CN109829465A - A method of it searching prawn and most preferably draws position and identification uropodium feature - Google Patents
A method of it searching prawn and most preferably draws position and identification uropodium feature Download PDFInfo
- Publication number
- CN109829465A CN109829465A CN201910004638.5A CN201910004638A CN109829465A CN 109829465 A CN109829465 A CN 109829465A CN 201910004638 A CN201910004638 A CN 201910004638A CN 109829465 A CN109829465 A CN 109829465A
- Authority
- CN
- China
- Prior art keywords
- shrimp
- uropodium
- polygon
- prawn
- point
- 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.)
- Granted
Links
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
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of methods that search prawn most preferably draws position and identifies uropodium feature, are related to field of machine vision, include the following steps: the color image interception area-of-interest and binaryzation of shrimp tail；Each connected region area is calculated to screen satisfactory shrimp；Polygon approach is carried out to the edge of each connected region, calculates caudal apex；Debranching enzyme operation is carried out to polygon, obtains debranching enzyme polygon；The minimum circumscribed rectangle for calculating debranching enzyme polygon, calculates the feature value vector of shrimp, judges whether to subsequent processing；To the shrimp for needing to carry out subsequent processing, the point set of shrimp abdomen and shrimp back is determined according to minimum circumscribed rectangle；Shrimp uropodium turning point is determined in shrimp antinode；The skeleton line of shrimp is isolated in shrimp antapex；Search the best absorption position of sucker.The present invention can accurately extract the complete bone line of shrimp tail and identify the position of uropodium, improve the success rate for drawing prawn, and be placed into uniform location for it and provide important location parameter.
Description
Technical field
The present invention relates to field of machine vision more particularly to a kind of search prawn most preferably to draw position and identification uropodium feature
Method.
Background technique
Traditional bakery and confectionery heavy dependence manual labor.With the arrival of industry 4.0, many bakery and confectioneries are introduced
Automatic production line replaces the repeated labor of worker with robot and software.However the shape difference opposite sex of individual food is larger,
The repetitive of fixation locus cannot be met the requirements, it is therefore necessary to be introduced machine vision and be carried out online feature identification, to provide
Sufficient location information carries out the processing of food to automatic production line.
Machine vision is a kind of according to practical application task, is downstream by the image information that analysis visual sensor provides
Automation equipment provides the technology of information needed, is industrially widely used in target detection, quality monitoring and robot guidance
Etc. tasks.The detection target of industrial circle is often the standard workpiece of simple shape, and the detection target in food service industry has
More complicated shape feature.Prawn is common aquatic product food materials, but itself limbs is irregular, and shrimp foot, shrimp tail and shrimp back are curved
There are various possible situations, the body characteristics of existing identification technology prawn extract not accurate enough Qu Chengdu, will affect absorption
The success rate of prawn, and then influence the processing of prawn.
Therefore, those skilled in the art is dedicated to developing a kind of search prawn and most preferably draws position and identification uropodium feature
Method, solve the problems, such as existing identification technology prawn body characteristics extract it is not accurate enough.
Summary of the invention
In view of the above drawbacks of the prior art, the technical problem to be solved by the present invention is to how accurately search prawn most
Good absorption position and identification uropodium feature.
