CN109829465B - Method for searching optimum sucking position of prawn and identifying tail limb characteristics - Google Patents
Method for searching optimum sucking position of prawn and identifying tail limb characteristics Download PDFInfo
- Publication number
- CN109829465B CN109829465B CN201910004638.5A CN201910004638A CN109829465B CN 109829465 B CN109829465 B CN 109829465B CN 201910004638 A CN201910004638 A CN 201910004638A CN 109829465 B CN109829465 B CN 109829465B
- Authority
- CN
- China
- Prior art keywords
- shrimp
- tail
- point
- polygon
- searching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Abstract
The invention discloses a method for searching the optimum sucking position of prawns and identifying the characteristics of a tail limb, which relates to the field of machine vision and comprises the following steps: intercepting an interested area of the color image of the shrimp tail and binarizing; calculating the area of each communicated area to screen shrimps meeting the requirements; performing polygon fitting on the edge of each communication area, and calculating the vertex of the tail part; carrying out a debranching operation on the polygon to obtain a debranched polygon; calculating the minimum circumscribed rectangle of the branch-removed polygon, calculating the eigenvalue vector of the shrimps, and judging whether to perform subsequent processing; judging point sets of the shrimp belly and the shrimp back of the shrimps needing subsequent treatment according to the minimum circumscribed rectangle; judging the turning point of the tail limb of the shrimp in the abdominal point of the shrimp; separating the skeleton line of the shrimp from the back spot of the shrimp; searching the best sucking position of the sucking disc. The invention can accurately extract the complete skeleton line of the shrimp tail and identify the position of the tail limb, improves the success rate of sucking the shrimp, and provides important position parameters for placing the shrimp tail to a uniform position.
Description
Technical Field
The invention relates to the field of machine vision, in particular to a method for searching an optimal suction position of a prawn and identifying characteristics of a tail limb.
Background
Conventional food factories rely heavily on manual labor. With the advent of industry 4.0, many food factories introduced automated production lines, replacing repetitive labor of workers with robots and software. However, the shape of individual food products is different greatly, and the repetitive motion of a fixed track cannot meet the requirement, so that machine vision must be introduced for online feature recognition to provide sufficient position information for an automatic production line to process the food products.
Machine vision is a technology for providing required information for downstream automation equipment by analyzing image information provided by a vision sensor according to actual application tasks, and is widely applied to tasks such as target detection, quality monitoring and robot guidance in industry. The inspection target in the industrial field is often a standard workpiece with a simple shape, while the inspection target in the food industry has more complex shape characteristics. The prawn is a common aquatic food material, but the limbs of the prawn are irregular, the bending degree of the prawn feet, the prawn tail and the prawn back is possible, the extraction of the body characteristics of the prawn by the existing identification technology is not accurate enough, the success rate of prawn suction is affected, and further the processing and production of the prawn are affected.
Therefore, the technical personnel in the field are dedicated to developing a method for searching the optimum sucking position of the prawns and identifying the characteristics of the tail limbs, and solving the problem that the existing identification technology is not accurate enough for extracting the body characteristics of the prawns.
Disclosure of Invention
In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is how to accurately search the optimum sucking position of the prawn and identify the characteristics of the tail limb.
In order to achieve the purpose, the invention provides a method for searching the optimal suction position of prawns and identifying the characteristics of the tail limbs, which comprises the following steps:
step 1, intercepting an interested area of a color image of the shrimp tail, performing binarization, and performing corresponding morphological operation to obtain a binarized image of the shrimp tail;
step 2, calculating the area of each communication region for the binarized image of the shrimp tail in the step 1, screening out the region with the area within a certain range, and screening out the shrimps with the bending degree meeting the requirement through the length-width ratio of the minimum external rectangle;
step 3, performing polygon fitting on the edge of each communication area in the step 2, and calculating a tail vertex PE;
step 4, carrying out a debranching operation on the polygon in the step 3 to obtain a debranching polygon;
step 5, calculating the minimum circumscribed rectangle of the branch polygon in the step 4, calculating the eigenvalue vector of the shrimp, and judging whether to perform subsequent processing;
step 6, judging point sets of the shrimp belly and the shrimp back of the shrimps needing to be subjected to subsequent treatment in the step 5 according to the minimum circumscribed rectangle;
step 7, judging the turning point PE of the shrimp tail limb in the shrimp abdominal points of the point set in the step 6 1 ；
Step 8, separating a skeleton line S of the shrimp closer to the shrimp belly from the shrimp back points collected in the step 6 H And skeleton line S closer to the back of the shrimp W ；
And 9, searching the optimal sucking position of the sucking disc.
