CN112330663B - Method for detecting width of cut tobacco based on reducing circle by computer vision - Google Patents
Method for detecting width of cut tobacco based on reducing circle by computer vision Download PDFInfo
- Publication number
- CN112330663B CN112330663B CN202011337868.2A CN202011337868A CN112330663B CN 112330663 B CN112330663 B CN 112330663B CN 202011337868 A CN202011337868 A CN 202011337868A CN 112330663 B CN112330663 B CN 112330663B
- Authority
- CN
- China
- Prior art keywords
- tobacco
- circle
- width
- tobacco shred
- cut tobacco
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
A method for detecting the width of cut tobacco based on computer vision of a reducing circle comprises the following steps: a) The cut tobacco is placed on an object stage and flattened with a glass sheet. B) And acquiring an original tobacco shred image by using an image pickup device. C) The collected original cut tobacco images are subjected to binarization, open operation and other pretreatment to remove cut tobacco images with the area smaller than 20 pixels, and a plurality of target areas are separated so as to treat the cut tobacco one by one. D) Detecting the effective outline of the single cut tobacco. E) Detecting the central line of a single tobacco shred framework. F) And making a diameter-variable circle at one end of the central line with a certain step length, and adaptively adjusting the position of the central line until the maximum radius circle is tangent to the contour line. G) And analyzing the acquired tobacco shred width data, namely screening invalid data, and calculating the average width and the like. The method has the greatest characteristics that the diameter of the largest radius circle tangent to the tobacco shred contour is used as the tobacco shred width, and the method has the characteristics of high accuracy, less flow and high detection speed.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method for detecting the width of cut tobacco by computer vision based on a reducing circle.
Background
The cut tobacco is a main raw material in the cigarette production process and is also a main source of cigarette smoke. The tobacco leaves are processed, the shredding width is usually between 0.7mm and 1.3mm, and the width has great influence on the combustion performance and the sensory quality of cigarettes. At present, the measurement of the tobacco shred width mainly depends on manual measurement, the process is tedious and time-consuming, and different detection personnel and different detection methods can have great influence on the detection result. With the continuous development of computer vision detection technology, the method is continuously applied to various industries due to the characteristics of rapidness, accuracy and the like. The existing computer vision detection technology mainly comprises the processes of image acquisition, image transmission, image analysis and the like, wherein the image analysis technology mainly comprises the steps of image binarization, filtering, segmentation, characteristic value extraction, index detection output and the like.
At present, the domestic detection of tobacco shred width mainly depends on manual detection, and a method of visual detection by means of a computer is also available. Chinese patent CN109946300a provides a method for detecting the cut tobacco processing resistance during air-feeding and roller processing, but does not provide a reasonable and effective width detection method.
Chinese patent CN201910761617.8 provides a new method for measuring tobacco shred width based on machine vision detection technique. The method comprises the steps of skeletonizing tobacco shreds, segmenting, extracting a central line, and calculating the average value of pixels meeting the conditions by setting a single-area pixel width threshold value, a pixel point width deviation coefficient and a standard deviation threshold value range of the central line of the tobacco shreds, so as to obtain the segment tobacco shred width. The method has certain requirements on various threshold setting ranges, needs model regression, is complex in process, is not direct and simple, and has higher requirements on operators.
Chinese patent CN201910984864.4 provides an online adaptive tobacco width measurement method based on machine vision. The method marks a plurality of points on the contour center line, and the marked points are used as the normal lines of the center line, so that the intersection point distance between the normal lines and the tobacco shred contour line is measured to be the tobacco shred width. The method needs to preset templates and match the templates, needs to set matching coefficients and matching matrixes, has higher operation difficulty and causes difficulty to application.
Xia Yingwei et al propose a cut tobacco cut recognition method and cut matching criterion based on Hough transformation, (Xia Yingwei et al. Cut tobacco width measurement method based on computer vision [ J ]. Tobacco science and technology, 2014 (09): 10-14.), the method uses the distance between parallel cut line segments matched on two sides of cut tobacco as cut tobacco width. Although the method can accurately detect the tobacco shred width, the accuracy depends on the line segments matched with each other, and the accuracy is questionable for the tobacco shreds of which the matched line segments cannot be found.
Disclosure of Invention
The invention provides a computer vision tobacco shred width detection method based on a reducing circle based on the problems existing in the existing method. The method can be used for rapidly detecting the tobacco shred width and is used for solving the problems of complicated steps, difficult operation and the like of the existing method.