To achieve the above object, position is most preferably drawn the present invention provides a kind of search prawn and identify the side of uropodium feature
Method includes the following steps:
The color image of shrimp tail is intercepted area-of-interest and carries out binaryzation by step 1, then is corresponding morphology behaviour
Make, obtains the binary image of shrimp tail；
Step 2 calculates each connected region area to the binary image of step 1 shrimp tail, filters out area in a certain range
The satisfactory shrimp of camber is screened by the length-width ratio of minimum circumscribed rectangle in interior region；
Step 3 carries out polygon approach to the edge of each connected region of step 2, calculates caudal apex PE；
Step 4 carries out debranching enzyme operation to step 3 polygon, obtains debranching enzyme polygon；
Step 5, the minimum circumscribed rectangle for calculating step 4 debranching enzyme polygon, calculate the feature value vector of this shrimp, judge
Whether subsequent processing is carried out；
Step 6, the shrimp for needing to carry out subsequent processing to step 5 determine the point of shrimp abdomen and shrimp back according to minimum circumscribed rectangle
Collection；
Step 7, the turning point PE that shrimp uropodium is determined in the shrimp antinode of step 6 point set1；
Step 8, the skeleton line S closer to shrimp abdomen that shrimp is isolated in the shrimp antapex of step 6 point setHIt is carried on the back with closer to shrimp
Skeleton line SW；
Step 9, the best absorption position for searching sucker.
Further, the caudal apex PE in step 3 is point farthest away from polygon mass center in polygon vertex.
Further, the debranching enzyme operation in step 4 is traversal polygon vertex, is carried out to the vertex for meeting branching characteristic
It deletes, meets deletion the new polygon formed behind the vertex of the branching characteristic and repeat this step until all vertex are not inconsistent
Close the branching characteristic.
Further, the branching characteristic is the interior angle when some vertex and adjacent both sides d1,d2Meet the following conditions it
One:
(1) α < αpoly0；
(2) α < αpoly1And max (d1,d2) < dpoly1；
(3) α < αpoly2And (max (d1,d2) < dpoly2Or min (d1,d2) < dpoly3)；
Wherein, αpoly0,αpoly1,αpoly2,dpoly1,dpoly2,dpoly3It is preset threshold value.
Further, the feature value vector in step 5 is that the length and width, deflection angle and center of the minimum circumscribed rectangle are sat
Mark.
Further, the method that subsequent processing is judged whether in step 5 is will be in feature value vector and dynamic container
All feature value vectors of storage are compared, during showing the shrimp before if having similar feature value vector
It appears in camera fields of view and by calculating, therefore skips over all subsequent processings, otherwise it is assumed that the shrimp is to appear in phase for the first time
In the machine visual field, feature value vector is stored in dynamic container and carries out subsequent processing.
Further, the determination method of the point set of step 6 Prawn abdomen and shrimp back is: on the polygon that step 4 obtains, note
In minimum circumscribed rectangle away from caudal apex PE nearest vertex be P1, corresponding long side vertex is P2；In PE and polygon vertex
Away from P2Nearest point is boundary, polygon is divided into two parts, and calculate two point sets to the average distance of long side, will be averaged
It is determined as shrimp abdomen apart from small point set, the big point set of average distance is determined as that shrimp carries on the back.
Further, the determination method of the turning point of step 7 Prawn uropodium is: searching on the shrimp antinode collection that step 6 obtains
The vertex for meeting the following conditions is sought, is determined as the turning point PE of shrimp uropodium1:
(1) 190 ° of interior angle >；
(2) meet away from PE length d
Wherein, A is the area of the polygon, dεmin,dεmax,AstdIt is preset threshold value.
Further, the skeleton line separation method of the shrimp in step 8 is: carrying out expansive working by certain size, obtains
Skeleton line of the part as shrimp into the edge line of connected domain in polygon encirclement, is obtained by small one and large one two kinds of sizes
The skeleton line of two different locations remembers that the skeleton line closer to shrimp abdomen is SH, the skeleton line carried on the back closer to shrimp is SW。
Further, the method for searching in step 9 is: the turning point PE that note step 7 obtains1The shrimp tail obtained with step 3
The distance of portion vertex PE is shrimp uropodium length L1, in the S that step 8 obtainsWOn away from PE1Nearest point is starting point, along shrimp head
It is γ L that the path length apart from starting point is searched in direction1Point as sucker suction point PX1, remember that the fixed range of two interambulacrums is
L2, in the S that step 8 obtainsHUpper search is away from PX1Linear distance is L2Point as sucker suction point PX2。
The present invention can accurately extract the complete bone line of shrimp tail and identify the position of uropodium, between improving using fixing
Away from Double-sucker draw stacking at random prawn success rate, and provide important location parameter to be placed into uniform location.
