CN110570422B - Capsule defect visual detection method based on matrix analysis - Google Patents
Capsule defect visual detection method based on matrix analysis Download PDFInfo
- Publication number
- CN110570422B CN110570422B CN201910880056.3A CN201910880056A CN110570422B CN 110570422 B CN110570422 B CN 110570422B CN 201910880056 A CN201910880056 A CN 201910880056A CN 110570422 B CN110570422 B CN 110570422B
- Authority
- CN
- China
- Prior art keywords
- capsule
- image
- matrix
- region
- interest
- 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
- 239000002775 capsule Substances 0.000 title claims abstract description 164
- 239000011159 matrix material Substances 0.000 title claims abstract description 63
- 230000007547 defect Effects 0.000 title claims abstract description 57
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 230000000007 visual effect Effects 0.000 title claims abstract description 11
- 238000004458 analytical method Methods 0.000 title claims abstract description 10
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 3
- 239000003814 drug Substances 0.000 claims description 11
- 238000003709 image segmentation Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 5
- 230000002950 deficient Effects 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000011179 visual inspection Methods 0.000 claims 1
- 230000011218 segmentation Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- 210000004798 organs belonging to the digestive system Anatomy 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 210000002345 respiratory system Anatomy 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- 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
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G01N2021/8883—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 involving the calculation of gauges, generating models
-
- 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
- G06T2207/10004—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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color 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
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Medical Preparation Storing Or Oral Administration Devices (AREA)
Abstract
The invention discloses a capsule defect visual detection method based on matrix analysis. Firstly, the image preprocessing mainly comprises three steps of extracting a capsule plate area, correcting the color of an image and converting the color space of the image; then, carrying out block division on the image of the region of interest of the capsule cap, obtaining transverse and longitudinal segmentation coordinates, and constructing a capsule existence matrix; and finally, processing and analyzing the capsule existence matrix to judge the capsule defect, and marking the capsule position with the defect according to the coordinates of the block division. Compared with the traditional manual detection mode, the invention has the advantages that the manual labor force is liberated, the detection efficiency is improved, and the detection result has higher stability and reliability; compared with the existing machine vision detection mode, the method has the advantages that the image operation is converted into matrix operation, the operation process is simplified, the data processing amount during detection is reduced, and the detection speed is improved.
Description
Technical Field
The invention relates to a machine vision defect detection method used in the field of medicine production and processing, in particular to a machine vision detection method for defects such as capsule missing, medicine cap dislocation, homochromatic and the like.
Background
The capsule has the advantages of protecting the powdery medicine from being decomposed in the oral cavity, avoiding damage of the medicine to digestive organs and respiratory tracts, being convenient and easy to use, and the like, and is one of the main packaging modes of medicines in the market. However, various defects cannot be avoided in the production process of the medicine, and in order to improve the delivery quality of the medicine, defect detection is required. The detection of the defects of the capsules is mainly performed manually at present, but the defects of low efficiency, low reliability of detection results and the like exist in manual detection, and the requirements of industrial production cannot be met.
The machine vision technology provides an automatic solution for detecting the defects of the capsules, and the detection method based on the image processing technology has the advantages of eliminating tedious work of detection personnel, reducing labor cost in production, along with long-time stable and reliable work, high detection efficiency, high speed and the like, and is suitable for industrial mass production compared with a manual detection mode.
Domestic related researches are mostly conducted in theory, while foreign related mature products are expensive in large polyvalent, such as a SADE capsule classification detection machine in the United kingdom, a capsule weighing and defect detection machine of MOCOM company in the United states, and the like. At present, the machine vision detection of the capsule defects still has many problems, the defect detection type is single, the requirement on matched hardware is high, many methods require a plurality of cameras of different types to realize the defect detection in a matched mode, or the matched hardware is required to be specially designed, and some detection methods based on machine learning require a large number of sample training learning and identification classification.
Therefore, the invention provides a capsule defect visual detection method based on matrix analysis.