Further, the tail vertex PE in step 3 is the point of the polygon vertex that is farthest from the polygon centroid.
Further, the operation of removing the branches in step 4 is to traverse the vertices of the polygon, delete the vertices conforming to the branch characteristics, and repeat this step for the new polygon formed after deleting the vertices conforming to the branch characteristics until all the vertices do not conform to the branch characteristics.
Further, the branch feature is when the internal angle α of a vertex is adjacent to two edges d 1 ,d 2 One of the following conditions is satisfied:
(1)α＜α poly0 ；
(2)α＜α poly1 and max (d) 1 ,d 2 )＜d poly1 ；
(3)α＜α poly2 And (max (d) 1 ,d 2 )＜d poly2 Or min (d) 1 ,d 2 )＜d poly3 )；
Wherein alpha is poly0 ,α poly1 ,α poly2 ,d poly1 ,d poly2 ,d poly3 Are all preset threshold values.
Further, the eigenvalue vector in step 5 is the length and width, the deflection angle and the center coordinate of the minimum circumscribed rectangle.
Further, the method for determining whether to perform the subsequent processing in step 5 is to compare the feature value vector with all feature value vectors stored in the dynamic container, if there is a similar feature value vector, it indicates that the shrimp has appeared in the camera field in the previous process and is calculated, so as to skip all the subsequent processing, otherwise, it is considered that the shrimp appears in the camera field for the first time, and the feature value vector is stored in the dynamic container and is subjected to the subsequent processing.
Further, the method for judging the point sets of the shrimp belly and the shrimp back in the step 6 is as follows: recording the vertex of the minimum circumscribed rectangle closest to the tail vertex PE as P on the polygon obtained in the step 4 1 The corresponding long side vertex is P 2 (ii) a By PE and polygon vertex neutral distance P 2 The nearest point is a boundary, the polygon is divided into two parts, the average distance between two point sets and the long side is calculated, the point set with small average distance is judged as the shrimp belly, and the point set with large average distance is judged as the shrimp back.
Further, the method for determining the turning point of the shrimp tail limb in the step 7 is as follows: searching the peak meeting the following conditions on the shrimp belly point set obtained in the step 6, and judging the peak as the turning point PE of the shrimp tail limb 1 ：
(1) The internal angle alpha is more than 190 degrees;
(2) A length d from PE
Wherein A is the area of the polygon, d εmin ,d εmax ,A std Are all preset threshold values.
Further, the method for separating the skeleton line of the shrimps in the step 8 comprises the following steps: performing expansion operation through a certain size to obtain a part in the polygonal enclosure in the edge line of the connected domain as a skeleton line of the shrimp, obtaining two skeleton lines at different positions through one large size and one small size, and marking the skeleton line closer to the shrimp belly as S H The skeleton line closer to the back of the shrimp is S W 。
Further, the searching method in step 9 is: recording the turning point PE obtained in step 7 1 The distance between the top point PE of the tail part of the shrimp obtained in the step 3 is the length L of the tail limb of the shrimp 1 S obtained in step 8 W Upper pitch PE 1 The nearest point is the starting point, and the path length from the starting point along the direction of the head of the shrimp is gamma L 1 Point of (2)As suction point PX of suction cup 1 Recording the fixed distance between two suckers as L 2 S obtained in step 8 H Upper search distance PX 1 Linear distance L 2 Point of (2) as a suction point PX of the suction cup 2 。
The invention can accurately extract the complete skeleton line of the shrimp tail and identify the position of the tail limb, improves the success rate of sucking the scattered and piled prawns by adopting the double suction trays with fixed intervals, and provides important position parameters for placing the prawns at a uniform position.
