CN112365450A - Method, device and storage medium for classifying and counting articles based on image recognition - Google Patents
Method, device and storage medium for classifying and counting articles based on image recognition Download PDFInfo
- Publication number
- CN112365450A CN112365450A CN202011146495.0A CN202011146495A CN112365450A CN 112365450 A CN112365450 A CN 112365450A CN 202011146495 A CN202011146495 A CN 202011146495A CN 112365450 A CN112365450 A CN 112365450A
- Authority
- CN
- China
- Prior art keywords
- image
- article
- gray
- binary image
- carrying
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 230000009466 transformation Effects 0.000 claims abstract description 13
- 230000007547 defect Effects 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims description 19
- 230000005484 gravity Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 241001270131 Agaricus moelleri Species 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 2
- 238000005192 partition Methods 0.000 claims description 2
- 239000012535 impurity Substances 0.000 description 10
- 238000010586 diagram Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 3
- 241000519995 Stachys sylvatica Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of article identification statistics, in particular to an article classification counting method based on image identification, a device and a storage medium, wherein the method comprises the following steps: acquiring a photo of an article; selecting a picture of an article, carrying out gray level transformation on the picture, and then carrying out filtering processing to obtain a binary image; extracting color features according to the binary image, then carrying out image graying processing, sequentially extracting the outline and geometric shape features of the article, and then obtaining a target area image by the difference between the original image and the binary image; filling and repairing defects existing in the target area image to obtain an optimized binary image; and scanning and identifying the optimized binary image in the up-down and left-right sequence to obtain the quantity of the articles. According to the invention, the image quality is improved, so that the image area is complete, the judgment of a program on a frame can be reduced, the speed is increased, and meanwhile, the error rate is reduced by extracting the geometric shape features.
Description
Technical Field
The invention relates to the technical field of article identification statistics, in particular to an article classification counting method and device based on image identification and a storage medium.
Background
In the places of assembly lines or article mixing, articles need to be classified and counted, and at present, manual counting methods are generally adopted for classification and counting. This method is labor and time consuming and inefficient.
Image recognition is a basic technical means of artificial intelligence, and at present, image recognition is realized by extracting the characteristics of each pixel point in an image to be recognized, comparing the characteristics with the characteristics of each pixel point in the existing image, and outputting an article in the existing image as the article in the image to be recognized when the similarity of the characteristics of the pixel points is compared in a set range. However, there is a problem that the image processing function is insufficient: the article becomes blurred after the photo processing of the article, and the photo processing of the article is lost, thereby causing inaccurate statistics.
Disclosure of Invention
The present invention is directed to a method, an apparatus and a storage medium for sorting and counting articles based on image recognition, so as to solve the problems mentioned in the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a method of item sort counting based on image recognition, comprising:
acquiring an image: acquiring a photo of an article;
preprocessing of the image: selecting a picture of an article, carrying out gray level transformation on the picture, and then carrying out filtering processing to obtain a binary image;
feature extraction of the article: extracting color features according to the binary image, then carrying out image graying processing, sequentially extracting the outline and geometric shape features of the article, and then obtaining a target area image by the difference between the original image and the binary image;
the quality of the image is improved: filling and repairing defects existing in the target area image to obtain an optimized binary image;
counting articles: and scanning and identifying the optimized binary image in the up-down and left-right sequence to obtain the quantity of the articles.
Preferably, the gray scale transformation performs gray scale processing on the leaf by using a weighted average method, and the gray scale transformation is performed by using a formula: g-0.299 r +0.587G +0.114b converts the 32-bit RGB image into a 256-bit grayscale map, where: g is a gray value, r, G and b are values of 3 components of red, green and blue in the RGB image respectively, and the filtering process is median filtering.
Preferably, the color features are extracted by adopting a color histogram; the image graying processing includes: reading of three primary color 24bit values, defining a scaling matrix
Determining a division gray level value: mmax255; obtaining a gray-to-inverse function when Mmin is 0, and determining a transformation function and an equalization coefficient: pr 0.3, Pg 0.59, Pb 0.l1, to realize equalization, gray scale and frequency adjustment, to complete gray scale image processing, wherein: gray-value g-b, r-Sr，g＝g*Sg，b＝b*Sb， Sr、Sg、SbRespectively, the transformed image R, G, B gray scale value, Mmax、MminRespectively corresponding to a white gray value and a black gray value; the extracting the item profile includes: removing most background gray scales from the histogram by adopting an OSTU threshold segmentation method, and then performing secondary segmentation on the remaining objects and shadow parts by using the OSTU threshold segmentation method after removing the background; the extracting geometric features includes: and calculating several region-based geometric parameters of the article according to the extracted article contour, wherein the geometric parameters comprise region area, major axis, minor axis, average distance from the region gravity center to the article boundary and mean square error of the distance from the region gravity center to each point of the boundary.
