CN108133184A - It is a kind of based on the fish of fractal theory and BP algorithm identification and vaccine injection method - Google Patents
It is a kind of based on the fish of fractal theory and BP algorithm identification and vaccine injection method Download PDFInfo
- Publication number
- CN108133184A CN108133184A CN201711383774.7A CN201711383774A CN108133184A CN 108133184 A CN108133184 A CN 108133184A CN 201711383774 A CN201711383774 A CN 201711383774A CN 108133184 A CN108133184 A CN 108133184A
- Authority
- CN
- China
- Prior art keywords
- fish
- image
- algorithm
- fractal theory
- vaccine injection
- 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
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 139
- 238000002347 injection Methods 0.000 title claims abstract description 49
- 239000007924 injection Substances 0.000 title claims abstract description 49
- 229960005486 vaccine Drugs 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013528 artificial neural network Methods 0.000 claims abstract description 9
- 238000003709 image segmentation Methods 0.000 claims abstract description 4
- 238000000605 extraction Methods 0.000 claims abstract description 3
- 230000011218 segmentation Effects 0.000 claims abstract description 3
- 238000010586 diagram Methods 0.000 claims description 17
- 210000001015 abdomen Anatomy 0.000 claims description 14
- 238000001228 spectrum Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000006073 displacement reaction Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 238000005096 rolling process Methods 0.000 claims description 2
- 238000010304 firing Methods 0.000 claims 1
- 238000012512 characterization method Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010052428 Wound Diseases 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 235000013547 stew Nutrition 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/10—Culture of aquatic animals of fish
- A01K61/13—Prevention or treatment of fish diseases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Environmental Sciences (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Zoology (AREA)
- Marine Sciences & Fisheries (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The present invention provide it is a kind of based on the fish of fractal theory and BP algorithm identification and vaccine injection method, including:Obtain the coloured image of fish;The coloured image is pre-processed, image segmentation obtains target image;With the characteristic value of each target image after the extraction segmentation of fractal theory algorithm, multi-feature vector group is obtained;The multi-feature vector group is trained with BP neural network algorithm, the image for meeting the combination requirement of fish privileged site is identified in the target image;Satisfactory fish carries out vaccine injection.The present invention uses fractal theory algorithm to provide completely new method for fish body part characterization, and the characteristic value of 8 characterization fishes can more reflect the body part information of fish convenient for distinguishing.Fractal theory and BP algorithm combine the image for effectively identifying fish head and ridge combination requirement, provide a good recognition methods for fish vaccine injection, realize robotic identification, injection process also using automatic injection, mitigates artificial burden.
Description
Technical field
The present invention relates to the identification of fish body part and vaccine injection fields, and in particular to one kind is calculated based on fractal theory and BP
The fish identification of method and vaccine injection method.
Background technology
Fish vaccine injection is one of most important work in fry cultivation project, and the purpose of vaccine injection is to prevent
Fish generate disease, ensure fish healthy growth and obtain output increased, it is desirable to obtain health, yield it is big, meat is good, cultivation
Fish need to carry out the injection of vaccine, and otherwise breed in stew industry is certain to by very big economic loss.Aquatic products vaccine connects at this stage
Kind mainly have three ways, such as injection, it is oral, impregnate, wherein, vaccinate with dosage is few, antibody titer is high, it is immune continue when
Between it is long the features such as.
How automatic injection identifies fish head, fish tail, fish belly and dorsal fin in the process, is the pass for determining fish vaccine injection success or failure
Key.
Most of to fish vaccine injection at present to use manual injection, artificial amount is big, and labor intensity is high, needs very high people
Work cost.Machine vision technique possesses the features such as contactless, high-precision, improves production flexibility and the degree of automation, extensively
It is general to be used for each field of each subject.So far, machine vision technique is used to be detected different fish by some scholars
And Study of recognition, but be identified both for different fish, not yet see in being injected to related fish vaccine fish head,
The relevant report of fish tail, fish belly and dorsal fin detection Study of recognition.