The conception, the specific structure and the technical effects of the present invention will be further described with reference to the accompanying drawings to fully understand the objects, the features and the effects of the present invention.
Drawings
FIG. 1 is a color image taken by a camera in accordance with a preferred embodiment of the present invention;
FIG. 2 is an image after the region of interest is intercepted, binarized and morphologically manipulated according to a preferred embodiment of the present invention;
FIG. 3 is a schematic diagram of the connected area of a selected single prawn according to a preferred embodiment of the present invention;
FIG. 4 is a result of a polygon fit according to a preferred embodiment of the present invention;
FIG. 5 is a diagram of the polygon debranching results of a preferred embodiment of the present invention;
FIG. 6 is a diagram of the boundary point between the long side of the minimum bounding rectangle and the shrimp heads and shrimp tails according to a preferred embodiment of the present invention;
FIG. 7 is a profile of a preferred embodiment of the invention after shrimp postcoital expansion;
FIG. 8 is a skeleton line obtained after two sizes of inflation according to a preferred embodiment of the present invention;
FIG. 9 is a shrimp tail limb turning point in the polygon vertex for a preferred embodiment of the present invention;
FIG. 10 shows a preferred embodiment of the invention for searching the suction point PX of the suction cup 1 A path of (a);
fig. 11 is a final effect diagram of a preferred embodiment of the present invention.
Wherein, 11-shrimp tail boundary point, 12-shrimp head boundary point, 13-shrimp tail limb turning point, 14-sucking disc suction point PX 1 15-suction point PX of suction cup 2 21-the long side of the smallest circumscribed rectangle, 22-the expanded outline of the shrimp back line, 23-the skeleton line closer to the shrimp back, 24-the skeleton line closer to the shrimp belly, 25-the search suction point PX 1 The path of (2).
Detailed Description
The technical contents of the preferred embodiments of the present invention will be made clear and easily understood by referring to the drawings attached to the specification. The present invention may be embodied in many different forms of embodiments and the scope of the invention is not limited to the embodiments set forth herein.
In the drawings, structurally identical elements are represented by like reference numerals, and structurally or functionally similar elements are represented by like reference numerals throughout the several views. The size and thickness of each component shown in the drawings are arbitrarily illustrated, and the present invention is not limited to the size and thickness of each component. The thickness of the components may be exaggerated where appropriate in the figures to improve clarity.
In the embodiment, aiming at the aquatic product processing automation assembly line which adopts the double suction trays with fixed spacing to suck prawns which are randomly stacked and place the prawns in a unified position, the robot and the camera are firstly opened, the camera image is collected through the industrial personal computer, the robot is calibrated by hands and eyes, and the conversion relation and the scaling ratio from the image coordinate system to the robot coordinate system are obtained. Then, a hard trigger signal is sent to an industrial personal computer and a camera at regular time through an upper computer, and identification and positioning software embedded with the method is opened on the industrial personal computer. After software is started, a local parameter file is automatically loaded, and a 'start acquisition' button is clicked to start implementing the method. The acquired image is shown in fig. 1. The implementation steps are as follows:
step 1, software waits for a camera to send an image, intercepts an interested region after receiving a color image, binarizes the image, and performs corresponding morphological operation to obtain a binary image of the shrimp tail, as shown in fig. 2.
And 2, screening the area and the position of each connected domain, and taking the connected domain with each area within a specified range and without contacting with the edge as a complete single prawn, as shown in figure 3.
And 3, performing polygon fitting on each selected connected domain, and taking the polygon vertex farthest from the centroid as the shrimp tail vertex as shown in fig. 4.