Preferably, the OSTU threshold segmentation method includes: let the threshold obtained by 1 OSTU threshold segmentation be q0On this basis, the 2 nd OSTU threshold division is performed for gray levels 0 to q: firstly, the average gray level of the pixel between 0 and q is calculated
The variance was then calculated with 1, 2, 3 … k … q-1 as the threshold:
Preferably, the defect filling and repairing of the target area image uses the target pixel as a central point, and when the gray levels of at least 1 pixel in the upper, lower, left, right and four neighborhoods of the target area image are different from the gray level of the target pixel, the gray level of the central point is replaced by the gray level of 255 (black), so that the purpose of eliminating white point noise can be achieved.
Preferably, the ratio of the area of the region multiplied by the major axis and the minor axis is the squareness of the article, and the ratio of the average distance from the center of gravity of the region to the boundary of the article and the average variance of the distances from the center of gravity of the region to each point of the boundary is the circularity of the article.
In order to achieve the above purpose, the invention also provides the following technical scheme:
an apparatus for sorting and counting articles based on image recognition, comprising:
the acquisition module is used for acquiring a photo of an article;
the preprocessing module is used for carrying out gray level transformation on the object picture and then carrying out filtering processing to obtain a binary image;
the characteristic extraction module is used for extracting color characteristics according to the binary image, then carrying out image graying processing, sequentially extracting the outline and geometric shape characteristics of the article, and then obtaining a target area image by the difference between the original image and the binary image;
the quality improvement module is used for filling and repairing the defects of the target area image to obtain an optimized binary image; and
and the counting module is used for scanning and identifying the optimized binary image in the vertical, horizontal and left sequences to obtain the quantity of the articles.
In order to achieve the above purpose, the invention also provides the following technical scheme:
a computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor, when executing the computer program, performs the steps of the method according to any of the preceding claims.
In order to achieve the above purpose, the invention also provides the following technical scheme:
a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of the preceding claims.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, through the first gray processing, smaller impurities in the article image can be filtered, the area of larger impurities is reduced, the color is lightened, the article part is not blurred while the impurities are removed, the second gray processing can enable the details of the image to be clear, the visual effect of the image is improved, the image quality is improved through an OSTU threshold segmentation method, the image area is complete, the judgment of a program on a frame can be reduced, the speed is increased, and meanwhile, the error rate is reduced by extracting geometric shape features.
Drawings
FIG. 1 is a block diagram of a method for sorting and counting articles based on image recognition according to the present invention;
FIG. 2 is a schematic representation of a grayed article of the present invention;
FIG. 3 is a schematic diagram of the invention for median filtering to desalt white spots and impurities on an article;
FIG. 4 is a schematic diagram of a binary image obtained by the secondary OSTU threshold segmentation of the present invention;
FIG. 5 is a block diagram of an apparatus for sorting and counting articles based on image recognition according to the present invention;
FIG. 6 is an internal structural view of a computer apparatus of the present invention;
fig. 7 is a schematic diagram of the object image feature extraction and identification method and counting according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 to 7, the present invention provides a technical solution:
a method of item sort counting based on image recognition, comprising:
s101, acquiring an image: acquiring a photo of an article;
s102, preprocessing of the image: selecting a picture of an article, carrying out gray level transformation on the picture, and then carrying out filtering processing to obtain a binary image;
s103, feature extraction of the articles: extracting color features according to the binary image, then carrying out image graying processing, sequentially extracting the outline and geometric shape features of the article, and then obtaining a target area image by the difference between the original image and the binary image;
s104, improving the quality of the image: filling and repairing defects existing in the target area image to obtain an optimized binary image;
s105, counting articles: and scanning and identifying the optimized binary image in the up-down and left-right sequence to obtain the quantity of the articles.
