference between the grid line categories and other categories. And obtaining the pixel mutation degree according to the pixel difference between each pixel point in the grid analysis region and other pixel points in the neighborhood range, and obtaining the gel shortage degree of the grid analysis region by combining the analysis confidence. And judging whether the glue shortage occurs or not according to the glue shortage degree. The embodiment of the invention realizes simple, convenient and accurate glue shortage detection of the grid of the water receiving tray by combining the pixel characteristics of the glue shortage with the confidence coefficient of each area.
The invention also provides an air conditioner plastic water pan grid glue deficiency detection system based on angular point detection, which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes any step of the air conditioner plastic water pan grid glue deficiency detection method based on angular point detection when executing the computer program.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. An air conditioner plastic water pan grid glue shortage detection method based on angular point detection is characterized by comprising the following steps:
acquiring a grid image of the water receiving tray; acquiring grid angular points in the grid image of the water receiving tray; classifying the grid corner points according to the coordinate information of the grid corner points to obtain a plurality of grid corner point groups;
obtaining a circular grid vertex area according to the coordinate information of the grid corner points in the grid corner point group; taking the direction perpendicular to the connecting line between the circle centers of the adjacent grid vertex areas as a reference direction; taking a straight line which passes through the circle center and takes the direction as the reference direction as a reference straight line; constructing a grid analysis area between the grid vertex areas according to the intersection point of the reference straight line and the grid vertex area;
dividing the pixel points in the grid analysis area into two pixel point categories according to the pixel values; taking the class with the pixel average value of the pixel point class similar to the pixel average value of the grid vertex area as the grid line class; obtaining the analysis confidence of the grid analysis region according to the number of the pixel points of the grid line type and the average pixel difference between the pixel point types; the method for obtaining the analysis confidence comprises the following steps: obtaining the number proportion of the pixel points of the grid line category in the grid analysis area; taking the ratio of the number ratio to the average pixel difference between the pixel point categories as the analysis confidence;
obtaining pixel mutation degrees according to pixel differences between each pixel point in the grid analysis region and other pixel points in a preset neighborhood range; obtaining the gel-lacking degree of the grid analysis region according to the pixel mutation degree and the analysis confidence coefficient; and judging whether the glue shortage occurs or not according to the glue shortage degree.
2. The air conditioner plastic water pan grid glue shortage detection method based on angular point detection as claimed in claim 1, wherein the obtaining of the water pan grid image comprises:
collecting an initial water pan grid image; and removing and graying the background in the initial grid image of the water receiving tray to obtain the grid image of the water receiving tray only containing the grid gray information of the water receiving tray.
3. The method for detecting the adhesive shortage of the grids of the plastic water pan for the air conditioner based on the angular point detection as claimed in claim 1, wherein the step of classifying the grid angular points according to the coordinate information of the grid angular points to obtain a plurality of grid angular point groups comprises the steps of:
and classifying the grid corner points by using a mean shift algorithm according to the coordinate information to obtain a plurality of grid corner point groups.
4. The method for detecting the grid glue shortage of the air-conditioning plastic water pan based on the angular point detection as claimed in claim 1, wherein the obtaining of the circular grid vertex area according to the coordinate information of the grid angular point group comprises:
and performing circle fitting on the grid corner point group by using a random sampling consistency algorithm according to the coordinate information to obtain the grid vertex area.
5. The method for detecting the grid glue shortage of the air-conditioning plastic water pan based on the angular point detection as claimed in claim 1, wherein the obtaining of the pixel mutation degree according to the pixel difference between each pixel point in the grid analysis area and other pixel points in the preset neighborhood range comprises:
and accumulating the pixel difference of each pixel point in the grid analysis region and other pixel points in the eight neighborhood range of the pixel point to obtain the pixel mutation degree.
6. The air conditioner plastic water pan grid gel-deficiency detection method based on angular point detection as claimed in claim 1, wherein the obtaining of the gel-deficiency degree of the grid analysis region according to the pixel mutation degree and the analysis confidence degree comprises:
and multiplying the normalized analysis confidence coefficient by the pixel mutation degree to obtain the gel shortage degree.
7. The air conditioner plastic water pan grid gel deficiency detection method based on angular point detection as claimed in claim 1, wherein said determining whether gel deficiency occurs according to the degree of gel deficiency comprises:
and if the glue shortage degree is greater than a preset degree threshold value, determining that the corresponding grid analysis area has glue shortage.