And 4, traversing the vertexes of the polygon, removing the vertexes conforming to the branch characteristics, and repeating the traversal until no vertex conforms to the branch characteristics, wherein the result is shown in fig. 5.
And 5, fitting the minimum circumscribed rectangle of the de-branched polygon, taking the length, the width, the deflection angle and the center coordinate of the minimum circumscribed rectangle as the characteristic values of the shrimps, and storing the shrimps in a dynamic container. And taking the length, the width, the deflection angle and the central coordinate of the minimum circumscribed rectangle as a characteristic value vector of the shrimp, comparing the characteristic value vector with all characteristic value vectors stored in the dynamic container, if the characteristic value vectors are close to each other, indicating that the shrimp appears in the camera visual field in the previous process and calculating, and therefore omitting all subsequent processing, otherwise, considering that the shrimp appears in the camera visual field for the first time, storing the characteristic value vector in the dynamic container and performing the subsequent processing.
And 6, as shown in fig. 6, finding out two boundary points of the polygon, namely a shrimp tail boundary point 11 and a shrimp head boundary point 12 according to the distance between the vertex of the polygon and the vertex of the minimum external rectangle, dividing the vertex of the polygon into two point sets, and recording the two point sets as a back point set and an abdomen point set respectively according to the average distance between the two point sets and the long edge 21 of the minimum external rectangle.
And 7, as shown in fig. 9, searching for a satisfactory shrimp tail limb turning point 13 in the abdominal point set.
And 8, as shown in fig. 7, expanding the shrimp back line according to a certain size to obtain the expanded contour line 22 of the shrimp back line. The portion of the outline inside the polygonal enclosure is taken as the skeleton line of the shrimp, and the same operation is performed in another size to obtain another skeleton line, as shown in fig. 8, a skeleton line 23 closer to the back of the shrimp and a skeleton line 24 closer to the belly of the shrimp are obtained.
Step 9, recording PE 1 At a distance L from PE 1 To do so byPE 1 As a reference, at S W Upper pitch PE 1 The nearest point is the starting point, and the path length from the starting point along the direction of the head of the shrimp is gamma L 1 As the suction point PX of the sucking disc 1 And then PX 1 For reference, searching for an extraction point PX on a skeleton line near the back of the shrimp 2 FIG. 10 shows the method for searching the sucking point PX of the sucking disc 1 Of the path 25. As a result of the final processing of the picture shown in FIG. 11, the suction point PX of the suction cup 1 Point 14, suction point PX of suction cup 2 Point 15.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (8)
1. A method for searching the optimal suction position of a prawn and identifying the characteristics of a tail limb is characterized by comprising the following steps:
step 1, intercepting an interested area of a color image of the shrimp tail, performing binarization, and performing corresponding morphological operation to obtain a binarized image of the shrimp tail;
step 2, calculating the area of each communicated region of the binarized image of the shrimp tail in the step 1, screening out the regions with the areas within a certain range, and screening out the shrimps with the curvatures meeting the requirements through the length-width ratio of the minimum external rectangle;
step 3, performing polygon fitting on the edge of each communication area in the step 2, and calculating a tail vertex PE;
step 4, carrying out a debranching operation on the polygon in the step 3 to obtain a debranching polygon;
step 5, calculating the minimum circumscribed rectangle of the branch polygon in the step 4, calculating the eigenvalue vector of the shrimp, and judging whether to perform subsequent processing;
step 6, judging point sets of the shrimp belly and the shrimp back of the shrimps needing to be subjected to subsequent treatment in the step 5 according to the minimum circumscribed rectangle;
step 7, judging the turning point PE of the shrimp tail limb in the shrimp abdominal points of the point set in the step 6 1 ；