Specifically, the gray scale transformation adopts a weighted average method to perform gray scale processing on the leaf, converts an image from an RGB color space to a gray scale space, and firstly uses a formula: g-0.299 r +0.587G +0.114b converts the 32-bit RGB image into a 256-bit grayscale map, where: g is a gray value, r, G and b are values of 3 components of red, green and blue in the RGB image respectively, and the filtering process is median filtering. In order to reduce the interference of noise to the image processing link, the noise of the image is reduced by adopting a median filtering method, namely, a window with odd points is used, and the value of the center point of the window is replaced by the median of each point in the window. As can be seen from fig. 2-3, smaller impurities have been substantially filtered out, larger impurities have smaller areas and lighter colors, and are easily processed in the subsequent binarization. The impurity is removed while the article part is not changed to be very fuzzy, and the result is better.
Specifically, the color features are extracted by adopting a color histogram; the image graying processing includes: reading of three primary color 24bit values, defining a scaling matrix
Determining a division gray level value: mmax255; obtaining a gray-to-inverse function when Mmin is 0, and determining a transformation function and an equalization coefficient: pr 0.3, Pg 0.59, Pb 0.l1, to realize equalization, gray scale and frequency adjustment, to complete gray scale image processing, wherein: gray-value g-b, r-Sr，g＝g*Sg，b＝b*Sb， Sr、Sg、SbRespectively, the transformed image R, G, B gray scale value, Mmax、MminCorresponding to the white gray scale value and the black gray scale value, respectively, as shown in fig. 3, a better image gray scale processing effect is obtained, so that the details of the image become clear, and the visual effect of the image is improved.
The extracting the item profile includes: and removing most background gray scales from the histogram by adopting an OSTU threshold segmentation method, and then performing secondary segmentation on the rest objects and shadow parts after removing the background by adopting the OSTU threshold segmentation method. Specifically, the OSTU threshold segmentation method includes: let the threshold obtained by 1 OSTU threshold segmentation be q0On this basis, the 2 nd OSTU threshold division is performed for gray levels 0 to q: firstly, the average gray level of the pixel between 0 and q is calculated
The variance was then calculated with 1, 2, 3 … k … q-1 as the threshold:
The extracting geometric features includes: and calculating several region-based geometric parameters of the article according to the extracted article contour, wherein the geometric parameters comprise region area, major axis, minor axis, average distance from the region gravity center to the article boundary and mean square error of the distance from the region gravity center to each point of the boundary. The product ratio of the area of the region to the long axis and the short axis is the rectangle degree of the article, and the ratio of the average distance from the gravity center of the region to the boundary of the article and the mean square difference of the distances from the gravity center of the region to each point of the boundary is the circularity degree of the article. The recognition rate can be effectively improved by extracting the geometric shape characteristics, and the automatic classification of the articles is realized.
According to the invention, through the first gray processing, smaller impurities in the article image can be filtered, the area of larger impurities is reduced, the color is lightened, the article part is not blurred while the impurities are removed, the second gray processing can enable the details of the image to be clear, the visual effect of the image is improved, the image quality is improved through an OSTU threshold segmentation method, the image area is complete, the judgment of a program on a frame can be reduced, the speed is increased, and meanwhile, the error rate is reduced by extracting geometric shape features.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. A method for classifying and counting articles based on image recognition is characterized by comprising the following steps:
acquiring an image: acquiring a photo of an article;
preprocessing of the image: selecting a picture of an article, carrying out gray level transformation on the picture, and then carrying out filtering processing to obtain a binary image;
feature extraction of the article: extracting color features according to the binary image, then carrying out image graying processing, sequentially extracting the outline and geometric shape features of the article, and then obtaining a target area image by the difference between the original image and the binary image;
the quality of the image is improved: filling and repairing defects existing in the target area image to obtain an optimized binary image;
counting articles: and scanning and identifying the optimized binary image in the up-down and left-right sequence to obtain the quantity of the articles.
2. The method for classifying and counting articles based on image recognition as claimed in claim 1, wherein the gray scale transformation grays the leaves by a weighted average method according to a formula: g-0.299 r +0.587G +0.114b converts the 32-bit RGB image into a 256-bit grayscale map, where: g is a gray value, r, G and b are values of 3 components of red, green and blue in the RGB image respectively, and the filtering process is median filtering.