Divided shape (Fractal), the theory that upper world's nineties is put forward by Mang Deboluo wounds is had and tieed up with non-integer
The morphological feature of form filling space.Generally defined as " a coarse or scrappy geometry is segmented into several each portions
Point, and each section all (at least approximately) is shape after whole reduce ", i.e. the property with self similarity.According to not jljl
The form of body extracts each section relevant parameter feature, the characteristic value most basic as identification.It can facilitate the spy of description image
Sign, can be applied to each occasion.
BP algorithm thought is to read network parameter and training sample parameter, and after normalized, retraining is concentrated to each
A sample is calculated, and is reached required precision and is then exited training, otherwise continues to train, finally obtain a result.Usual BP nerve nets
Network is mainly used for, in pattern-recognition, classification and data compression.
Invention content
The technical issues of to solve the identification of fish body part and vaccine injection, the purpose of the present invention is to provide one kind to be based on
The fish of fractal theory and BP algorithm identifies and vaccine injection method.
The present invention is achieved by the following technical solutions:
It is a kind of based on the fish of fractal theory and BP algorithm identification and vaccine injection method, include the following steps:
S1, the coloured image for obtaining fish;
S2, the coloured image is pre-processed, image segmentation acquisition target image;
S3, the characteristic value with each target image after the extraction segmentation of fractal theory algorithm, obtain multi-feature vector group;
S4, the multi-feature vector group is trained with BP neural network algorithm, is identified in the target image
Go out to meet the image of fish privileged site combination requirement;
S5, undesirable fish then discharge, and are put into pool, and satisfactory fish then by distance measuring sensor, measures mesh
The length of fish is marked, calculates injection position, carries out vaccine injection.
Further, in step S1, camera is mounted on the surface of the fish, and L × W pictures are intercepted by the camera
The fish diagram of element obtains the coloured image of fish as m.
Further, in step S2, the pretreatment is included to image filtering and smoothing processing, and described image is divided from figure
Be split acquisition target image as middle part is divided into two, the target image there are four types of part combination image, described four kinds
Part combination is respectively fish tail and abdomen, fish tail and ridge, fish head and abdomen, fish head and ridge.
Further, in step S3, the characteristic value has 8, respectively
Singular value minimum value amin, fish diagram is represented as maximum probability estimates region property;
Singular value maximum value amax, fish diagram is represented as medium and small probability measure region property;
Spectrum width amax-amin, reflect inhomogeneities degree of the entire fish diagram as probability distribution on fractal structure;
Multifractal spectra maximum value f (amax), fish diagram is represented as small probability lower structure complexity and degree of irregularity;
Multifractal spectra minimum value f (amin), fish diagram is represented as complexity and degree of irregularity under maximum probability;
Spectral difference f (amax)-f(amin), reflect that fish diagram image surface is maximum, number ratio at minimum;
β is image slices vegetarian refreshments number;
γ is the fish head or fish tail width value of distance measuring sensor actual measurement.
Further, in step S4, the fish privileged site combination is specially fish head and ridge combination.
Further, in step S4, the model structure of the BP neural network includes input layer, hidden layer, output layer
And desired output, the input number of plies NinFor the number 8 of the characteristic value, the output number of plies NoutFor the fish privileged site
Number 2, imply the number of plies be Nhidden, formula Nhidden=2 × (Nout×Nin)1/2, implicit number of plies N is calculatedhiddenIt is 8;
The desired output, if fish head output is 1, ridge output is 1, and the output of remaining position is 0;
The desired output difference of the target fish tail and abdomen, fish tail and ridge, fish head and abdomen, fish head and ridge
For 0 and 0,0 and 1,1 and 0,1 and 1;
Training is iterated by the BP neural network so that network output overall error is less than 0.1 everywhere convergent, training knot
Beam;Identify the image of the fish head and ridge combination, the corresponding desired output is 1 and 1, is met the requirements, and others are all
It is undesirable.
Further, in step S5, during the vaccine injection, the direction of fish is fish head preceding, and dorsal fin is upward, Yi Zhongzhi
Vertical state, injection angles are to put position partially in dorsal fin.