Disclosure of Invention
The invention provides a method for rapidly detecting capsule defects based on a machine vision technology and a matrix analysis idea aiming at the technical problem to be solved.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a visual detection method of capsule defects based on matrix analysis is characterized in that: the method comprises the steps of obtaining an original image of a capsule, extracting an area image of a capsule plate, preprocessing the area image of the capsule plate, extracting an area of interest of a capsule cap, constructing a capsule existence matrix, identifying a capsule defect and the like.
The method for acquiring the original image of the capsule comprises the following steps: the original capsule image to be detected is a capsule image acquired in real time by an industrial camera from a capsule defect detection system or capsule image data acquired and stored in advance is read.
The extraction method of the capsule plate area image comprises the following steps: traversing all contours in an original image of the capsule, wherein a contour area with the largest area is a capsule plate, and rotating and correcting the area by affine transformation to obtain an area image of the capsule plate due to the fact that the area of the capsule plate possibly has certain angle deflection.
The pretreatment method of the capsule plate area image comprises the following steps: color correction is carried out on the image of the capsule plate area by adopting a gray world method; since the HSV color space is more suitable for color image segmentation than the RGB color space, the capsule plate area image is converted from the RGB color space to the HSV color space.
The extraction method of the interested region of the capsule cap comprises the following steps: and extracting a medicine cap with one color in the capsule from the preprocessed capsule plate area image by adopting a fixed-threshold color image segmentation method in the HSV color space to obtain a capsule cap region-of-interest image with the color.
The method for dividing the blocks of the region of interest image comprises the following steps: according to the position of each capsule cap, carrying out block division on the region-of-interest image based on a projection method, namely acquiring the coordinates of a transverse dividing line and a longitudinal dividing line of the region-of-interest image; and respectively carrying out transverse or longitudinal projection, namely counting the number of black pixels in each column or each row in the image of the region of interest, and easily obtaining transverse coordinates and longitudinal coordinates of image block division because the black pixels are distributed in different regions in a transverse or longitudinal discrete manner.
The construction method of the capsule existence matrix comprises the following steps: constructing a capsule existence matrix based on the block-divided region-of-interest image, wherein each capsule cap region in the region-of-interest image has a one-to-one correspondence with the capsule existence matrix; the basic idea is as follows: and (3) at the transverse center of each column of capsule caps, calculating the number of black pixels in the longitudinal partition interval of the capsule caps, if the number exceeds a set threshold value, setting the corresponding position 1 of the capsule existence matrix, otherwise setting 0, and processing each column in turn from left to right to construct the capsule existence matrix.
The identification method of the capsule defect comprises the following steps: firstly, constructing a template capsule existence matrix without defects according to the capsule existence matrix; then, performing exclusive OR operation on the template matrix and the capsule existence matrix to obtain a defect judgment matrix; finally, analyzing the defect judgment matrix to identify defects, dividing the defect judgment matrix by taking two rows and one column as a unit, calculating the sum of all elements in each unit, and if the sum is 0, judging that no defects exist; if the sum is 1, the defective capsules are the same color or are in missing capsules; if the sum is 2, there is a defective capsule cap ectopic.
The beneficial effects of the invention are as follows: according to the capsule defect visual detection method based on matrix analysis, disclosed by the invention, the capsule image to be detected is obtained in real time through the industrial color camera, the defect detection is carried out on the obtained image based on the image processing technology, the tedious work of manual detection is avoided, and the problems of low manual detection efficiency, poor detection result reliability and the like are solved. The method is suitable for the qualification detection of the capsule medicines in industrial production, converts long-time image operation into short-time feature matrix operation, and has great advantages in the aspect of detection efficiency.
Drawings
FIG. 1 is an overall flow chart of capsule defect detection of the present invention.
Fig. 2 is an original image of a capsule obtained by the present invention.
Fig. 3 is an image of the area of a capsule plate extracted by the present invention.