It is described further below with reference to technical effect of the attached drawing to design of the invention, specific structure and generation, with
It is fully understood from the purpose of the present invention, feature and effect.
Detailed description of the invention
Fig. 1 is the color image of the camera shooting of a preferred embodiment of the invention；
Fig. 2 be a preferred embodiment of the invention interception area-of-interest after binaryzation and after carrying out morphological operation
Image；
Fig. 3 is the connected domain for the single prawn of a preferred embodiment of the invention screened；
Fig. 4 is the polygon approach result of a preferred embodiment of the invention；
Fig. 5 is the polygon debranching enzyme result of a preferred embodiment of the invention；
Fig. 6 is the long side and shrimp head shrimp tail separation of the minimum circumscribed rectangle of a preferred embodiment of the invention；
Fig. 7 is the profile obtained after the shrimp lineback of a preferred embodiment of the invention expands；
Fig. 8 be a preferred embodiment of the invention two kinds of size expansions after obtained skeleton line；
Fig. 9 is the shrimp uropodium turning point in the polygon vertex of a preferred embodiment of the invention；
Figure 10 is the search sucker suction point PX of a preferred embodiment of the invention1Path；
Figure 11 is a preferred embodiment final effect figure of the invention.
Wherein, 11- shrimp tail separation, 12- shrimp head separation, 13- shrimp uropodium turning point, 14- sucker suction point PX1, 15-
Sucker suction point PX2, the long side of 21- minimum circumscribed rectangle, the contour line after the expansion of 22- shrimp lineback, the bone that 23- is carried on the back closer to shrimp
Stringing, skeleton line of the 24- closer to shrimp abdomen, 25- search sucker suction point PX1Path.
Specific embodiment
The preferred embodiment of the present invention is introduced below with reference to Figure of description, keeps its technology contents more clear and convenient for reason
Solution.The present invention can be emerged from by many various forms of embodiments, and protection scope of the present invention is not limited only to text
In the embodiment mentioned.
In the accompanying drawings, the identical component of structure is indicated with same numbers label, everywhere the similar component of structure or function with
Like numeral label indicates.The size and thickness of each component shown in the drawings are to be arbitrarily shown, and there is no limit by the present invention
The size and thickness of each component.Apparent in order to make to illustrate, some places suitably exaggerate the thickness of component in attached drawing.
The present embodiment is directed to be drawn the prawn of stacking at random and is placed in uniform location using the Double-sucker of constant spacing
Aquatic products processing automatic assembly line, is first turned on robot and camera, is acquired by industrial personal computer to camera image, and to machine
Device people carry out hand and eye calibrating, obtain image coordinate system to robot coordinate system transformational relation and scaling.Then by upper
Position machine regularly sends hard trigger signal to industrial personal computer and camera, and the identification positioning for being embedded in the method for the present invention is opened on industrial personal computer
Software.Local parameter file is loaded automatically after software starting, is clicked " starting to acquire " key and is come into effect the method for the present invention.Acquisition
Image it is as shown in Figure 1.Implementation steps are as follows:
Step 1, software wait camera to send image, receive and intercept area-of-interest after color image, and to image into
Row binaryzation, then corresponding morphological operation is done, the binary image of shrimp tail is obtained, as shown in Figure 2.
Step 2 screens the area of each connected domain and position, and each area is touched side within the specified range and not
Connected domain as complete single prawn, as shown in Figure 3.
Step 3 carries out polygon approach to each connected domain chosen, as shown in figure 4, by the polygon farthest away from mass center
Vertex is as shrimp caudal apex.
Step 4 traverses the vertex of polygon, and removal meets the vertex of branch's feature, repeats traversal until not having
Vertex meets branch's feature, as a result as shown in Figure 5.
