CN108564573A - Fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter - Google Patents
Fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter Download PDFInfo
- Publication number
- CN108564573A CN108564573A CN201810310744.1A CN201810310744A CN108564573A CN 108564573 A CN108564573 A CN 108564573A CN 201810310744 A CN201810310744 A CN 201810310744A CN 108564573 A CN108564573 A CN 108564573A
- Authority
- CN
- China
- Prior art keywords
- fish
- spanish mackerel
- segment
- image
- fish tail
- 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
-
- 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
- G06T7/12—Edge-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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Processing Of Meat And Fish (AREA)
Abstract
The invention discloses a kind of fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter, includes the following steps:A, sample collection;B, hardware system is set up;C, Image Acquisition and background segment;D, edge contour extracts;E, the detection of fish body size;F, the identification and removal of fish head fish tail;G, the fixed segment mathematical model again of Spanish mackerel is established.The present invention mainly uses machine vision technique quick obtaining fish body information, it establishes fish body characteristics parameter and removes the correlation model with segment technological parameter end to end, the Dynamic Programming with segment technique end to end is gone in realization, and based on this, develop high quality high accurancy and precision it is novel go end to end with segment mechanism, establish it is novel go end to end with segment all-in-one machine model machine, realize intelligent processing fresh-water fishes, improve working efficiency.
Description
Technical field
The present invention relates to a kind of fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter.
Background technology
It is 21 century, highly developed with computer technology, wait weight, surely heavy cutting technique to be widely used to meat products
Manufacture field.Khodabandehloo (1990) reports some certain types of chicken processing and packings, to reach scheduled, solid
Fixed weight.This system is selected using a series of logic steps and is grouped into corresponding pallet, the one of Ya Kebu (1996)
Show to estimate the volume of object with CCD camera and the image processing system of laser irradiation in part work report, then
The part of isometric (weight) is cut objects into a water jet cutting machine, this method uses homogeneous object, can be from can
The shape for being shown in Table face determines that volume, this method are only limitted to the object similar to top surface, not hollow part, and
And bottom surface is considered flat, due to equal weight, determines to be cut again given cutting gravimetric value and accuracy rating, and fish body belongs to not
Regular body, therefore incision principle is complicated, more demanding to relevant device technology, foreign countries have occurred based on the phase for waiting weight, fish
Close equipment, public demand cannot be met, therefore, establish a kind of quick, lossless and suitable freshwater fish fixed heavy Cut Stratagem and
System has become urgent problem to be solved.
Invention content
The object of the present invention is to provide a kind of fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter.The present invention
Technical solution used for the above purpose is:A kind of fish head fish tail image automatic identification side towards Spanish mackerel segment cutter
Method includes the following steps:
A, sample collection is chosen one group of length in the median size Spanish mackerel of 20-35cm, is gone dirty rear as test sample;
B, hardware system is set up, experiment porch is set up by industrial camera, camera bellows, LED bar graph light source and computer;
Sample is placed on viewing field of camera center, keeps central axis flat with visual field border by C, Image Acquisition and background segment
Row carries out pretreatment and binaryzation to Spanish mackerel image, is then removed shade to image, and removal background obtains Spanish mackerel and integrally makees
For region of interest;
D, edge contour extracts, and optimal detection criterion, single response criteria of oplimal Location criterion and edge is selected, to edge
It is made the assumption that with noise, then obtain the optimal filter of edge detection using mathematical method, i.e. it is high to be located at image for boundary point
The maximum point of gradient amplitude after this function is smooth finally detects the edge contour after background segment, edge contour is led to
Overscanning method obtains, that is, obtains edge contour coordinate;
E, the characteristics of image of fish body, including long axis, short axle and major and minor axis are extracted in the detection of fish body size on profile diagram
The ratio between, for the ratio of semi-minor axis length that kind correlation is larger, acquire the ratio of semi-minor axis length of Spanish mackerel 5.0 or so, major and minor axis it
Fish head than the fish products kind 5.0 or so accounts for overall fish length a quarter, and all samples Spanish mackerel is all in this, as decaptitating standard
Then, understand that worst error is 1.5cm by examining, using the theoretical foundation as fish head cut-off rule;
F, the identification and removal of fish head fish tail obtains fish jawbone contour line according to long axis length a quarter, realizes fish head
Feature recognition carries out width value screening, when generating minimum value, using this position coordinates as fish to sample second half section projected image
Body and fish tail line of demarcation position coordinates, and the length of fish tail is asked to be denoted as l0Data are provided for follow-up founding mathematical models;
G, the fixed segment mathematical model again of Spanish mackerel is established, Spanish mackerel is established using the relationship and the differential calculus of quality and volume and weighs surely
The mathematical model of segment.