Fig. 4 is an image of the capsule plate area after color correction in accordance with the present invention.
Fig. 5 is an image of a capsule cap region of interest extracted in accordance with the present invention.
Fig. 6 is a cross-projection scatter plot of an image of a region of interest of the present invention.
Fig. 7 is a longitudinal projected scatter plot of an image of a region of interest of the present invention.
FIG. 8 is a schematic representation of the construction of a capsule presence matrix according to the present invention.
FIG. 9 shows the results of the capsule defect detection of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and examples, which perform defect detection on yellow-green capsules (two capsule caps of which are yellow and green). It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
For example, please refer to fig. 1 to 9: FIG. 1 schematically illustrates an overall flow of the disclosed image processing based capsule defect detection; fig. 2 schematically shows an original image of a capsule obtained according to the invention; FIG. 3 schematically shows an image of the area of a capsule plate extracted according to the present invention; FIG. 4 schematically shows an image of the capsule plate area after color correction in accordance with the present invention; FIG. 5 schematically shows an image of a capsule cap region of interest extracted according to the present invention; FIG. 6 schematically illustrates a cross-projection scatter plot of an image of a region of interest in accordance with the present invention; FIG. 7 schematically illustrates a longitudinal projected scatter plot of an image of a region of interest in accordance with the present invention; FIG. 8 schematically shows a schematic representation of the construction of a capsule presence matrix according to the invention; fig. 9 schematically shows the results of the capsule defect detection of the present invention.
According to the flow shown in fig. 1, the capsule defect is detected according to the following steps:
(1) Acquiring a capsule image in real time through an industrial camera or reading capsule image data acquired and stored in advance to obtain a capsule original image I src As shown in fig. 2. Image I src The color image based on the RGB color space comprises two images of a capsule plate area to be detected and an ineffective background area.
(2) In order to extract a capsule plate area image to be detected, detecting all contours in the image by using a contour marking algorithm, calculating the area of all contour containing areas, wherein the contour area corresponding to the maximum area is the capsule plate area, calculating the deflection angle theta of the area, and obtaining a capsule plate area image I after rotationally correcting the image by using affine transformation based on the deflection angle theta cap As shown in fig. 3.
(3) Image I in the capsule plate area under the influence of illumination and camera parameter settings cap Some color deviation may exist in the image, the gray world color balance algorithm is adopted to correct the color difference, the influence of the ambient light on the color display is eliminated, and the processed image is shown in fig. 4. The gray world method is based on the assumption that: for RGB images with a large number of color variations, the average of the three color components tends to the same gray value, the basic idea is to first calculate the gray average R of R, G, B three components av 、G av 、B av The gains G of the components are calculated respectively R 、G G 、G B And finally, calculating the color components after balance through a gray level transformation formula, wherein the specific calculation is shown in a formula (1).
Compared to the RGB color spaceThe HSV color space is more in line with the visual sense of people and is also more suitable for image segmentation, and the RGB color space is more suitable for electronic display of images, so that before the image segmentation, the color-balanced images are converted from the RGB color space to the HSV color space to obtain an image I HSV 。
Where X represents R, G, B three components, M and N representing the number of pixels in the lateral and longitudinal directions of the image, respectively.
(4) In order to separate the target detection area from the background area, the preprocessed image I HSV Image segmentation is performed. In the implementation, a color image segmentation method with fixed threshold is adopted based on an HSV color space, the upper and lower threshold values of a target area are set according to the color of a capsule cap to be extracted, the image of the region of interest of a green capsule cap is extracted, and due to some miscellaneous points or holes possibly existing in the image of the region of interest, the image is rounded by morphological opening operation, and finally the image I of the region of interest of the capsule cap is obtained roi As shown in fig. 5.