Step 5 carries out minimum circumscribed rectangle fitting to the polygon of debranching enzyme, by the length and width of minimum circumscribed rectangle, deflection
The characteristic value of angle and centre coordinate as this shrimp, is stored in dynamic container.By the length and width of minimum circumscribed rectangle, deflection angle and
Feature value vector of the centre coordinate as this shrimp, all feature value vectors that will be stored in this feature value vector and dynamic container
It is compared, appears in camera fields of view and pass through during showing the shrimp before if having similar feature value vector
Calculating is crossed, therefore skips over all subsequent processings, otherwise it is assumed that the shrimp is to appear in camera fields of view for the first time, by feature value vector
It is stored in dynamic container and carries out subsequent processing.
Step 6, as shown in fig. 6, finding out the two of polygon away from the distance on minimum circumscribed rectangle vertex according to polygon vertex
A separation, shrimp tail separation 11 and shrimp head separation 12, are divided into two point sets for polygon vertex, according to two point sets away from most
Two point sets are denoted as back point set and abdomen point set by the average distance of the long side 21 of small boundary rectangle respectively.
Step 7 finds satisfactory shrimp uropodium turning point 13 as shown in figure 9, concentrating in abdomen point.
Step 8, the contour line 22 as shown in fig. 7, shrimp lineback is expanded according to certain size, after obtaining the expansion of shrimp lineback.
Skeleton line of part of the contouring in polygon encirclement as shrimp, then same operation is carried out with another size and obtains another bone
Stringing, the skeleton line 23 carried on the back closer to shrimp being illustrated in figure 8 and closer to the skeleton line 24 of shrimp abdomen.
Step 9, note PE1With at a distance from PE be L1, with PE1On the basis of, in SWOn away from PE1Nearest point is starting point, along
It is γ L that the path length apart from starting point is searched in the direction of shrimp head1Point as sucker suction point PX1, then with PX1On the basis of, it is leaning on
Suction point PX is searched on the skeleton line of nearly shrimp back2, it is as shown in Figure 10 search sucker suction point PX1Path 25.As shown in figure 11
The final process result of picture, sucker suction point PX1For point 14, sucker suction point PX2For point 15.
The preferred embodiment of the present invention has been described in detail above.It should be appreciated that the ordinary skill of this field is without wound
The property made labour, which according to the present invention can conceive, makes many modifications and variations.Therefore, all technician in the art
Pass through the available technology of logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Scheme, all should be within the scope of protection determined by the claims.
Claims (10)
1. it is a kind of search prawn most preferably draws position and identification uropodium feature method, which is characterized in that the method includes with
Lower step:
The color image of shrimp tail is intercepted area-of-interest and carries out binaryzation, then does corresponding morphological operation by step 1, is obtained
To the binary image of shrimp tail；
Step 2 calculates each connected region area to the binary image of step 1 shrimp tail, filters out area in a certain range
The satisfactory shrimp of camber is screened by the length-width ratio of minimum circumscribed rectangle in region；
Step 3 carries out polygon approach to the edge of each connected region of step 2, calculates caudal apex PE；
Step 4 carries out debranching enzyme operation to step 3 polygon, obtains debranching enzyme polygon；
Step 5, the minimum circumscribed rectangle for calculating step 4 debranching enzyme polygon, calculate the feature value vector of this shrimp, judge whether
Carry out subsequent processing；
Step 6, the shrimp for needing to carry out subsequent processing to step 5 determine the point set of shrimp abdomen and shrimp back according to minimum circumscribed rectangle；
Step 7, the turning point PE that shrimp uropodium is determined in the shrimp antinode of step 6 point set1；
Step 8, the skeleton line S closer to shrimp abdomen that shrimp is isolated in the shrimp antapex of step 6 point setHWith the bone carried on the back closer to shrimp
Stringing SW；
Step 9, the best absorption position for searching sucker.