8. An air conditioner plastic water pan grid glue shortage detection system based on corner detection comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, and is characterized in that the processor executes the computer program to realize the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210285635.5A CN114387271B (en) | 2022-03-23 | 2022-03-23 | Air conditioner plastic water pan grid glue shortage detection method and system based on angular point detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210285635.5A CN114387271B (en) | 2022-03-23 | 2022-03-23 | Air conditioner plastic water pan grid glue shortage detection method and system based on angular point detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114387271A CN114387271A (en) | 2022-04-22 |
| CN114387271B true CN114387271B (en) | 2022-06-10 |
Family
ID=81206401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210285635.5A Active CN114387271B (en) | 2022-03-23 | 2022-03-23 | Air conditioner plastic water pan grid glue shortage detection method and system based on angular point detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114387271B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116630317B (en) * | 2023-07-24 | 2023-09-26 | 四川新荷花中药饮片股份有限公司 | On-line quality monitoring method for traditional Chinese medicine decoction pieces |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0930499A1 (en) * | 1998-01-16 | 1999-07-21 | NEC Corporation | Automatic visual inspection apparatus, automatic visual inspection method, and recording medium having recorded an automatic visual inspection program |
| CN107248159A (en) * | 2017-08-04 | 2017-10-13 | 河海大学常州校区 | A kind of metal works defect inspection method based on binocular vision |
| CN108830842A (en) * | 2018-06-04 | 2018-11-16 | 哈尔滨工程大学 | A kind of medical image processing method based on Corner Detection |
| CN109376770A (en) * | 2018-09-26 | 2019-02-22 | 凌云光技术集团有限责任公司 | A kind of net region recognition methods and device applied to egative film check machine |
| CN111523611A (en) * | 2020-05-07 | 2020-08-11 | 北京智机科技有限公司 | Gluing detection method |
| CN113298809A (en) * | 2021-06-25 | 2021-08-24 | 成都飞机工业（集团）有限责任公司 | Composite material ultrasonic image defect detection method based on deep learning and superpixel segmentation |
| CN113920118A (en) * | 2021-12-14 | 2022-01-11 | 武汉卓久玻璃制品有限公司 | Hollow glass spacer glue-shortage detection method based on image processing |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111429450B (en) * | 2020-04-10 | 2022-08-16 | 展讯通信（上海）有限公司 | Corner point detection method, system, equipment and storage medium |
| CN114187289B (en) * | 2021-12-23 | 2022-08-09 | 武汉市坤瑞塑胶模具制品有限公司 | Plastic product shrinkage pit detection method and system based on computer vision |
-
2022
- 2022-03-23 CN CN202210285635.5A patent/CN114387271B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0930499A1 (en) * | 1998-01-16 | 1999-07-21 | NEC Corporation | Automatic visual inspection apparatus, automatic visual inspection method, and recording medium having recorded an automatic visual inspection program |
| CN107248159A (en) * | 2017-08-04 | 2017-10-13 | 河海大学常州校区 | A kind of metal works defect inspection method based on binocular vision |
| CN108830842A (en) * | 2018-06-04 | 2018-11-16 | 哈尔滨工程大学 | A kind of medical image processing method based on Corner Detection |
| CN109376770A (en) * | 2018-09-26 | 2019-02-22 | 凌云光技术集团有限责任公司 | A kind of net region recognition methods and device applied to egative film check machine |
| CN111523611A (en) * | 2020-05-07 | 2020-08-11 | 北京智机科技有限公司 | Gluing detection method |
| CN113298809A (en) * | 2021-06-25 | 2021-08-24 | 成都飞机工业（集团）有限责任公司 | Composite material ultrasonic image defect detection method based on deep learning and superpixel segmentation |
| CN113920118A (en) * | 2021-12-14 | 2022-01-11 | 武汉卓久玻璃制品有限公司 | Hollow glass spacer glue-shortage detection method based on image processing |
Non-Patent Citations (2)
| Title |
|---|
| Van Trang Phung.Detection of Bearing Faults in Repetitive Mechanical.《2016 IEEE 8th International Power Electronics and Motion Control Conference (IPEMC-ECCE Asia)》.2016,第3089-3095页. * |
| 刘新辉.基于机器视觉的孔边缺陷检测算法研究与应用.《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》.2015,第I138-723页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114387271A (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116186634B (en) | Intelligent management system for construction data of building engineering | |
| CN110148130B (en) | Method and device for detecting part defects | |
| CN114387271B (en) | Air conditioner plastic water pan grid glue shortage detection method and system based on angular point detection | |
| CN115351598A (en) | Numerical control machine tool bearing detection method | |
| CN110378313B (en) | Cell cluster identification method and device and electronic equipment | |
| CN111862194A (en) | Deep learning plant growth model analysis method and system based on computer vision | |
| CN109410192B (en) | Fabric defect detection method and device based on multi-texture grading fusion | |
| CN107316301B (en) | Convenient online detection system for concentration of suspended particles in sewage | |
| CN115019158B (en) | Image recognition-based marine pollution area recognition method and system | |
| CN108827597B (en) | Light spot uniformity detection method and detection system of structured light projector | |
| CN105225523A (en) | A kind of parking space state detection method and device | |
| CN114792314B (en) | Laser beam-based metal mesh defect detection method and artificial intelligence system | |
| CN117392469B (en) | Perovskite battery surface coating detection method and system based on machine vision | |
| CN112683166B (en) | Die-cutting product size detection method | |
| CN114663393A (en) | Convolutional neural network-based detection method for defect of poor spacing between photovoltaic modules | |
| CN116561535B (en) | Individualized building interaction design processing method | |
| CN116363136B (en) | On-line screening method and system for automatic production of motor vehicle parts | |
| CN115001394B (en) | Solar cell state monitoring method and system based on artificial intelligence | |
| CN115830302A (en) | Multi-scale feature extraction and fusion power distribution network equipment positioning identification method | |
| CN114125435B (en) | Intelligent image defect detection method for network camera | |
| CN115659195A (en) | Online atmospheric pollution identification method | |
| CN114862786A (en) | Retinex image enhancement and Ostu threshold segmentation based isolated zone detection method and system | |
| CN111861950A (en) | Method and device for detecting fabric surface ball area | |
| CN117173492B (en) | Intelligent recognition method for abnormal production of composite board | |
| CN117437228B (en) | Photovoltaic steel structure component fracture detection method based on image characteristics |
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 |