The invention is realized by the following technical scheme: a method for detecting the width of cut tobacco based on computer vision of a reducing circle comprises the following steps: a) And placing the cut tobacco on a prefabricated glass sheet object stage, flattening, and flattening the cut tobacco to be detected by using another glass sheet under a certain pressure. B) And an original tobacco shred image is acquired by using a camera device at a fixed position, so that the tobacco shred width can be conveniently calibrated in the later period. C) The collected original cut tobacco images are subjected to binarization, open operation and other pretreatment to remove cut tobacco images with the area smaller than 20 pixels, and a plurality of target areas are separated so as to treat the cut tobacco one by one. D) Detecting the effective outline of the single cut tobacco. E) Detecting the central line of a single tobacco shred framework. F) And making a diameter-variable circle at one end of the central line with a certain step length, and adaptively adjusting the position of the central line until the maximum radius circle is tangent to the contour line. G) And analyzing the acquired tobacco shred width data, namely screening invalid data, and calculating the average width and the like.
Preferably, in the step A), the tobacco shreds should be unfolded and flattened as much as possible, and the artificial damages such as breakage, holes and the like are avoided, so that morphological processing and accuracy of measurement results are affected.
Preferably, in step B), in order to reduce image distortion, the image pickup device is arranged right above and at the center of the cut tobacco to be detected, and before step F) detects the width of the cut tobacco, a Zhang Zhengyou method is adopted to calibrate the camera. And the scene light distribution is regulated before the image is acquired, so that the influence caused by the shadow of cut tobacco is reduced.
Preferably, in the step C), the method for obtaining the tobacco shreds comprises the following steps: c1 The cut tobacco image with the area smaller than 20 pixels is deleted by the open operation for the binarized cut tobacco image, and the cut tobacco area with the area smaller than 100 pixels is deleted by the secondary open operation. C2 After the small target area is removed, the 8-communication mark communication area is adopted, the pixel point of the area (non-target area) except the cut tobacco to be detected is set to be 0 (the area is represented as black in the binarized image), and the target area is set to be 1 (white).
Preferably, in step D), the method for obtaining the tobacco shred effective contour comprises the following steps: and the specifier 8 is communicated with and tracks the boundary of the cut tobacco outline to obtain boundary point coordinates, and the coordinates are stored in a matrix form.
Preferably, in step E), the method for detecting the central line of the single tobacco shred skeleton further comprises: the Zhang-Suen iterative refinement algorithm uses a 3*3 pixel window with detection pixels as the center to continuously erode and refine the cut tobacco image until a single pixel is reached.
Preferably, in step F), the method for finding the circle with the largest radius further includes: and taking a certain step length as a circle center point from one end of the tobacco shred thinning center line, and continuously increasing the radius of the circle until the circumferential part point falls outside the tobacco shred contour. Traversing the circumferential coordinate points, judging the circumferential part outside the tobacco shred outline, taking the central coordinate, taking the opposite direction of the central coordinate relative to the central coordinate as the central adjustment direction, and setting a certain step length. Making a circle at the new circle center coordinates, detecting the circumference, and judging whether the new circumference falls outside the tobacco shred outline. If the circumference point falls outside the outline, the adjusted circle is tangential (or slightly intersected) with the outline, the diameter of the circle is used as the local tobacco shred width, and the next point is continuously traversed until all points are traversed.
Preferably, in step G), the measurement accuracy is calibrated by comparison with the standard cut tobacco measurement width. And (3) screening out invalid data by using a statistical method, reducing measurement errors, and counting the average width and the characteristic width of the tobacco shreds by comparing with historical measurement results.
The detection method has the advantages that:
(1) The automatic tobacco shred measurement is realized, the detection flow is shortened, and the detection efficiency is improved.
(2) By comparing with standard tobacco shreds and historical data, extreme data are screened out, the measurement accuracy is continuously improved, the measurement error is reduced, the detection accuracy is improved, and the reference value of the measurement result is ensured.
(3) The diameter of the largest circle tangent with the tobacco shred outline is used as the tobacco shred width, so that the automatic measurement of the tobacco shred width is realized. By continuously adjusting the position of the circle center and the radius, the local maximum circle in the tobacco shred contour is found, and the effectiveness of taking the maximum circle diameter as the tobacco shred width is ensured. In addition, the detection method has less flow, is easy to realize, and provides basis for online detection of the tobacco shred width.
Drawings
Fig. 1 is a flowchart of a tobacco width measurement method of example 1.