2. searching the method that prawn most preferably draws position and identifies uropodium feature as described in claim 1, which is characterized in that step
Caudal apex PE in rapid 3 is point farthest away from polygon mass center in polygon vertex.
3. searching the method that prawn most preferably draws position and identifies uropodium feature as described in claim 1, which is characterized in that step
Debranching enzyme operation in rapid 4 is traversal polygon vertex, is deleted the vertex for meeting branching characteristic, is met deletion described
The new polygon formed behind the vertex of branching characteristic repeats this step until all vertex do not meet the branching characteristic.
4. searching the method that prawn most preferably draws position and identifies uropodium feature as claimed in claim 3, which is characterized in that institute
Stating branching characteristic is interior angle and the adjacent both sides d when some vertex1,d2Meet one of the following conditions:
(1) α < αpoly0；
(2) α < αpoly1And max (d1,d2) < dpoly1；
(3) α < αpoly2And (max (d1,d2) < dpoly2Or min (d1,d2) < dpoly3)；
Wherein, αpoly0,αpoly1,αpoly2,dpoly1,dpoly2,dpoly3It is preset threshold value.
5. searching the method that prawn most preferably draws position and identifies uropodium feature as described in claim 1, which is characterized in that step
Feature value vector in rapid 5 is length and width, deflection angle and the centre coordinate of the minimum circumscribed rectangle.
6. searching the method that prawn most preferably draws position and identifies uropodium feature as described in claim 1, which is characterized in that step
The method that subsequent processing is judged whether in rapid 5 is all feature value vectors that will be stored in feature value vector and dynamic container
It is compared, appears in camera fields of view and pass through during showing the shrimp before if having similar feature value vector
Calculating is crossed, therefore skips over all subsequent processings, otherwise it is assumed that the shrimp is to appear in camera fields of view for the first time, by feature value vector
It is stored in dynamic container and carries out subsequent processing.
7. searching the method that prawn most preferably draws position and identifies uropodium feature as described in claim 1, which is characterized in that step
The determination method of the point set of rapid 6 Prawn abdomen and shrimp back is: on the polygon that step 4 obtains, remembering in minimum circumscribed rectangle away from tail
Portion vertex PE nearest vertex is P1, corresponding long side vertex is P2；With in PE and polygon vertex away from P2Nearest point is minute
Polygon is divided into two parts by boundary, and calculates two point sets to the average distance of long side, and the small point set of average distance is determined
For shrimp abdomen, the big point set of average distance is determined as that shrimp carries on the back.
8. searching the method that prawn most preferably draws position and identifies uropodium feature as described in claim 1, which is characterized in that step
The determination method of the turning point of rapid 7 Prawn uropodium is: the top for meeting the following conditions is searched on the shrimp antinode collection that step 6 obtains
Point is determined as the turning point PE of shrimp uropodium1:
(1) 190 ° of interior angle >；
(2) meet away from PE length d
Wherein, A is the area of the polygon, dεmin,dεmax,AstdIt is preset threshold value.