In the step C, Image Acquisition mode has two kinds of single frames acquisition and continuous acquisition.
According to minimum width value in the step F, fish tail feature recognition is realized.
Assume that Spanish mackerel sample rate is ρ in the step G, total weight M, total volume V then have
M=ρ V (1)
Assuming that being the initial position (x=0) of fish at Spanish mackerel fish mouth, then the fish at the x of initial position is:
Wherein, A (x) is the sectional area of Spanish mackerel.
Assuming that the length of fish head and fish tail apart from initial position is respectively L1And L2, according to (2) formula it is found that removal fish head fish
Fish body after tail accumulates v:
ByAnd L2=L-L0And Spanish mackerel sample rate be ρ it is found that so remove fish head fish tail after fish body
Quality m is:
When the fixed heavy parameter of Spanish mackerel segment cutter is set as m0, then needing the hop count n cut to be:
Similarly, the hop count cut when the needs of Spanish mackerel segment cutter is n, then can acquire, to determine heavy amount be m0:
A kind of fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter of the present invention, mainly uses machine vision skill
Art quick obtaining fish body information establishes fish body characteristics parameter and removes the correlation model with segment technological parameter end to end,
The Dynamic Programming with segment technique end to end is gone in realization, and based on this, is developed the novel of high quality high accurancy and precision and gone end to end
With segment mechanism, establish it is novel go end to end with segment all-in-one machine model machine, realize intelligent processing fresh-water fishes, improve working efficiency.
Description of the drawings
Fig. 1 is a kind of Image Acquisition system of the fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter of the present invention
System.
Fig. 2 is a kind of Spanish mackerel imagery exploitation of the fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter of the present invention
Otsu methods obtain background segment figure.
Fig. 3 is a kind of Spanish mackerel imagery exploitation of the fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter of the present invention
Canny algorithms carry out edge-detected image.
Fig. 4 be a kind of Spanish mackerel of the fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter of the present invention four/
One fish length substitutes the Error Absolute Value figure of practical fish head length.
Fig. 5 is a kind of workflow of the Spanish mackerel of the fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter of the present invention
Cheng Tu.
Fig. 6 is that a kind of image of the fish body of the fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter of the present invention is special
Levy table.
Fig. 7 is a kind of fish head length and four of the fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter of the present invention
The difference absolute value table of/mono- length of fish body.
Specific implementation mode
As shown in Figures 1 to 7, the fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter, specific implementation step
It is as follows:A, sample collection:Investigation situation is processed according to Dalian the aquatic products processing enterprises Spanish mackerel segment, is chosen one group (10)
Median size Spanish mackerel (go dirty rear) of the length in 20-35cm is used as test sample;B, experiment hardware system is set up:Experiment porch
It is mainly made of industrial camera 1, camera bellows 4, LED bar graph light source 2, objective table 5, computer 6, such as Fig. 1, C, Image Acquisition and the back of the body
Scape is divided:Sample is placed on viewing field of camera center, and central axis is parallel with visual field border;There is the impurity such as the moisture back of the body in Spanish mackerel image
Scape, and the image that hardware system obtains is coloured image, needs to carry out pretreatment and binaryzation to original image first, then to image
It is removed shade, removal background obtains Spanish mackerel and is integrally used as region of interest.Such as Fig. 2 in fact, D, edge contour extraction:It utilizes
Canny algorithms carry out edge detection, and Canny algorithms are the canonical algorithms of edge detection, are in optimal detection criterion, oplimal Location
On the basis of criterion and single response criteria at edge, edge and noise are made the assumption that, then obtaining edge using mathematical method examines
The optimal filter of survey, i.e. boundary point are located at the maximum point of gradient amplitude of the image by Gaussian function after smooth, then utilize
Scanning method obtains profile coordinate.Its edge detection results such as Fig. 3, the detection of E, fish body size:The size detection of fish body be exactly
The characteristics of image of fish body is extracted on profile diagram, includes mainly long axis, short axle and ratio of semi-minor axis length etc..Long axis reflects fish body
Body is long, and specific computational algorithm is as follows:Using scanning method first from left to right into rank scanning when, obtained first value is 0
Point is denoted as a1, then turn left from the right side into rank scanning, the point that first obtained value is 0 is denoted as a2, last a2-a1As long axis;
The body that short axle reflects fish body is wide, and specific computational algorithm is as follows:Using scanning method first from left to right into rank scanning when, into