Further, in step S5, by the satisfactory fish by the rolling axial advancement of certain speed v, institute is triggered
The time for stating distance measuring sensor is t, obtains length s=v × t of fish, and the displacement distance for calculating given injecting motor is injected,
Change before and after carrying out on the position of first time movement is injected through next time to adjust or return to by injecting motor by reset command
Initial position is injected, and controls the position of vaccine injection, for the fish of different length, accurately controls the position having an injection.
Further, in step S5, the distance measuring sensor is laser sensor.
Compared with prior art, the present invention has the advantages that:
The present invention uses fractal theory algorithm to provide completely new method, the spy of 8 characterization fishes for fish body part characterization
Value indicative can more reflect the body part information of fish convenient for distinguishing.
Fractal theory and BP algorithm combine the image for effectively identifying fish head and ridge combination requirement, are carried for fish vaccine injection
For a good recognition methods, robotic identification is realized, injection process also using automatic injection, mitigates artificial burden.
Description of the drawings
Fig. 1 is identified the present invention is based on the fish of fractal theory and BP algorithm and vaccine injection method flow diagram.
Specific embodiment
Elaborate below to the embodiment of the present invention, the present embodiment with the technical scheme is that according to development,
Give detailed embodiment and specific operating process.
The embodiment of the present invention provides a kind of fish vaccine injecting method based on fractal theory and BP algorithm, vaccine injection
When, the direction of fish is fish head preceding, and dorsal fin is upward, and a kind of upright state, injection angles are to put position partially in dorsal fin.It identifies
The image that is combined for fish head and ridge of target image.
It is that the present invention is based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method flow diagrams referring to Fig. 1.
Specific implementation step is:
1st, camera is mounted on the surface of fish, by the fish diagram of camera interception 512*256 pixels as 200,
Obtain the coloured image of fish.
2nd, the coloured image of the fish is filtered and smoothing processing so that image clearly, from image in the middle part of one point be
Two be split obtain pixel be 256*256 target image, the target image there are four types of part combination image, described four
Kind of part combination is respectively fish tail and abdomen, fish tail and ridge, fish head and abdomen, fish head and ridge.
3rd, with fractal theory algorithm, to the 256*256 pixel images of acquisition, feature vector is obtained, wherein characteristic value has 8
It is a, including singular value minimum value amin, singular value maximum value amax, spectrum width amax-amin, multifractal spectra maximum value f (amax), it is more
Multifractal spectrum minimum value f (amin), spectral difference f (amax)-f(amin), β is image slices vegetarian refreshments number, because of ridge and fish head direction,
Pixel number than tail portion and ventral direction is more;γ is the fish head or fish tail width value of distance measuring sensor actual measurement, judges head
Portion or tail portion, fish head portion is then wide forward, and fish tail is then narrow forward.
4th, three layers of BP neural network model are established, the model structure of the BP neural network includes input layer, hidden layer, defeated
Go out layer and desired output, the input number of plies NinFor the number 8 of the characteristic value, the output number of plies NoutFor fish head to be identified
And ridge, the number 2 of fish privileged site, it is N to imply the number of plieshidden, formula Nhidden=2 × (Nout×Nin)1/2, it is calculated
Implicit number of plies NhiddenIt is 8.
The desired output, if fish head output is 1, ridge output is 1, and the output of remaining position is 0;
The desired output difference of the target fish tail and abdomen, fish tail and ridge, fish head and abdomen, fish head and ridge
For 0 and 0,0 and 1,1 and 0,1 and 1;
Training is iterated by the BP neural network so that network output overall error is less than 0.1 everywhere convergent, training knot
Beam;Identify the image of the fish head and ridge combination, the corresponding desired output is 1 and 1, is met the requirements, and others are all
It is undesirable.
5th, undesirable fish then discharges, and is put into pool, and satisfactory fish then by distance measuring sensor, measures target
The length of fish calculates injection position, carries out vaccine injection.