(5) Image I roi The capsule caps are distributed in a form and can be in one-to-one correspondence with the matrix, and the image I is needed according to the positions of the capsule caps roi And performing transverse and longitudinal division, namely acquiring coordinates of transverse and longitudinal dividing lines of the image, and realizing the operation based on a projection method. Taking the transverse projection as an example, the number of black pixel points in each column in the image is counted, and the scatter diagram is shown in fig. 6, and obviously, the image I roi The middle black pixels are uniformly distributed in different intervals, and the transverse division coordinate array L of the image is obtained and recorded according to the middle black pixels X . Wherein, when a special condition exists and a capsule cap is completely missing, the data of the transverse divided coordinate array is missing, the judgment condition of the condition is that the divided coordinate distance D i Greater than standard interval D c Standard interval calculation is as in equation (2), the solution is that missing position coordinates are filled with 0, the number of fillsThe longitudinal projection is the same, the scatter diagram is shown in figure 7, and the longitudinal division coordinate array is L Y 。
Where Width is the number of pixels in the image in the lateral direction and Cols is the number of columns of capsules.
(6) After the capsule cap division is completed, based on image I roi The capsule presence matrix is constructed, and a matrix construction schematic is shown in fig. 8. The basic idea is as follows: and calculating the number of black pixels in the longitudinal partition interval of each column of capsule caps at the transverse center of the capsule caps, if the number exceeds a set threshold value, setting the corresponding position 1 of the capsule existence matrix, otherwise, setting 0, and sequentially processing each column to construct the capsule existence matrix.
In particular, the transverse center coordinates XC of each column of capsule caps are calculated i If XC, as shown in equation (3) i Equal to 0, the capsule presence matrix is set to 0 for all columns. At the coordinates XC i At each point, the longitudinal division intervals L are calculated Y [j]To the point ofAnd->To L Y [j+1]Black pixels in between, where j=0, 2, …, (Rows-2), rows is the number of Rows of capsules.
The black pixel number value and the threshold valueIn comparison, if greater than or equal to threshold, the capsule presence matrix corresponds to position 1,otherwise, set to 0. The final capsule presence matrix A is shown in formula (4).
(7) And processing and analyzing the capsule existence matrix to identify possible capsule defects. From matrix a, a defect-free template capsule presence matrix C is constructed, the basic idea of which is that the minority obeys the majority principle, and the orientation of the majority capsules is positive. Specifically, the sum of elements of one row in the matrix a is calculated, if the sum value is greater than or equal to half of the number of columns of the capsule, the template exists in a corresponding row of all-set 1 in the matrix C, otherwise all-set 0. The template capsule presence matrix C of the example is shown in formula (5).
And performing exclusive OR operation on the matrix C and the matrix A to obtain a capsule defect judging matrix F, wherein the capsule defect judging matrix F is shown in a formula (6).
The analysis defect judgment matrix F identifies possible capsule defects. Dividing a matrix F by taking two rows and one column as units, wherein each unit represents a capsule, calculating the sum of all elements in each unit, and if the sum is 0, no defect exists; if the sum is 1, the defect of capsule deficiency or the same color of the medicine cap exists; if the sum is 2, there is a defect of ectopic capsule cap. Finally, the capsule positions with defects are marked by rectangular frames according to the capsule cap segmentation coordinates, and the visual detection result of the defects of the capsule in the embodiment is shown in fig. 9.
While the foregoing description of the embodiments of the present invention has been presented in conjunction with the drawings, it should be understood that it is not intended to limit the scope of the invention, but rather, it is intended to cover all modifications or variations within the scope of the invention as defined by the claims of the present invention.