9. searching the method that prawn most preferably draws position and identifies uropodium feature as described in claim 1, which is characterized in that step
The skeleton line separation method of shrimp in rapid 8 is: expansive working is carried out by certain size, obtain in the edge line of connected domain
Skeleton line of the part as shrimp in polygon encirclement, obtains the skeleton of two different locations by small one and large one two kinds of sizes
Line remembers that the skeleton line closer to shrimp abdomen is SH, the skeleton line carried on the back closer to shrimp is SW。
10. searching the method that prawn most preferably draws position and identifies uropodium feature as described in claim 1, which is characterized in that
Method for searching in step 9 is: the turning point PE that note step 7 obtains1It is shrimp at a distance from the shrimp caudal apex PE obtained with step 3
Uropodium length L1, in the S that step 8 obtainsWOn away from PE1Nearest point is starting point, is searched along the direction of shrimp head apart from starting point
Path length is γ L1Point as sucker suction point PX1, the fixed range of two interambulacrums of note is L2, in the S that step 8 obtainsHOn
It searches away from PX1Linear distance is L2Point as sucker suction point PX2。
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 true CN109829465A (en) | 2019-05-31 |
| CN109829465B 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) |
Cited By (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 |
| CN111650196A (en) * | 2020-04-13 | 2020-09-11 | 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 |
| 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 |
| CN112173639A (en) * | 2020-10-15 | 2021-01-05 | 佛山松瀚智能设备有限公司 | Feeding and conveying method of automatic shrimp peeling machine |
| CN113642847A (en) * | 2021-07-15 | 2021-11-12 | 中国农业大学 | Prawn quality estimation method and device |
| CN115009575A (en) * | 2022-07-22 | 2022-09-06 | 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 |
|---|
| 张伟: "基于机器视觉技术的缺损对虾在线识别与剔除系统研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 罗艳: "基于机器视觉技术的对虾规格检测方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (10)
| 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 |
| CN111650196A (en) * | 2020-04-13 | 2020-09-11 | 浙江大学 | Sick shrimp red body disease detection device based on machine vision technique |
| 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 |
| 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 |
| CN112173639A (en) * | 2020-10-15 | 2021-01-05 | 佛山松瀚智能设备有限公司 | Feeding and conveying method of automatic shrimp peeling machine |
| 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 |
| CN113642847A (en) * | 2021-07-15 | 2021-11-12 | 中国农业大学 | Prawn quality estimation method and device |
| CN113642847B (en) * | 2021-07-15 | 2023-08-04 | 中国农业大学 | Method and device for estimating prawn quality |
| CN115009575A (en) * | 2022-07-22 | 2022-09-06 | 中国农业大学 | Grading tray arranging system and method for semi-finished shrimps |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109829465B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829465A (en) | A method of it searching prawn and most preferably draws position and identification uropodium feature | |
| CN106952258B (en) | A kind of bottle mouth defect detection method based on gradient orientation histogram | |
| CN103984928B (en) | Finger gesture recognition methods based on depth image | |
| CN107451999B (en) | Foreign matter detection method and device based on image recognition | |
| EP3243166B1 (en) | Structural masking for progressive health monitoring | |
| Oprisescu et al. | Automatic static hand gesture recognition using tof cameras | |
| CN108304819B (en) | Gesture recognition system and method, and storage medium | |
| CN110543837A (en) | visible light airport airplane detection method based on potential target point | |
| US10043105B2 (en) | Method and system to characterize video background changes as abandoned or removed objects | |
| CN106326860A (en) | Gesture recognition method based on vision | |
| CN110763700A (en) | Method and equipment for detecting defects of semiconductor component | |
| CN109255792B (en) | Video image segmentation method and device, terminal equipment and storage medium | |
| CN111932490B (en) | Visual system grabbing information extraction method for industrial robot | |
| CN107388991A (en) | A kind of more fillet axial workpiece radius of corner measuring methods in end face | |
| CN106900601B (en) | Method for quickly and accurately identifying shrimp head points and shrimp tail points of prawn image | |
| Chelouati et al. | Lobster detection using an Embedded 2D Vision System with a FANUC industrual robot | |
| Han et al. | Shape context based object recognition and tracking in structured underwater environment | |
| CN105528782B (en) | A kind of milk carton suction pipe whether there is or not detection method | |
| CN111415348A (en) | Method for extracting characteristics of bubbles in automobile brake pipeline | |
| Yang et al. | Method for building recognition from FLIR images | |
| JPH08315152A (en) | Image recognition device | |
| CN107833222B (en) | Nonmetal part surplus detection device and method | |
| Baird | Image Segmentation Technique for Locating Automotive Parts on Belt Conveyors. | |
| Nasreddine et al. | Shape-based fish recognition via shape space | |
| Kiratiratanapruk et al. | Segmentation algoritm for touching round grain image |
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 |