In rank scanning mainly from top to bottom, the point that first obtained value is 0 is denoted as b1, then scanned from the bottom up in the row,
The point that first obtained value is 0 is denoted as b2, last b2-b1As short axle, wherein mainly being grown for kind correlation is larger
The ratio between short axle, acquires the ratio of semi-minor axis length of Spanish mackerel 5.0 or so, and as a result such as Fig. 6, and ratio of semi-minor axis length is 5.0 or so
The fish head of fish products kind accounts for overall fish length a quarter, and by all Spanish mackerel samples 3 in this, as decaptitating criterion, can by inspection
Know that worst error is 1.5cm, as a result such as Fig. 7 and Fig. 4, therefore can be as the theoretical foundation of fish head cut-off rule, F, fish head fish
The identification and removal of tail:Fish jawbone contour line is obtained according to long axis length a quarter, to realize fish head feature recognition;To sample
This second half section projected image carries out width value screening, when generating minimum value, demarcates this position coordinates as fish body and fish tail
Line position coordinate;The fish head fish tail position coordinates of acquisition are utilized into ant group algorithm optimization fish head fish tail cutting path, are reduced
Feed path improves cutting efficiency and obtains meat rate, in fact such as Fig. 5, G, establishes the fixed segment mathematical model again of Spanish mackerel:Assuming that
Spanish mackerel sample rate is ρ, and total weight M, total volume V then have
M=ρ V (1)
Assuming that being the initial position (x=0) of fish at Spanish mackerel fish mouth, then the fish at the x of initial position is:
Wherein, A (x) is the sectional area of Spanish mackerel;
Assuming that the length of fish head and fish tail apart from initial position is respectively L1And L2, according to (2) formula it is found that removal fish head fish
Fish body volume v after tail is:
ByWithAnd Spanish mackerel sample rate be ρ it is found that so remove fish head fish tail after fish body
Quality m is:
When the fixed heavy parameter of Spanish mackerel segment cutter is set as m0, then needing the hop count n cut to be:
Similarly, the hop count cut when the needs of Spanish mackerel segment cutter is n, then can acquire, to determine heavy amount be m0:
To sum up, the present invention uses machine vision technique quick obtaining fish body information, establishes fish body characteristics parameter
The Dynamic Programming with segment technique end to end is gone with the correlation model with segment technological parameter end to end, realization is removed, and based on this,
Develop high quality high accurancy and precision it is novel go end to end with segment mechanism, establish it is novel go end to end with segment all-in-one machine model machine, it is real
Existing intelligent processing fresh-water fishes, improve working efficiency.
Claims (4)
1. a kind of fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter, which is characterized in that include the following steps:
A, sample collection is chosen one group of length in the median size Spanish mackerel of 20-35cm, is gone dirty rear as test sample;
B, hardware system is set up, experiment porch is set up by industrial camera, camera bellows, LED bar graph light source and computer;
Sample is placed on viewing field of camera center, keeps central axis parallel with visual field border by C, Image Acquisition and background segment, right
Spanish mackerel image carries out pretreatment and binaryzation, is then removed shade to image, and removal background obtains Spanish mackerel integrally as sense
Region of interest;
D, edge contour extracts, and selects optimal detection criterion, single response criteria of oplimal Location criterion and edge, to edge and makes an uproar
Sound makes the assumption that, then obtains the optimal filter of edge detection using mathematical method, i.e. boundary point is located at image by Gaussian function
The maximum point of gradient amplitude after number is smooth, finally detects the edge contour after background segment, by edge contour by sweeping
Method acquisition is retouched, that is, obtains edge contour coordinate;
E, the detection of fish body size, on profile diagram extract fish body characteristics of image, including long axis, short axle and major and minor axis it
Than for the ratio of semi-minor axis length that kind correlation is larger, acquiring the ratio of semi-minor axis length of Spanish mackerel 5.0 or so, ratio of semi-minor axis length
Account for overall fish length a quarter in the fish head of 5.0 or so fish products kind, all samples Spanish mackerel all in this, as decaptitating criterion,
Understand that worst error is 1.5cm by examining, using the theoretical foundation as fish head cut-off rule;
F, the identification and removal of fish head fish tail obtains fish jawbone contour line according to long axis length a quarter, realizes fish head feature
Identification carries out width value screening to sample second half section projected image, when generating minimum value, using this position coordinates as fish body and
Fish tail line of demarcation position coordinates, and the length of fish tail is asked to be denoted as l0Data are provided for follow-up founding mathematical models;
G, the fixed segment mathematical model again of Spanish mackerel is established, Spanish mackerel is established using the relationship and the differential calculus of quality and volume and determines segment again
Mathematical model.