Above example be the application preferred embodiment, those of ordinary skill in the art can also on this basis into
The various transformation of row or improvement, under the premise of the total design of the application is not departed from, these transformation or improvement should all belong to this Shen
Within the scope of please being claimed.
Claims (9)
- It is 1. a kind of based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method, it is characterised in that:Include the following steps:S1, the coloured image for obtaining fish;S2, the coloured image is pre-processed, image segmentation acquisition target image;S3, the characteristic value with each target image after the extraction segmentation of fractal theory algorithm, obtain multi-feature vector group;S4, the multi-feature vector group is trained with BP neural network algorithm, symbol is identified in the target image Close the image of fish privileged site combination requirement;S5, undesirable fish then discharge, and are put into pool, and satisfactory fish then by distance measuring sensor, measures target fish Length, calculate injection position, carry out vaccine injection.
- 2. it is according to claim 1 a kind of based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method, it is special Sign is, in step S1, camera is mounted on the surface of the fish, and the fish diagram picture of L × W pixels is intercepted by the camera M, obtain the coloured image of fish.
- 3. it is according to claim 1 a kind of based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method, it is special Sign is, in step S2, the pretreatment is included to image filtering and smoothing processing, and described image segmentation is from one point in the middle part of image Acquisition target image is split for two, there are four types of the image of part combination, four kinds of part combinations point for the target image Not Wei fish tail and abdomen, fish tail and ridge, fish head and abdomen, fish head and ridge.
- 4. it is according to claim 1 a kind of based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method, it is special Sign is, in step S3, the characteristic value has 8, respectivelySingular value minimum value amin, fish diagram is represented as maximum probability estimates region property;Singular value maximum value amax, fish diagram is represented as medium and small probability measure region property;Spectrum width amax-amin, reflect inhomogeneities degree of the entire fish diagram as probability distribution on fractal structure;Multifractal spectra maximum value f (amax), fish diagram is represented as small probability lower structure complexity and degree of irregularity;Multifractal spectra minimum value f (amin), fish diagram is represented as complexity and degree of irregularity under maximum probability;Spectral difference f (amax)-f(amin), reflect that fish diagram image surface is maximum, number ratio at minimum;β is image slices vegetarian refreshments number;γ is the fish head or fish tail width value of distance measuring sensor actual measurement.
- 5. it is according to claim 1 a kind of based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method, it is special Sign is, in step S4, the fish privileged site combination is specially fish head and ridge combination.
- 6. it is according to claim 5 a kind of based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method, it is special Sign is, in step S4, the model structure of the BP neural network includes input layer, hidden layer, output layer and desired output, institute State input number of plies NinFor the number 8 of the characteristic value, the output number of plies NoutFor the number 2 of the fish privileged site, hidden layer Number is Nhidden, formula Nhidden=2 × (Nout×Nin)1/2, implicit number of plies N is calculatedhiddenIt is 8;The desired output, if fish head output is 1, ridge output is 1, and the output of remaining position is 0;The desired output of the target fish tail and abdomen, fish tail and ridge, fish head and abdomen, fish head and ridge is respectively 0 With 0,0 and 1,1 and 0,1 and 1;Training is iterated by the BP neural network so that network output overall error is less than 0.1 everywhere convergent, and training terminates; Identify the image of the fish head and ridge combination, the corresponding desired output is 1 and 1, is met the requirements, and others are not all inconsistent Close requirement.
- 7. it is according to claim 6 a kind of based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method, it is special Sign is, in step S5, during the vaccine injection, the direction of fish is fish head preceding, and dorsal fin is upward, a kind of upright state, note Firing angle degree is to put position partially in dorsal fin.
- 8. it is according to claim 1 a kind of based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method, it is special Sign is, in step S5, by the satisfactory fish by the rolling axial advancement of certain speed v, triggers the ranging sensing The time of device is t, obtains length s=v × t of fish, and the displacement distance for calculating given injecting motor is injected, and next time, injection was logical Cross on first time mobile position carry out front and rear change adjust or by reset command by injecting motor return to initial position into Row injection.