Claims (2)
1. A visual detection method of capsule defects based on matrix analysis is characterized in that: the method comprises the steps of obtaining an original image of a capsule, extracting an image of a capsule plate area, preprocessing the image of the capsule plate area, extracting a capsule cap region of interest, dividing a block of the region of interest, constructing a capsule existence matrix and identifying a capsule defect;
the acquisition of the original image of the capsule comprises the following steps: the original image of the capsule to be detected is a capsule image acquired in real time by an industrial camera from a capsule defect visual detection system or capsule image data acquired and stored in advance is read;
the extraction of the capsule plate area image comprises the following steps: traversing all contours in an original image of the capsule, wherein a contour area with the largest area is a capsule plate, and rotating and correcting the area by affine transformation to obtain an area image of the capsule plate because the area of the capsule plate possibly has certain angle deflection;
the extraction of the region of interest of the capsule cap comprises the following steps: extracting a medicine cap with one color in a capsule from the preprocessed capsule plate area image by adopting a fixed-threshold color image segmentation method in an HSV color space to obtain a capsule cap region-of-interest image with the color;
the block division of the region of interest includes: according to the position of each capsule cap, carrying out block division on the region-of-interest image based on a projection method, namely acquiring the coordinates of a transverse dividing line and a longitudinal dividing line of the region-of-interest image; respectively carrying out transverse or longitudinal projection, namely counting the number of black pixels in each column or each row in the image of the region of interest, and easily obtaining transverse coordinates and longitudinal coordinates of image block division because the black pixels are distributed in different regions in a transverse or longitudinal discrete manner;
the construction of the capsule existence matrix comprises the following steps: constructing a capsule existence matrix based on the block-divided region-of-interest image, wherein each capsule cap region in the region-of-interest image has a one-to-one correspondence with elements in the capsule existence matrix; the basic idea is as follows: at the transverse center of each column of capsule caps, calculating the number of black pixels in the longitudinal partition interval of the capsule caps, if the number exceeds a set threshold value, setting the corresponding position 1 of the capsule existence matrix, otherwise setting 0, and sequentially processing each column from left to right to construct the capsule existence matrix;
the identification of the capsule defect comprises the following steps: firstly, constructing a defect-free template capsule existence matrix according to the capsule existence matrix, and calculating the sum of one row in the capsule existence matrix, if the sum is greater than or equal to half of the number of columns of the capsules, setting the corresponding row in the template capsule existence matrix as 1, otherwise, setting the corresponding row as 0; secondly, performing exclusive OR operation on the template existence matrix and the capsule existence matrix to obtain a defect judgment matrix; then analyzing the defect judgment matrix to identify defects, dividing the defect judgment matrix by taking two rows and one column as a unit, calculating the sum of all elements in each unit, and if the sum is 0, judging that no defects exist; if the sum is 1, the defective capsules are the same color or are in missing capsules; if the sum is 2, defective capsule cap is ectopic; finally, marking the defective capsules to finish visual detection of the defects of the capsules.
2. The matrix analysis-based capsule defect visual inspection method according to claim 1, wherein: color correction is carried out on the image of the capsule plate area by adopting a gray world method; since the HSV color space is more suitable for color image segmentation than the RGB color space, the capsule plate area image is converted from the RGB color space to the HSV color space.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910880056.3A CN110570422B (en) | 2019-09-18 | 2019-09-18 | Capsule defect visual detection method based on matrix analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910880056.3A CN110570422B (en) | 2019-09-18 | 2019-09-18 | Capsule defect visual detection method based on matrix analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110570422A CN110570422A (en) | 2019-12-13 |
| CN110570422B true CN110570422B (en) | 2024-02-27 |
Family