3. The method for classifying and counting the articles based on the image recognition is characterized in that the color features are extracted by adopting a color histogram; the image graying processing includes: reading of three primary color 24bit values, defining a scaling matrix
Determining a division gray level value: mmax255; obtaining a gray-to-inverse function when Mmin is 0, and determining a transformation function and an equalization coefficient: pr 0.3, Pg 0.59, Pb 0.l1, to realize equalization, gray scale and frequency adjustment, to complete gray scale image processing, wherein: gray-value g-b, r-Sr，g＝g*Sg，b＝b*Sb，Sr、Sg、SbRespectively, the transformed image R, G, B gray scale value, Mmax、MminRespectively corresponding to a white gray value and a black gray value; the extracting the item profile includes: removing most background gray scales from the histogram by adopting an OSTU threshold segmentation method, and then performing secondary segmentation on the remaining objects and shadow parts by using the OSTU threshold segmentation method after removing the background; the extracting geometric features includes: and calculating several region-based geometric parameters of the article according to the extracted article contour, wherein the geometric parameters comprise region area, major axis, minor axis, average distance from the region gravity center to the article boundary and mean square error of the distance from the region gravity center to each point of the boundary.
4. The method of claim 3, wherein the OSTU thresholding comprises: let the threshold obtained by 1 OSTU threshold segmentation be q0On this basis, the 2 nd OSTU threshold division is performed for gray levels 0 to q: firstly, the average gray level of the pixel between 0 and q is calculated
The variance was then calculated with 1, 2, 3 … k … q-1 as the threshold:
5. The method as claimed in claim 4, wherein the defect filling and repairing for the target area image uses the target pixel as the center point, and when the gray levels of at least 1 pixel in the upper, lower, left, right four neighborhoods of the target area image are different from the gray level of the target pixel, the gray level of 255 is used to replace the gray level of the center point, so as to achieve the purpose of eliminating the white point noise.
6. The method as claimed in claim 4, wherein the ratio of the area of the region multiplied by the major axis and the minor axis is the rectangularity of the article, and the ratio of the average distance from the center of gravity of the region to the boundary of the article and the mean square difference of the distances from the center of gravity of the region to the points of the boundary is the circularity of the article.
7. An apparatus for classifying and counting articles based on image recognition, comprising:
the acquisition module is used for acquiring a photo of an article;
the preprocessing module is used for carrying out gray level transformation on the object picture and then carrying out filtering processing to obtain a binary image;
the characteristic extraction module is used for extracting color characteristics according to the binary image, then carrying out image graying processing, sequentially extracting the outline and geometric shape characteristics of the article, and then obtaining a target area image by the difference between the original image and the binary image;
the quality improvement module is used for filling and repairing the defects of the target area image to obtain an optimized binary image; and
and the counting module is used for scanning and identifying the optimized binary image in the vertical, horizontal and left sequences to obtain the quantity of the articles.
8. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 4 when executing the computer program.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011146495.0A CN112365450A (en) | 2020-10-23 | 2020-10-23 | Method, device and storage medium for classifying and counting articles based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011146495.0A CN112365450A (en) | 2020-10-23 | 2020-10-23 | Method, device and storage medium for classifying and counting articles based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112365450A true CN112365450A (en) | 2021-02-12 |
Family
ID=74511841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011146495.0A Pending CN112365450A (en) | 2020-10-23 | 2020-10-23 | Method, device and storage medium for classifying and counting articles based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112365450A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160182A (en) * | 2021-04-25 | 2021-07-23 | 湖南九九智能环保股份有限公司 | Stacking section counting system based on image recognition |
| CN113160181A (en) * | 2021-04-25 | 2021-07-23 | 湖南九九智能环保股份有限公司 | Stacking profile counting method based on image recognition |
| CN114554294A (en) * | 2022-03-04 | 2022-05-27 | 天比高零售管理(深圳)有限公司 | Live broadcast content filtering and prompting method |