- 9. it is according to claim 1 a kind of based on the identification of the fish of fractal theory and BP algorithm and vaccine injection method, it is special Sign is, in step S5, the distance measuring sensor is laser sensor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711383774.7A CN108133184B (en) | 2017-12-20 | 2017-12-20 | Fish identification and vaccine injection method based on fractal theory and BP algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711383774.7A CN108133184B (en) | 2017-12-20 | 2017-12-20 | Fish identification and vaccine injection method based on fractal theory and BP algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108133184A true CN108133184A (en) | 2018-06-08 |
CN108133184B CN108133184B (en) | 2020-04-28 |
Family
ID=62391891
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711383774.7A Active CN108133184B (en) | 2017-12-20 | 2017-12-20 | Fish identification and vaccine injection method based on fractal theory and BP algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108133184B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112288719A (en) * | 2020-10-29 | 2021-01-29 | 中国水产科学研究院渔业机械仪器研究所 | Kelp water content diagnosis method |
CN112464744A (en) * | 2020-11-09 | 2021-03-09 | 湖北省农业科学院农产品加工与核农技术研究所 | Fish posture identification method |
CN112580662A (en) * | 2020-12-09 | 2021-03-30 | 中国水产科学研究院渔业机械仪器研究所 | Method and system for recognizing fish body direction based on image features |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5957365A (en) * | 1982-09-25 | 1984-04-02 | Fujitsu Ltd | Discriminating circuit of back and belly of fish |
CN102867196A (en) * | 2012-09-13 | 2013-01-09 | 武汉大学 | Method for detecting complex sea-surface remote sensing image ships based on Gist characteristic study |
CN103039395A (en) * | 2013-01-11 | 2013-04-17 | 中国水产科学研究院渔业机械仪器研究所 | Industrial aquaculture automatic feeding system |
CN103400147A (en) * | 2013-07-25 | 2013-11-20 | 中国农业大学 | Image processing-based target fish recognition method and system |
CN104304199A (en) * | 2014-10-29 | 2015-01-28 | 中国水产科学研究院淡水渔业研究中心 | Fishing device capable of automatically selecting fish species |
CN104636737A (en) * | 2015-03-10 | 2015-05-20 | 无锡桑尼安科技有限公司 | Fish body fresh degree recognition system |
CN105046228A (en) * | 2015-07-25 | 2015-11-11 | 张丽 | Data communication based fish body identification method |
CN105069414A (en) * | 2015-07-25 | 2015-11-18 | 张丽 | Diver special fish identification system based on data communication |
US9298978B1 (en) * | 2012-05-03 | 2016-03-29 | Joseph F Hlatky | Optical fish recognition |
CN106503677A (en) * | 2016-10-28 | 2017-03-15 | 中国水产科学研究院渔业机械仪器研究所 | A kind of motion fry recognition methodss based on PCA and AdaBoost algorithms |
CN107292340A (en) * | 2017-06-19 | 2017-10-24 | 南京农业大学 | Lateral line scales recognition methods based on convolutional neural networks |
-
2017
- 2017-12-20 CN CN201711383774.7A patent/CN108133184B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5957365A (en) * | 1982-09-25 | 1984-04-02 | Fujitsu Ltd | Discriminating circuit of back and belly of fish |
US9298978B1 (en) * | 2012-05-03 | 2016-03-29 | Joseph F Hlatky | Optical fish recognition |
CN102867196A (en) * | 2012-09-13 | 2013-01-09 | 武汉大学 | Method for detecting complex sea-surface remote sensing image ships based on Gist characteristic study |
CN103039395A (en) * | 2013-01-11 | 2013-04-17 | 中国水产科学研究院渔业机械仪器研究所 | Industrial aquaculture automatic feeding system |
CN103400147A (en) * | 2013-07-25 | 2013-11-20 | 中国农业大学 | Image processing-based target fish recognition method and system |
CN104304199A (en) * | 2014-10-29 | 2015-01-28 | 中国水产科学研究院淡水渔业研究中心 | Fishing device capable of automatically selecting fish species |
CN104636737A (en) * | 2015-03-10 | 2015-05-20 | 无锡桑尼安科技有限公司 | Fish body fresh degree recognition system |
CN105046228A (en) * | 2015-07-25 | 2015-11-11 | 张丽 | Data communication based fish body identification method |