Fig. 2 is a schematic view of the tobacco cut filler of example 1 after flattening.
Fig. 3 is a schematic view of the maximum circle of the first cut tobacco in example 1.
Fig. 4 is a schematic view of the maximum circle of the second cut tobacco in example 1.
Detailed Description
The following description of the embodiments of the invention will be made with reference to the accompanying drawings by way of specific examples:
example 1
A method for detecting the width of cut tobacco based on the computer vision of a reducing circle comprises the following specific implementation steps:
a) Taking two tobacco shreds at the outlet of the shredding section, carefully spreading the tobacco shreds on a backboard by using tweezers, flattening the tobacco shreds for image acquisition, and preventing the tobacco shreds from being broken, broken and other morphological influences.
B) Under a proper light distribution environment, a high-resolution camera is adopted to collect the tobacco shred images, and the camera is a calibrated camera, so that the original image of the tobacco shred in fig. 2 is obtained.
C) The collected cut tobacco images are transmitted to an analysis program, and the cut tobacco images are preprocessed through binarization, opening and closing operation, noise reduction, deburring and the like, so that the morphological preprocessing operation of the cut tobacco is completed. And (3) separating the tobacco shreds to make the detected tobacco shreds be white pixels and the other areas be black pixel areas so as to detect the tobacco shreds one by one.
D) And (3) adopting a tracking algorithm, detecting the outline of each cut tobacco in a communication way, further screening out the influence of noise points, burrs, shadows and the like on the measured value, and storing the coordinates of boundary points.
E) And continuously removing pixels at the outer edge of the tobacco shreds in an iterative stripping mode until a single-pixel skeleton is left, and obtaining the central line of the tobacco shreds in fig. 2, as shown in fig. 3 and 4.
F) Starting from one end of the central line, taking points with a certain step length as the center of the diameter-variable circle, continuously increasing the radius of the circle until the circumference appears outside the outline, collecting pixel coordinates of the outer circumference of the cut tobacco outline after judging that some points of the circumference fall outside the cut tobacco outline, and taking the coordinate mean value as the center point of the outline outer point set. The relative position of the center point and the center coordinates is used as the basis for adjusting the center of a circle, the opposite direction of the center point relative to the center coordinates is used as the center adjusting direction, a certain length is adjusted, and a new center is used as a circle with the same radius at the moment, so that the intersecting condition with the cut tobacco contour is judged. If the circumference point does not appear outside the tobacco shred outline, continuing to increase the radius and judging whether the circumference point appears outside the outline; if the circumference point falls outside the outline, the adjusted circle is tangential (or slightly intersected) with the outline, the diameter of the circle is used as the local tobacco shred width, and the next point is continuously traversed until all points are traversed.
G) After the traversing is finished, the tobacco shred and reducing circle images as shown in fig. 3 and 4 and the tobacco shred width measured value are obtained, and the unreasonable values can be screened out through the conventional data calibration to carry out numerical analysis.
In the embodiment, the position and the radius of the circle center are continuously adjusted, so that a local maximum circle in the outline is found, and the diameter of the circle is used as the width of the tobacco shreds. The method is simple to operate and consumes less time. In addition, the width measurement quantity of single cut tobacco can be increased by adjusting the traversing step length, so that the accuracy and the reference value of the measurement result are improved.
Claims (6)
1. A method for detecting the width of cut tobacco based on the computer vision of a reducing circle is characterized in that: the method comprises the following steps:
a) Placing the cut tobacco on a prefabricated glass sheet object stage, flattening, and flattening the cut tobacco to be detected by using another glass sheet under a certain pressure;
b) The original tobacco shred images are acquired by using the camera device at the fixed position, so that the tobacco shred width can be conveniently calibrated in the later period;
c) The collected original tobacco shred images are subjected to binarization, open operation and other pretreatment to remove broken tobacco shred images with the area smaller than 20 pixels, and a plurality of target areas are separated so as to treat the tobacco shreds one by one;
d) Detecting the effective outline of a single cut tobacco;
e) The method for detecting the central line of the single tobacco shred framework comprises the following steps: the Zhang-Suen iterative refinement algorithm uses a 3*3 pixel window with a detection pixel as a center to continuously erode and refine the cut tobacco image until a single pixel is formed;
f) Making a diameter-variable circle at one end of the central line with a certain step length, and adaptively adjusting the position of the central line until the maximum radius circle is tangent to the contour line; the method for searching the maximum radius circle comprises the following steps: continuously increasing the radius of the circle by taking a certain step length as a circle center point from one end of the tobacco shred thinning center line until a circumferential part point falls outside the tobacco shred outline; traversing the circumferential coordinate points, judging the circumferential part outside the tobacco shred outline, taking the central coordinate of the circumferential coordinate points, taking the opposite direction of the central coordinate relative to the central coordinate as the central adjustment direction, and setting a certain step length; making a circle at the new circle center coordinates, detecting the circle, judging whether the new circle falls outside the tobacco shred outline, if a circle point falls outside the outline, indicating that the adjusted circle is just tangential to or slightly intersected with the outline, taking the diameter of the circle as the local tobacco shred width, and continuing to traverse the next point until all points are traversed;
g) And analyzing the acquired tobacco shred width data, namely screening invalid data, and calculating the average width and the like.