Step 8, separating a skeleton line S of the shrimp closer to the shrimp belly from the shrimp back points collected in the step 6 H And skeleton line S closer to the back of the shrimp W ；
Step 9, searching the optimal suction position of the sucker;
wherein the content of the first and second substances,
in step 5, the method for judging whether to perform the subsequent processing is as follows: comparing the characteristic value vector with all characteristic value vectors stored in the dynamic container, if the characteristic value vectors are similar, indicating that the shrimp appears in the camera visual field in the previous process and calculating, and therefore skipping all subsequent processing, otherwise, considering that the shrimp appears in the camera visual field for the first time, storing the characteristic value vectors in the dynamic container and performing subsequent processing;
in step 9, the method for searching the optimal suction position of the suction cup includes: recording the turning point PE obtained in the step 7 1 The distance between the top point PE of the tail part of the shrimp obtained in the step 3 is the length L of the tail limb of the shrimp 1 S obtained in said step 8 W Upper pitch PE 1 The nearest point is the starting point, and the path length from the starting point along the direction of the shrimp head is gamma L 1 Point of (2) as a suction point PX of the suction cup 1 The fixed distance between the two suckers is recorded as L 2 S obtained in said step 8 H Upper search distance PX 1 Linear distance L 2 Point of (2) as a suction point PX of the suction cup 2 。
2. The method for searching the best sucking position and identifying the characteristics of the tail limb of the prawn as claimed in claim 1, wherein the tail vertex PE in the step 3 is the point of the polygon vertex which is farthest from the centroid of the polygon.
3. The method as claimed in claim 1, wherein the operation of removing branches in step 4 is to traverse the vertices of the polygon, delete the vertices matching the branch feature, and repeat the steps for the new polygon formed after the vertices matching the branch feature are deleted until all the vertices do not match the branch feature.
4. The method for searching for the optimum sucking position and identifying the characteristics of the tail limbs of prawn as claimed in claim 3, wherein said branch characteristics are the internal angle α of a certain vertex and the adjacent two sides d 1 ,d 2 One of the following conditions is satisfied:
(1)α＜α poly0 ；
(2)α＜α poly1 and max (d) 1 ,d 2 )＜d poly1 ；
(3)α＜α poly2 And (max (d) 1 ,d 2 )＜d poly2 Or min (d) 1 ,d 2 )＜d poly3 )；
Wherein alpha is poly0 ,α poly1 ,α poly2 ,d poly1 ,d poly2 ,d poly3 Are all preset threshold values.
5. The method for searching the optimal suction position and identifying the characteristics of the tail limbs of the prawns as claimed in claim 1, wherein the characteristic value vectors in the step 5 are the length, the width, the deflection angle and the central coordinates of the minimum circumscribed rectangle.
6. The method for searching the optimum sucking position and identifying the characteristics of the tail limbs of the prawns as claimed in claim 1, wherein the point sets of the belly and the back of the prawns in the step 6 are determined by the following steps: recording the vertex of the minimum circumscribed rectangle closest to the tail vertex PE as P on the polygon obtained in the step 4 1 The corresponding long side vertex is P 2 (ii) a By PE and polygon vertex neutral distance P 2 The nearest point is a boundary, the polygon is divided into two parts, the average distance between two point sets and the long side is calculated, the point set with small average distance is judged as the shrimp belly, and the point set with large average distance is judged as the shrimp back.
7. The method for searching for the optimum sucking position and identifying the characteristics of the shrimp tail according to claim 1, wherein the method for determining the turning point of the shrimp tail in step 7 is: searching the peak meeting the following conditions on the shrimp belly point set obtained in the step 6, and judging the peak as the turning point PE of the shrimp tail limb 1 ：
(1) The internal angle alpha is more than 190 degrees;
(2) A length d from PE
Wherein A is the area of the polygon, d εmin ,d εmax ,A std Are all preset threshold values.