2. a kind of fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter according to claim 1, feature
It is:In the step C, Image Acquisition mode has two kinds of single frames acquisition and continuous acquisition.
3. a kind of fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter according to claim 1, feature
It is:According to minimum width value in the step F, fish tail feature recognition is realized.
4. a kind of fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter according to claim 1, feature
It is:Assume that Spanish mackerel sample rate is ρ in the step G, total weight M, total volume V then have
M=ρ V (1)
Assuming that being the initial position (x=0) of fish at Spanish mackerel fish mouth, then the fish at the x of initial position is:
Wherein, A (x) is the sectional area of Spanish mackerel.
Assuming that the length of fish head and fish tail apart from initial position is respectively L1And L2, according to (2) formula it is found that after removal fish head fish tail
Fish body product v be:
ByAnd L2=L-L0And Spanish mackerel sample rate be ρ it is found that so remove fish head fish tail after quality of fishes m
For:
When the fixed heavy parameter of Spanish mackerel segment cutter is set as m0, then needing the hop count n cut to be:
Similarly, the hop count cut when the needs of Spanish mackerel segment cutter is n, then can acquire, to determine heavy amount be m0:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810310744.1A CN108564573B (en) | 2018-03-30 | 2018-03-30 | Automatic fish head and tail image identification method for spanish mackerel cutting machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810310744.1A CN108564573B (en) | 2018-03-30 | 2018-03-30 | Automatic fish head and tail image identification method for spanish mackerel cutting machine |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108564573A true CN108564573A (en) | 2018-09-21 |
CN108564573B CN108564573B (en) | 2021-10-08 |
Family
ID=63534395
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810310744.1A Active CN108564573B (en) | 2018-03-30 | 2018-03-30 | Automatic fish head and tail image identification method for spanish mackerel cutting machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108564573B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109275609A (en) * | 2018-11-14 | 2019-01-29 | 常州大学 | Common fresh-water fishes type automatic identifying method based on image procossing |
CN111696150A (en) * | 2020-05-19 | 2020-09-22 | 杭州飞锐科技有限公司 | Method for measuring phenotypic data of channel catfish |
CN111738279A (en) * | 2020-06-24 | 2020-10-02 | 西藏自治区农牧科学院水产科学研究所 | Non-contact type automatic acquisition device and method for fish morphological phenotype |
CN112017201A (en) * | 2020-08-07 | 2020-12-01 | 湖北省农业科学院农产品加工与核农技术研究所 | Method for judging head and tail postures of fish body in processing and conveying |
CN112614090A (en) * | 2020-12-09 | 2021-04-06 | 中国水产科学研究院渔业机械仪器研究所 | Method and system for identifying fish abdominal cavity structural features |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5957364A (en) * | 1982-09-25 | 1984-04-02 | Fujitsu Ltd | Detecting circuit of fish head cutting position |
CN103400147A (en) * | 2013-07-25 | 2013-11-20 | 中国农业大学 | Image processing-based target fish recognition method and system |
CN203913197U (en) * | 2014-05-16 | 2014-11-05 | 浙江海洋学院 | A kind of multiple-cutting-edge flesh of fish food slicer |
CN206949395U (en) * | 2017-02-15 | 2018-02-02 | 刘良忠 | A kind of fish head fish tail cutter device of roller-brush type push fish body displacement |
-
2018
- 2018-03-30 CN CN201810310744.1A patent/CN108564573B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5957364A (en) * | 1982-09-25 | 1984-04-02 | Fujitsu Ltd | Detecting circuit of fish head cutting position |
CN103400147A (en) * | 2013-07-25 | 2013-11-20 | 中国农业大学 | Image processing-based target fish recognition method and system |
CN203913197U (en) * | 2014-05-16 | 2014-11-05 | 浙江海洋学院 | A kind of multiple-cutting-edge flesh of fish food slicer |
CN206949395U (en) * | 2017-02-15 | 2018-02-02 | 刘良忠 | A kind of fish head fish tail cutter device of roller-brush type push fish body displacement |
Non-Patent Citations (7)
Title |
---|
FERNANDO MARTÍN-RODRÍGUEZ 等: "Automatic Turbot Fish Cutting Using Machine Vision", 《MARTECH》 * |
MAJID DOWLATI 等: "Application of machine-vision techniques to fish-quality assessment", 《TRENDS IN ANALYTICAL CHEMISTRY》 * |