2. The reducing circle-based computer vision tobacco width detection method according to claim 1, wherein the method comprises the following steps of: in the step A), the tobacco shreds should be unfolded and flattened as much as possible, and the artificial damage such as breakage, holes and the like is avoided, and the morphological treatment and the accuracy of the measurement result are influenced.
3. The reducing circle-based computer vision tobacco width detection method according to claim 1, wherein the method comprises the following steps of: in the step B), in order to reduce image distortion, a camera device is arranged right above and at the center of the tobacco shred to be detected, and before the tobacco shred width is detected in the step F), a Zhang Zhengyou method is adopted to calibrate a camera; and the scene light distribution is regulated before the image is acquired, so that the influence caused by the shadow of cut tobacco is reduced.
4. The reducing circle-based computer vision tobacco width detection method according to claim 1, wherein the method comprises the following steps of: in the step C), the method for obtaining the tobacco shreds comprises the following steps: c1 The broken tobacco images with the area smaller than 20 pixels are deleted by the open operation for the binarized tobacco shred images, and the broken tobacco shred areas with the area smaller than 100 pixels are deleted by the secondary open operation; c2 After the small target area is removed, the 8-communication mark is adopted to communicate with the area, the pixel point of the non-target area which is the area except the cut tobacco to be detected is set to be 0, the area is represented as black in the binary image, the target area is 1, and the area is represented as white in the binary image.
5. The reducing circle-based computer vision tobacco width detection method according to claim 1, wherein the method comprises the following steps of: in the step D), the method for obtaining the effective contour of the tobacco shreds comprises the following steps: and the specifier 8 is communicated with and tracks the boundary of the cut tobacco outline to obtain boundary point coordinates, and the coordinates are stored in a matrix form.
6. The reducing circle-based computer vision tobacco width detection method according to claim 1, wherein the method comprises the following steps of: in the step G), the measurement accuracy is calibrated by comparing the measurement width with the standard cut tobacco measurement width; and (3) screening out invalid data by using a statistical method, reducing measurement errors, and counting the average width and the characteristic width of the tobacco shreds by comparing with historical measurement results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011337868.2A CN112330663B (en) | 2020-11-25 | 2020-11-25 | Method for detecting width of cut tobacco based on reducing circle by computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011337868.2A CN112330663B (en) | 2020-11-25 | 2020-11-25 | Method for detecting width of cut tobacco based on reducing circle by computer vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112330663A CN112330663A (en) | 2021-02-05 |
| CN112330663B true CN112330663B (en) | 2023-08-01 |
Family
ID=74308903
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011337868.2A Active CN112330663B (en) | 2020-11-25 | 2020-11-25 | Method for detecting width of cut tobacco based on reducing circle by computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112330663B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112862815A (en) * | 2021-03-12 | 2021-05-28 | 江苏鑫源烟草薄片有限公司 | Reconstructed cut stem width detection method based on monocular vision |
| CN112950607B (en) * | 2021-03-15 | 2023-12-22 | 上海烟草集团有限责任公司 | Method, system and computer readable storage medium for detecting tobacco leaf surface width change trend |
| CN114494169A (en) * | 2022-01-18 | 2022-05-13 | 南京邮电大学 | Industrial flexible object detection method based on machine vision |
| CN114578778A (en) * | 2022-03-28 | 2022-06-03 | 苏州以诚科技有限公司 | Vision-based intelligent control system and method for technological parameters |
| CN114985283B (en) * | 2022-04-27 | 2024-03-29 | 韩山师范学院 | Tea leaf identification method based on multi-feature image identification technology |
| CN115496753B (en) * | 2022-11-16 | 2023-04-07 | 山东中烟工业有限责任公司青州卷烟厂 | Tobacco shred structure detection method based on machine vision |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1128003A (en) * | 1965-03-06 | 1968-09-25 | Hauni Werke Koerber & Co Kg | Method of and apparatus for measuring the tobacco content of a tobacco rod |