8. The method for searching the optimum sucking position and identifying the characteristics of the tail limbs of the prawns as claimed in claim 1, wherein the skeleton line separation method of the prawns in the step 8 is as follows: performing expansion operation through a certain size to obtain a part of the edge line of the connected domain in the polygonal enclosure as a skeleton line of the shrimp, obtaining two skeleton lines at different positions through one large size and one small size, and recording the skeleton line closer to the shrimp belly as S H The skeleton line closer to the back of the shrimp is S W 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910004638.5A CN109829465B (en) | 2019-01-03 | 2019-01-03 | Method for searching optimum sucking position of prawn and identifying tail limb characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910004638.5A CN109829465B (en) | 2019-01-03 | 2019-01-03 | Method for searching optimum sucking position of prawn and identifying tail limb characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109829465A CN109829465A (en) | 2019-05-31 |
| CN109829465B true CN109829465B (en) | 2023-03-24 |
Family
ID=66861541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910004638.5A Active CN109829465B (en) | 2019-01-03 | 2019-01-03 | Method for searching optimum sucking position of prawn and identifying tail limb characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109829465B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110738631A (en) * | 2019-08-26 | 2020-01-31 | 中国农业机械化科学研究院 | prawn shape information detection method and detection system based on images |
| CN111650196B (en) * | 2020-04-13 | 2021-08-06 | 浙江大学 | Sick shrimp red body disease detection device based on machine vision technique |
| CN111832532A (en) * | 2020-07-24 | 2020-10-27 | 上海电气集团自动化工程有限公司 | Online visual detection method and system for crayfish pose identification |
| CN112173639B (en) * | 2020-10-15 | 2022-03-29 | 佛山松瀚智能设备有限公司 | Feeding and conveying method of automatic shrimp peeling machine |
| CN112173703A (en) * | 2020-10-15 | 2021-01-05 | 佛山松瀚智能设备有限公司 | Feeding and conveying system of automatic shrimp peeling machine |
| CN113642847B (en) * | 2021-07-15 | 2023-08-04 | 中国农业大学 | Method and device for estimating prawn quality |
| CN115009575B (en) * | 2022-07-22 | 2023-04-14 | 中国农业大学 | Grading tray arranging system and method for semi-finished shrimps |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203018326U (en) * | 2012-12-21 | 2013-06-26 | 浙江大学 | Prawn quality detecting-grading device based on machine vision technology |
| CN103801520A (en) * | 2014-01-27 | 2014-05-21 | 浙江大学 | Method and device for automatically carefully sorting and grading shrimps |
| CN104646313A (en) * | 2013-11-25 | 2015-05-27 | 王健 | Machine vision-based prawn online separation system |
| CN105117701A (en) * | 2015-08-21 | 2015-12-02 | 郑州轻工业学院 | Corn crop row skeleton extraction method based on largest square principle |
| CN105389586A (en) * | 2015-10-20 | 2016-03-09 | 浙江大学 | Method for automatically detecting integrity of shrimp body based on computer vision |
| CN106900601A (en) * | 2017-02-09 | 2017-06-30 | 浙江大学 | A kind of fast accurate identification prawn image shrimp head method of the point with shrimp tail point |
| CN106991667A (en) * | 2017-03-08 | 2017-07-28 | 浙江大学 | A kind of prawn integrality method of discrimination for building characteristics of image spectrum |
| WO2017221259A1 (en) * | 2016-06-23 | 2017-12-28 | S Jyothi | Automatic recognition of indian prawn species |
| CN108388874A (en) * | 2018-03-05 | 2018-08-10 | 厦门大学 | Prawn morphological parameters method for automatic measurement based on image recognition and cascade classifier |
| CN108960011A (en) * | 2017-05-23 | 2018-12-07 | 湖南生物机电职业技术学院 | The citrusfruit image-recognizing method of partial occlusion |
-
2019
- 2019-01-03 CN CN201910004638.5A patent/CN109829465B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203018326U (en) * | 2012-12-21 | 2013-06-26 | 浙江大学 | Prawn quality detecting-grading device based on machine vision technology |
