CN108719424A - A kind of aquatic products sorting technique and system based on machine vision - Google Patents
A kind of aquatic products sorting technique and system based on machine vision Download PDFInfo
- Publication number
- CN108719424A CN108719424A CN201810564167.9A CN201810564167A CN108719424A CN 108719424 A CN108719424 A CN 108719424A CN 201810564167 A CN201810564167 A CN 201810564167A CN 108719424 A CN108719424 A CN 108719424A
- Authority
- CN
- China
- Prior art keywords
- aquatic products
- image
- weight
- machine vision
- current
- 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.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A22—BUTCHERING; MEAT TREATMENT; PROCESSING POULTRY OR FISH
- A22C—PROCESSING MEAT, POULTRY, OR FISH
- A22C25/00—Processing fish ; Curing of fish; Stunning of fish by electric current; Investigating fish by optical means
- A22C25/04—Sorting fish; Separating ice from fish packed in ice
-
- A—HUMAN NECESSITIES
- A22—BUTCHERING; MEAT TREATMENT; PROCESSING POULTRY OR FISH
- A22C—PROCESSING MEAT, POULTRY, OR FISH
- A22C29/00—Processing shellfish or bivalves, e.g. oysters, lobsters; Devices therefor, e.g. claw locks, claw crushers, grading devices; Processing lines
- A22C29/005—Grading or classifying shellfish or bivalves
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
- Food Science & Technology (AREA)
- Sorting Of Articles (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of aquatic products sorting technique and system based on machine vision, to solve the problems, such as that aquatic products manual sort low precision, efficiency are low, this method includes：S10：The image information for obtaining aquatic products carries out image preprocessing to described image information, obtains the image outline area of the aquatic products；S20：The weight data for obtaining the aquatic products establishes prediction model according to the weight data of the aquatic products and image outline area；S30：Category signal is received, the image outline area of current aquatic products is obtained, according to the prediction model, obtains the pre- measured weight of current aquatic products；S40：According to the pre- measured weight of the current aquatic products, classify to the current aquatic products.Using the present invention, the size of aquatic products is judged by machine vision, further obtains weight information, so as to carry out mechanized classification to aquatic products, improved classification effectiveness and precision, reduce cost of labor.
Description
Technical field
The present invention relates to technical field of machine vision more particularly to a kind of aquatic products sorting technique based on machine vision and
System.
Background technology
Aquatic products are mainly based on the fish in fresh water or seawater, after being caught to fish, need to fish into
Row classifies choosing sieve to adapt to a variety of different demands in the market, for example, after fishing disembarkation in box for breeding, being looked forward to by Larimichthys crocea
Industry or raiser can classify according to weight, the quality of Larimichthys crocea, facilitate sale and seek profit.Fish are carried out at present
The equipment of classification mainly has Weighing type, optical principle formula, shape formula etc., Weighing type grader according to the difference of its classification principle
It is classified according to fish body weight using mass sensor, effectiveness of classification is high, but needs to weigh one by one, and efficiency is low；Optical principle
Grader is classified according to electro-optical distance measurement or colorimetric, is mainly sorted with fruits and vegetables；Shape formula grader is big according to the geometric dimension of fish body
It is small to be classified, it can be divided into two kinds of products of rotary roller and drum-type again according to the different of machinery are selected.Rotary roller system uses
The spacing distance of the roller slowly rotated, each roller is gradually widened, using fish body thickness as foundation, to divide different size of fish
It opens, rotary roller grading gaps and rotating speed need to be adjusted manually, and the degree of automation is low, and effectiveness of classification is influenced by operating personnel's subjective factor
Greatly；In roller classification, Larimichthys crocea is flowed into roller by hopper, rolling and movement occurs therebetween, and pass through in the process
Corresponding sieve pore outflow, to reach classification, but can cause secondary damage to fish body.Other than machine sorts, there is also hands
Work point selects, but hand-sorting obviously lacks efficiency, while accuracy is not also high, also adds cost of labor, is unfavorable for body
The different fish of weight carry out Fast Classification.
As the patent of Publication No. CN105665296A discloses apparatus for automatically sorting and the classification of a kind of fish products
Method, the device include bearing support and rewinding box, and kidney-shaped groove is offered at the top of bearing support, chain is provided in kidney-shaped groove
Item is installed with several pedestals on chain, and Weighing mechanism is arranged in the side of pedestal, and Weighing mechanism includes link block and weight induction
Unit, link block backwards to box body are provided with rotating arm, and turnover box is installed on rotating arm, and the first electricity is provided on bearing support
Machine is provided with the second motor in link block, control unit and wiper mechanism is additionally provided on bearing support, wiper mechanism includes water
Case, water pump and detergent line.The device can also classify to fish by its sorting technique, still, be needed in classification
Single fish body weight is weighed, classification speed is slow, and efficiency is low.
Invention content
The technical problem to be solved in the present invention be designed to provide a kind of aquatic products sorting technique based on machine vision and
System, accuracy low problem slow to solve existing manual sort speed.