| CN115457037A (en) * | 2022-11-10 | 2022-12-09 | 澳润(山东)药业有限公司 | Raw material quality inspection method for donkey-hide gelatin product production |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101789080A (en) * | 2010-01-21 | 2010-07-28 | 上海交通大学 | Detection method for vehicle license plate real-time positioning character segmentation |
| US20170301081A1 (en) * | 2015-09-30 | 2017-10-19 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for determining a breast region in a medical image |
| CN108830877A (en) * | 2018-06-08 | 2018-11-16 | 中国石油化工股份有限公司 | The stereoscopic micro-image quantitative description of rock core |
| CN110543857A (en) * | 2019-09-05 | 2019-12-06 | 安徽启新明智科技有限公司 | Contraband identification method, device and system based on image analysis and storage medium |
| CN111223115A (en) * | 2020-04-22 | 2020-06-02 | 杭州涂鸦信息技术有限公司 | Image segmentation method, device, equipment and medium |
-
2020
- 2020-10-23 CN CN202011146495.0A patent/CN112365450A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101789080A (en) * | 2010-01-21 | 2010-07-28 | 上海交通大学 | Detection method for vehicle license plate real-time positioning character segmentation |
| US20170301081A1 (en) * | 2015-09-30 | 2017-10-19 | Shanghai United Imaging Healthcare Co., Ltd. | System and method for determining a breast region in a medical image |
| CN108830877A (en) * | 2018-06-08 | 2018-11-16 | 中国石油化工股份有限公司 | The stereoscopic micro-image quantitative description of rock core |
| CN110543857A (en) * | 2019-09-05 | 2019-12-06 | 安徽启新明智科技有限公司 | Contraband identification method, device and system based on image analysis and storage medium |
| CN111223115A (en) * | 2020-04-22 | 2020-06-02 | 杭州涂鸦信息技术有限公司 | Image segmentation method, device, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 肖志云: ""结合Otsu与EM的啤酒平图像分割及动态计数研究"", 《重庆理工大学学报（自然科学）》, vol. 34, no. 8, 31 August 2020 (2020-08-31) * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160182A (en) * | 2021-04-25 | 2021-07-23 | 湖南九九智能环保股份有限公司 | Stacking section counting system based on image recognition |
| CN113160181A (en) * | 2021-04-25 | 2021-07-23 | 湖南九九智能环保股份有限公司 | Stacking profile counting method based on image recognition |
| CN113160181B (en) * | 2021-04-25 | 2021-12-03 | 湖南九九智能环保股份有限公司 | Stacking profile counting method based on image recognition |
| CN114554294A (en) * | 2022-03-04 | 2022-05-27 | 天比高零售管理(深圳)有限公司 | Live broadcast content filtering and prompting method |
| CN115457037A (en) * | 2022-11-10 | 2022-12-09 | 澳润(山东)药业有限公司 | Raw material quality inspection method for donkey-hide gelatin product production |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112365450A (en) | Method, device and storage medium for classifying and counting articles based on image recognition | |
| US11257194B2 (en) | Method for image dehazing based on adaptively improved linear global atmospheric light of dark channel | |
| CN112419250A (en) | Pavement crack digital image extraction, crack repair and crack parameter calculation method | |
| CN105046252B (en) | A kind of RMB prefix code recognition methods | |
| CN109191459A (en) | The automatic identification and ranking method of continuous casting billet macrostructure center segregation defect | |
| CN115063421B (en) | Pole piece region detection method, system and device, medium and defect detection method | |
| CN111915704A (en) | Apple hierarchical identification method based on deep learning | |
| CN111986222A (en) | Intelligent electric meter chip image binarization processing method based on self-adaptive mixed threshold value | |
| CN103175844A (en) | Detection method for scratches and defects on surfaces of metal components | |
| CN112861654B (en) | Machine vision-based famous tea picking point position information acquisition method | |
| CN115937216A (en) | Magnetic rotor appearance quality detection method for new energy automobile | |
| CN115619775B (en) | Material counting method and device based on image recognition | |
| CN108830857A (en) | A kind of adaptive Chinese character rubbings image binaryzation partitioning algorithm | |
| CN109544583A (en) | A kind of method, device and equipment for extracting Leather Image area-of-interest | |
| CN114299051A (en) | Leather material surface defect detection method based on feature modeling significance detection | |
| CN115082776A (en) | Electric energy meter automatic detection system and method based on image recognition | |
| CN112509026A (en) | Insulator crack length identification method | |
| CN116934787A (en) | Image processing method based on edge detection | |
| CN112288726A (en) | Method for detecting foreign matters on belt surface of underground belt conveyor | |
| CN115620075A (en) | Method, system and equipment for generating data set for leukocyte classification model | |
| CN111476784A (en) | Product surface defect online detection method based on image enhancement recognition technology | |
| CN108205678B (en) | Nameplate character recognition processing method containing bright spot interference | |
| CN105608683A (en) | Defogging method of single image | |
| CN113610187B (en) | Wood texture extraction and classification method based on image technology | |
| CN111881921A (en) | Optimal grain direct selection method for rice color selector |
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 |