| CN104646313A (en) * | 2013-11-25 | 2015-05-27 | 王健 | Machine vision-based prawn online separation system |
| CN103801520A (en) * | 2014-01-27 | 2014-05-21 | 浙江大学 | Method and device for automatically carefully sorting and grading shrimps |
| CN105117701A (en) * | 2015-08-21 | 2015-12-02 | 郑州轻工业学院 | Corn crop row skeleton extraction method based on largest square principle |
| CN105389586A (en) * | 2015-10-20 | 2016-03-09 | 浙江大学 | Method for automatically detecting integrity of shrimp body based on computer vision |
| WO2017221259A1 (en) * | 2016-06-23 | 2017-12-28 | S Jyothi | Automatic recognition of indian prawn species |
| CN106900601A (en) * | 2017-02-09 | 2017-06-30 | 浙江大学 | A kind of fast accurate identification prawn image shrimp head method of the point with shrimp tail point |
| CN106991667A (en) * | 2017-03-08 | 2017-07-28 | 浙江大学 | A kind of prawn integrality method of discrimination for building characteristics of image spectrum |
| CN108960011A (en) * | 2017-05-23 | 2018-12-07 | 湖南生物机电职业技术学院 | The citrusfruit image-recognizing method of partial occlusion |
| CN108388874A (en) * | 2018-03-05 | 2018-08-10 | 厦门大学 | Prawn morphological parameters method for automatic measurement based on image recognition and cascade classifier |
Non-Patent Citations (2)
| Title |
|---|
| 基于机器视觉技术的对虾规格检测方法研究;罗艳;《中国优秀硕士学位论文全文数据库信息科技辑》;20130615(第6期);全文 * |
| 基于机器视觉技术的缺损对虾在线识别与剔除系统研究;张伟;《中国优秀硕士学位论文全文数据库信息科技辑》;20180615(第6期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109829465A (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829465B (en) | Method for searching optimum sucking position of prawn and identifying tail limb characteristics | |
| CN109724990B (en) | Method for quickly positioning and detecting code spraying area in label of packaging box | |
| CN110648367A (en) | Geometric object positioning method based on multilayer depth and color visual information | |
| CN109658402B (en) | Automatic detection method for geometric dimension of industrial profile based on computer vision imaging | |
| CN113077437B (en) | Workpiece quality detection method and system | |
| CN112883881B (en) | Unordered sorting method and unordered sorting device for strip-shaped agricultural products | |
| CN106529551B (en) | Intelligent recognition counting detection method for round-like objects in packaging industry | |
| JP6288230B2 (en) | Object division method and apparatus | |
| CN111402238A (en) | Defect identification system realized through machine vision | |
| Potapova et al. | Attention-driven object detection and segmentation of cluttered table scenes using 2.5 d symmetry | |
| CN106900601B (en) | Method for quickly and accurately identifying shrimp head points and shrimp tail points of prawn image | |
| Chen et al. | A practical solution for ripe tomato recognition and localisation | |
| CN111932490B (en) | Visual system grabbing information extraction method for industrial robot | |
| CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
| Huang et al. | Implementation of workpiece recognition and location based on opencv | |
| CN115880699A (en) | Food packaging bag detection method and system | |
| CN109658388B (en) | Method for detecting and correcting packaging box segmentation errors based on vision and active interaction | |
| CN105057899B (en) | A kind of scanogram recognition methods being applied to Intelligent Laser cutting | |
| CN113989308A (en) | Polygonal target segmentation method based on Hough transform and template matching | |
| Chelouati et al. | Lobster detection using an Embedded 2D Vision System with a FANUC industrual robot | |
| TWI543117B (en) | Method for recognizing and locating object | |
| CN109934817B (en) | Method for detecting malformation of external contour of fruit body | |
| Mohana et al. | Stem-calyx recognition of an apple using shape descriptors | |
| Baird | Image Segmentation Technique for Locating Automotive Parts on Belt Conveyors. | |
| CN114049380A (en) | Target object positioning and tracking method and device, computer equipment and storage medium |
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 |