To achieve the goals above, the technical solution adopted by the present invention is as follows：
A kind of aquatic products sorting technique based on machine vision, including step：
S10：The image information for obtaining aquatic products carries out image preprocessing to described image information, obtains the aquatic products
Image outline area；
S20：The weight data for obtaining the aquatic products is built according to the weight data of the aquatic products and image outline area
Vertical prediction model；
S30：Category signal is received, the image outline area for obtaining current aquatic products is worked as according to the prediction model
The pre- measured weight of preceding aquatic products；
S40：According to the pre- measured weight of the current aquatic products, classify to the current aquatic products.
Further, further include step before the step S10：
The image information of aquatic products is acquired by imaging sensor, and by the aquatic products into line label.
Further, the step S10 further includes step：
Carry out image background removal, gradation of image processing, image binaryzation processing, image wheel successively to described image information
Wide area extraction.
Further, the step S40 specifically includes step：
Preset weight range is received, judges that the pre- measured weight is within the scope of preset weight, if so, sending triggering letter
Number the current aquatic products are sorted to corresponding sorting controller.
Further, the step S20 further includes step：
According to prediction model described in default Regression Equations, the regression equation is：
Y=a*xb
In above formula, y is the weight of aquatic products, and x is the image outline area of aquatic products, and a, b are predetermined coefficient.
A kind of aquatic products categorizing system based on machine vision, including：
Image processing module：Image information for obtaining aquatic products carries out image preprocessing to described image information, obtains
To the image outline area of the aquatic products；
Weight acquisition module：Weight data for obtaining the aquatic products, according to the weight data of the aquatic products and
Image outline area establishes prediction model；
Prediction module：For receiving category signal, the image outline area of current aquatic products is obtained, according to the prediction mould
Type obtains the pre- measured weight of current aquatic products；
Sort module：For the pre- measured weight according to the current aquatic products, classify to the current aquatic products.
Further, the system also includes：
Image acquisition units：For by imaging sensor acquire aquatic products image information, and by the aquatic products into
Line label.
Further, the system also includes：
Image processing unit：For carrying out image background removal, gradation of image processing, image successively to described image information
Binary conversion treatment, image outline area extraction.
Further, the sort module further includes：
Range judging unit：For receiving preset weight range, judge that the pre- measured weight is within the scope of preset weight,
The current aquatic products are sorted to corresponding sorting controller if so, sending trigger signal.
Further, the system also includes：
Model foundation unit：For being according to prediction model, the regression equation described in default Regression Equations：
Y=a*xb
In above formula, y is the weight of aquatic products, and x is the image outline area of aquatic products, and a, b are predetermined coefficient.
Using the present invention, the contour area of fish body is obtained by machine vision, using prediction model, according to the profile of fish body
The weight of Area Prediction fish quickly can carry out category filter to the fish body of different weight, save the cost of manual sort,
It can ensure the accuracy of fish body weight classification, and avoid fish body in assorting process by secondary damage.
Description of the drawings
Fig. 1 is a kind of aquatic products sorting technique flow chart based on machine vision that the embodiment of the present invention one provides；
Fig. 2 is display image of the Larimichthys crocea image in the channels R of one embodiment of the present invention offer；
Fig. 3 is display image of the Larimichthys crocea image in the channels G of one embodiment of the present invention offer；
Fig. 4 is display image of the Larimichthys crocea image in channel B of one embodiment of the present invention offer；
Fig. 5 is Larimichthys crocea image binaryzation treated the image that one embodiment of the present invention provides；
Fig. 6 is the Larimichthys crocea area profile extraction image that one embodiment of the present invention provides；
Fig. 7 is a kind of aquatic products sorting technique flow chart based on machine vision provided by Embodiment 2 of the present invention；
Fig. 8 is a kind of system construction drawing of aquatic products categorizing system based on machine vision provided in an embodiment of the present invention.
Specific implementation mode
Following is a specific embodiment of the present invention in conjunction with the accompanying drawings, technical scheme of the present invention will be further described,
However, the present invention is not limited to these examples.
Embodiment one
With reference to figure 1, Fig. 1 provides a kind of aquatic products sorting technique based on machine vision, including step：
S10：The image information for obtaining aquatic products carries out image preprocessing to described image information, obtains the aquatic products
Image outline area；
S20：The weight data for obtaining the aquatic products is built according to the weight data of the aquatic products and image outline area
Vertical prediction model；
S30：Category signal is received, the image outline area for obtaining current aquatic products is worked as according to the prediction model
The pre- measured weight of preceding aquatic products；
S40：According to the pre- measured weight of the current aquatic products, classify to the current aquatic products.
Mainly based on fish, there is fish aquatic products smooth surface, general fish all to have complete unified shape
Shape, although there are difference between different fingerlings, shape difference is little, facilitates the size of acquisition fish body, to convenient pre-
The weight of the fish body is surveyed, is further classified to the fish body of different weight.
In the embodiment of the present invention, aquatic products are illustrated as an example with Larimichthys crocea, Larimichthys crocea is salvaging disembarkation
Afterwards, it will be transported on each assembly line by conveyer belt to be handled accordingly.