ZHI-MING QIAN 等: "Automatically Detect and Track Multiple Fish Swimming in Shallow Water with Frequent Occlusion", 《PLOS ONE》 * |
张帆: "淡水鱼去头方法及装置设计试验研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
张志强 等: "基于机器视觉技术的淡水鱼质量分级", 《农业工程学报》 * |
胡灿: "基于ELM算法的鲜活淡水鱼图像自动归类研究", 《中国优秀硕士学位论文全文数据库 农业科技辑》 * |
陈庆余 等: "典型海产小杂鱼机械去头方法研究", 《渔业现代化》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109275609A (en) * | 2018-11-14 | 2019-01-29 | 常州大学 | Common fresh-water fishes type automatic identifying method based on image procossing |
CN111696150A (en) * | 2020-05-19 | 2020-09-22 | 杭州飞锐科技有限公司 | Method for measuring phenotypic data of channel catfish |
CN111738279A (en) * | 2020-06-24 | 2020-10-02 | 西藏自治区农牧科学院水产科学研究所 | Non-contact type automatic acquisition device and method for fish morphological phenotype |
CN111738279B (en) * | 2020-06-24 | 2022-01-04 | 西藏自治区农牧科学院水产科学研究所 | Non-contact type automatic acquisition device and method for fish morphological phenotype |
CN112017201A (en) * | 2020-08-07 | 2020-12-01 | 湖北省农业科学院农产品加工与核农技术研究所 | Method for judging head and tail postures of fish body in processing and conveying |
CN112017201B (en) * | 2020-08-07 | 2024-03-19 | 湖北省农业科学院农产品加工与核农技术研究所 | Fish body head and tail gesture judging method in processing and conveying |
CN112614090A (en) * | 2020-12-09 | 2021-04-06 | 中国水产科学研究院渔业机械仪器研究所 | Method and system for identifying fish abdominal cavity structural features |
CN112614090B (en) * | 2020-12-09 | 2021-12-31 | 中国水产科学研究院渔业机械仪器研究所 | Method and system for identifying fish abdominal cavity structural features |
Also Published As
Publication number | Publication date |
---|---|
CN108564573B (en) | 2021-10-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108564573A (en) | Fish head fish tail automatic distinguishing method for image towards Spanish mackerel segment cutter | |
Zion et al. | Real-time underwater sorting of edible fish species | |
CN102261892B (en) | Rapid width measurement system for tobacco shreds | |
CN108960011B (en) | Partially-shielded citrus fruit image identification method | |
CN107941808B (en) | 3D printing forming quality detection system and method based on machine vision | |
CN108764154B (en) | Water surface garbage identification method based on multi-feature machine learning | |
CN111583193B (en) | Pistachio nut framework extraction device based on geometric contour template matching and algorithm thereof | |
CN102110294B (en) | Method and system for processing image of diseased fish body | |
KR101743270B1 (en) | The method for separating and recognizing individual plankton using deep learning in a clumped or dispersed microscopic plankton image | |
CN109275609A (en) | Common fresh-water fishes type automatic identifying method based on image procossing | |
US9691144B2 (en) | System and method for counting zooplankton | |
CN109255757A (en) | A kind of machine vision places grape cluster carpopodium region segmentation method naturally | |
CN110687121B (en) | Intelligent online detection and automatic grading method and system for ceramic tiles | |
CN104915943B (en) | Method and apparatus for determining main parallax value in disparity map | |
US11756206B2 (en) | Recognition method and device for analyzing a starvation extent of a whiteleg shrimp based on underwater imaging | |
US10426143B2 (en) | Systems and methods for larval fish enumeration and growth monitoring | |
CN106296644A (en) | Method is analyzed in a kind of corn kernel species test based on image procossing | |
CN105678749A (en) | Fresh fish direction discrimination method based on visual sense | |
CN111784649A (en) | Fishbone phenotype information automatic detection system and method without fishbone damage | |
CN110176020A (en) | A kind of bird's nest impurity method for sorting merging 2D and 3D rendering | |
CN113655002A (en) | Recycled aggregate quality detection system with mortar on surface based on hyperspectral technology | |
CN113869252B (en) | Crayfish head-tail separation control method and crayfish head-tail separation control system based on deep learning | |
CN113180640B (en) | Size measuring method and system for livestock breeding | |
Culverhouse et al. | An instrument for rapid mesozooplankton monitoring at ocean basin scale | |
CN112132884A (en) | Sea cucumber length measuring method and system based on parallel laser and semantic segmentation |
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 |