| WO2018040302A1 (en) * | 2016-08-31 | 2018-03-08 | 上海创和亿电子科技发展有限公司 | Method and system for measuring width of cut tobacco piece or cut stem, and server having said system |
| CN111060014A (en) * | 2019-10-16 | 2020-04-24 | 杭州安脉盛智能技术有限公司 | Online self-adaptive tobacco shred width measuring method based on machine vision |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104515454A (en) * | 2013-09-30 | 2015-04-15 | 贵州中烟工业有限责任公司 | Method for fast detecting width of cut tobacco at outlet of tobacco cutting machine |
| CN108335311B (en) * | 2018-01-22 | 2021-11-09 | 上海烟草集团有限责任公司 | Method for extracting morphological structure characteristics of tobacco leaves, electronic equipment and storage medium |
| CN110345874A (en) * | 2019-08-16 | 2019-10-18 | 上海创和亿电子科技发展有限公司 | A kind of new method based on mechanical vision inspection technology measurement pipe tobacco width |
-
2020
- 2020-11-25 CN CN202011337868.2A patent/CN112330663B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1128003A (en) * | 1965-03-06 | 1968-09-25 | Hauni Werke Koerber & Co Kg | Method of and apparatus for measuring the tobacco content of a tobacco rod |
| WO2018040302A1 (en) * | 2016-08-31 | 2018-03-08 | 上海创和亿电子科技发展有限公司 | Method and system for measuring width of cut tobacco piece or cut stem, and server having said system |
| CN107798672A (en) * | 2016-08-31 | 2018-03-13 | 上海创和亿电子科技发展有限公司 | The width measurements method of pipe tobacco or stem, system and the server with the system |
| CN111060014A (en) * | 2019-10-16 | 2020-04-24 | 杭州安脉盛智能技术有限公司 | Online self-adaptive tobacco shred width measuring method based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| Prediction Method for Moisture Content in Dried Cut Tobacco Based on Combination Model of WNN and ARX;Chengcheng Yuan 等;ICNC-FSKD2018;全文 * |
| 基于计算机视觉的片烟形状测量方法;徐大勇 等;烟草科技;第48卷(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112330663A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112330663B (en) | Method for detecting width of cut tobacco based on reducing circle by computer vision | |
| Yiyang | The design of glass crack detection system based on image preprocessing technology | |
| CN110403232B (en) | Cigarette quality detection method based on secondary algorithm | |
| CN114757900B (en) | Artificial intelligence-based textile defect type identification method | |
| WO2018040302A1 (en) | Method and system for measuring width of cut tobacco piece or cut stem, and server having said system | |
| CN101944231B (en) | Method for extracting wheatear morphological parameters | |
| CN113554631B (en) | Chip surface defect detection method based on improved network | |
| CN114549446B (en) | Cylinder liner defect mark detection method based on deep learning | |
| CN108563979B (en) | Method for judging rice blast disease conditions based on aerial farmland images | |
| CN107590812B (en) | Wheat ear identification and counting method | |
| CN111122590A (en) | Ceramic surface defect detection device and detection method | |
| CN117173661A (en) | Asphalt road quality detection method based on computer vision | |
| CN115393657A (en) | Metal pipe production abnormity identification method based on image processing | |
| CN117808799B (en) | Chamfering equipment processing quality detection method based on artificial intelligence | |
| CN116777917A (en) | Defect detection method and system for optical cable production | |
| CN114985283A (en) | Tea leaf identification method based on multi-feature image identification technology | |
| CN114066924A (en) | Classification method of bacterial colonies | |
| CN115546615A (en) | Chinese herbal medicine rhizome slice identification method, storage medium and electronic equipment | |
| CN117808746A (en) | Fruit quality grading method based on image processing | |
| CN109916923A (en) | A kind of customization plate automatic defect detection method based on machine vision | |
| CN114549403B (en) | Method for detecting intelligent precise geometrical circle centers of multiple monomers of side section of mechanical part | |
| CN110857919A (en) | Tail yarn defect detection method for package filament | |
| CN114152211B (en) | Microscopic image processing-based roundness measurement method for fracturing propping agent | |
| CN112129700B (en) | Image detection method and device for flexible circuit board | |
| CN115170862A (en) | Machine vision-based fresh tobacco part identification method |
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 |