CN105069414A (en) * | 2015-07-25 | 2015-11-18 | 张丽 | Diver special fish identification system based on data communication |
CN106503677A (en) * | 2016-10-28 | 2017-03-15 | 中国水产科学研究院渔业机械仪器研究所 | A kind of motion fry recognition methodss based on PCA and AdaBoost algorithms |
CN107292340A (en) * | 2017-06-19 | 2017-10-24 | 南京农业大学 | Lateral line scales recognition methods based on convolutional neural networks |
Non-Patent Citations (1)
Title |
---|
洪锦奇: "《基于计算机视觉技术的分鱼算法研究》", 《中国优秀硕士论文全文数据库 信息科技辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112288719A (en) * | 2020-10-29 | 2021-01-29 | 中国水产科学研究院渔业机械仪器研究所 | Kelp water content diagnosis method |
CN112464744A (en) * | 2020-11-09 | 2021-03-09 | 湖北省农业科学院农产品加工与核农技术研究所 | Fish posture identification method |
CN112580662A (en) * | 2020-12-09 | 2021-03-30 | 中国水产科学研究院渔业机械仪器研究所 | Method and system for recognizing fish body direction based on image features |
Also Published As
Publication number | Publication date |
---|---|
CN108133184B (en) | 2020-04-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107871124B (en) | A kind of Remote Sensing Target detection method based on deep neural network | |
CN109785337A (en) | Mammal counting method in a kind of column of Case-based Reasoning partitioning algorithm | |
CN103942577B (en) | Based on the personal identification method for establishing sample database and composite character certainly in video monitoring | |
CN108133184A (en) | It is a kind of based on the fish of fractal theory and BP algorithm identification and vaccine injection method | |
CN109166094A (en) | A kind of insulator breakdown positioning identifying method based on deep learning | |
CN107168527A (en) | The first visual angle gesture identification and exchange method based on region convolutional neural networks | |
CN106845330A (en) | A kind of training method of the two-dimension human face identification model based on depth convolutional neural networks | |
CN109145808B (en) | Tuna identification method based on self-adaptive fish body bending model | |
CN108038513A (en) | A kind of tagsort method of liver ultrasonic | |
CN108427942A (en) | A kind of palm detection based on deep learning and crucial independent positioning method | |
CN108830856B (en) | GA automatic segmentation method based on time series SD-OCT retina image | |
CN107784308A (en) | Conspicuousness object detection method based on the multiple dimensioned full convolutional network of chain type | |
CN106127145A (en) | Pupil diameter and tracking | |
CN107392929A (en) | A kind of intelligent target detection and dimension measurement method based on human vision model | |
CN106991370A (en) | Pedestrian retrieval method based on color and depth | |
CN102222357A (en) | Foot-shaped three-dimensional surface reconstruction method based on image segmentation and grid subdivision | |
CN108961330A (en) | The long measuring method of pig body and system based on image | |
CN110310323A (en) | The retinal blood vessels caliber measurement method being fitted based on Hessian matrix and dimensional Gaussian | |
CN104546000B (en) | Shape feature-based ultrasonic image bladder volume measuring method and device | |
CN110197113A (en) | A kind of method for detecting human face of high-precision anchor point matching strategy | |
CN109145913A (en) | A kind of non-homogeneous background discrete phase Binary Sketch of Grey Scale Image processing method | |
CN104545999B (en) | Method and device for measuring bladder volume through ultrasound images | |
CN104966072B (en) | It is a kind of based on shape without colour code machine fish pose recognizer | |
CN105043395A (en) | Real-time dynamic location method for moon surface soft landing of aircraft | |
CN109191461A (en) | A kind of Countryside Egg recognition methods and identification device based on machine vision technique |
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 |