ID=68780781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910880056.3A Active CN110570422B (en) | 2019-09-18 | 2019-09-18 | Capsule defect visual detection method based on matrix analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110570422B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111250429B (en) * | 2020-01-15 | 2023-08-25 | 深圳市太赫兹科技创新研究院有限公司 | Method and device for detecting sealing defect |
| CN111398308B (en) * | 2020-03-27 | 2023-01-17 | 上海健康医学院 | Automatic detection method and system for packaging quality of aluminum-plastic bubble caps of tablets and capsules |
| CN114998097A (en) * | 2022-07-21 | 2022-09-02 | 深圳思谋信息科技有限公司 | Image alignment method, device, computer equipment and storage medium |
| CN115393318A (en) * | 2022-08-25 | 2022-11-25 | 朗天药业(湖北)有限公司 | Method and system for detecting appearance quality of Xuesaitong dropping pills |
| CN115482234B (en) * | 2022-10-08 | 2023-09-15 | 浙江花园药业有限公司 | High-precision defect detection method and system for aluminum-plastic blister medicines |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
| WO2017128605A1 (en) * | 2016-01-26 | 2017-08-03 | 上海葡萄纬度科技有限公司 | Educational toy kit and hsv-based magic cube color recognition method therefor |
| CN107084992A (en) * | 2017-04-20 | 2017-08-22 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of capsule detection method and system based on machine vision |
| CN107977671A (en) * | 2017-10-27 | 2018-05-01 | 浙江工业大学 | A kind of tongue picture sorting technique based on multitask convolutional neural networks |
| CN108636830A (en) * | 2018-05-10 | 2018-10-12 | 苏州大学 | The method, apparatus and equipment of defective capsule detection sorting based on machine vision |
-
2019
- 2019-09-18 CN CN201910880056.3A patent/CN110570422B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069790A (en) * | 2015-08-06 | 2015-11-18 | 潍坊学院 | Rapid imaging detection method for gear appearance defect |
| WO2017128605A1 (en) * | 2016-01-26 | 2017-08-03 | 上海葡萄纬度科技有限公司 | Educational toy kit and hsv-based magic cube color recognition method therefor |
| CN107084992A (en) * | 2017-04-20 | 2017-08-22 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of capsule detection method and system based on machine vision |
| CN107977671A (en) * | 2017-10-27 | 2018-05-01 | 浙江工业大学 | A kind of tongue picture sorting technique based on multitask convolutional neural networks |
| CN108636830A (en) * | 2018-05-10 | 2018-10-12 | 苏州大学 | The method, apparatus and equipment of defective capsule detection sorting based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110570422A (en) | 2019-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110570422B (en) | Capsule defect visual detection method based on matrix analysis | |
| CN111507976B (en) | Defect detection method and system based on multi-angle imaging | |
| CN104992449B (en) | Information identification and surface defect online test method based on machine vision | |
| CN110322522B (en) | Vehicle color recognition method based on target recognition area interception | |
| CN103051872B (en) | Based on the belt deflection detection method of Edge extraction | |
| CN109308700A (en) | A kind of visual identity defect inspection method based on printed matter character | |
| CN104616275A (en) | Defect detecting method and defect detecting device | |
| CN112304954B (en) | Part surface defect detection method based on line laser scanning and machine vision | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| CN110991360B (en) | Robot inspection point position intelligent configuration method based on visual algorithm | |
| CN113034464B (en) | Visual real-time detection method for defects of liquid crystal display under multiple backgrounds | |
| CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
| WO2021102741A1 (en) | Image analysis method and system for immunochromatographic detection | |
| CN114119591A (en) | Display screen picture quality detection method | |
| CN113657339A (en) | Instrument pointer counting and reading method and medium based on machine vision | |
| CN113989259B (en) | Photovoltaic panel hot spot detection method based on unmanned aerial vehicle infrared image distortion correction | |
| CN113808104B (en) | Metal surface defect detection method and system based on blocking | |
| CN114708234A (en) | Method and device for identifying number of detonators on automatic bayonet coding all-in-one machine | |
| CN113192061B (en) | Extraction method and device of LED package appearance detection image, electronic equipment and storage medium | |
| CN114581760A (en) | Equipment fault detection method and system for machine room inspection | |
| CN112634179A (en) | Transformer equipment image change detection method and system for preventing camera shake | |
| CN106546196B (en) | A kind of optical axis real-time calibration method and system | |
| CN110866917A (en) | Tablet type and arrangement mode identification method based on machine vision | |
| CN117475233A (en) | Method, device, equipment and computer storage medium for detecting abnormal state of gland | |
| CN117115171A (en) | Slight bright point defect detection method applied to subway LCD display screen |
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 |