First, it before the fish body to different weight is classified, needs to establish prediction model, step S10 and step
S20 is established by extracting the contour area and fish body weight of 40 Larimichthys croceas using the relationship of both different models fittings
Prediction model, to be predicted the weight of subsequent Larimichthys crocea using prediction model.
In step S10, the image information of aquatic products is obtained, image preprocessing is carried out to described image information, is obtained described
The image outline area of aquatic products.
The image information of Larimichthys crocea can be shot by camera, by being set above some location point of conveyer belt
Camera is set, often has a Larimichthys crocea by the position, camera shooting is primary, obtains the image information of each Larimichthys crocea.
In an embodiment of the invention, image preprocessing be image information is carried out successively image background removal,
Gradation of image processing, image binaryzation processing, image outline area extraction.Image background removal is the background for getting rid of image,
Make a kind of image processing method of the foreground and background class in image, for example, setting background to green, carries out Background
When as removal, the green in image is got rid of, that is, has achieved the purpose that background removal.Preferably, in the present embodiment, due to rheum officinale
Fish fish belly, fin color are mainly golden yellow, and fish body is faint yellow, and the fish back of the body is that lark forms, and the reflectivity of white background is high,
By setting conveyer belt to white, RGB triple channel color component mean values are obtained using histogram, each pixel is done into subtraction removal
The background of the image taken can obtain clearly Larimichthys crocea foreground, it needs to be understood that, it can also be according to fingerling not
Together, select corresponding suitable conveyer belt color as background color.As shown in Figures 2 to 4, Fig. 2 is Larimichthys crocea image in the channels R
When display situation, Fig. 3 is display situation of the Larimichthys crocea image under the channels G, and Fig. 4 is that Larimichthys crocea image is aobvious under channel B
Show situation.
Gradation of image processing is that coloured image is converted to gray level image, and the Larimichthys crocea taken is golden yellow, light due to having
The different color such as yellow and lark, after gray proces, color can further be unified, and improve processing speed
Degree.
Image binaryzation processing is the process that whole image is showed to apparent black and white effect so that the profile of Larimichthys crocea
It is more clear, can refer to Fig. 5, Fig. 5 is the image that Larimichthys crocea image obtains after gradation of image processing and binary conversion treatment.
Image outline area extraction finally is carried out to the image after binary conversion treatment, the profile of Larimichthys crocea is extracted, into one
The contour area of Larimichthys crocea is calculated in step, and with reference to figure 6, Fig. 6 is the contour area extraction figure of Larimichthys crocea.
In step S20, the weight data of the aquatic products is obtained, according to the weight data and image outline of the aquatic products
Area establishes prediction model.
The contour area of Larimichthys crocea is obtained from step S10, then obtains the weight of Larimichthys crocea, establishes prediction model, from a large amount of
Larimichthys crocea contour area and weight between relationship analysis, when the regression equation of prediction model is
Y=a*xb
When, most accurate degree of fitting can be obtained, accuracy is higher, and in above formula, y is the weight of aquatic products, and x is aquatic products
Image outline area, a, b be predetermined coefficient, i.e., using the contour area of Larimichthys crocea as input, obtain the prediction of the Larimichthys crocea
Weight.
Preferably, in the present embodiment, the numerical value that the numerical value of a is 1.3406, b is 2.943901*10-2。
In step S30, category signal is received, the image outline area of current aquatic products is obtained, according to the prediction model,
Obtain the pre- measured weight of current aquatic products.
After step S20 establishes prediction model, step S30 is entered, category signal can be the startup letter of system
Number, for example, when needing to classify to Larimichthys crocea, then activation system, generates category signal.
After receiving category signal, the image for the current Larimichthys crocea for needing to classify can be shot by camera, is gone forward side by side
Image procossing in row step S10, obtains image outline area, further according to the prediction model established in step S20, to current big
The weight of yellow croaker is predicted.
In step S40, according to the pre- measured weight of the current aquatic products, classify to the current aquatic products.It is different
The weight of the Larimichthys crocea of contour area is different, by pre- measured weight, classifies to the Larimichthys crocea of different weight, obtains more
The Larimichthys crocea of class different weight.
In the present embodiment, the image of Larimichthys crocea can be quickly acquired by image collecting device first, without right
Each Larimichthys crocea is weighed, and avoids Larimichthys crocea in weighing process by secondary damage, and uses prediction model can
Accurately the weight of Larimichthys crocea is predicted, ensures that accuracy, realization quickly classify to the Larimichthys crocea of different weight.
Embodiment two
With reference to figure 7, Fig. 7 is a kind of aquatic products sorting technique based on machine vision provided in this embodiment, including step：
S10：The image information for obtaining aquatic products carries out image preprocessing to described image information, obtains the aquatic products
Image outline area；
S20：The weight data for obtaining the aquatic products is built according to the weight data of the aquatic products and image outline area
Vertical prediction model；
S30：Category signal is received, the image outline area for obtaining current aquatic products is worked as according to the prediction model
The pre- measured weight of preceding aquatic products；
S401：Preset weight range is received, judges that the pre- measured weight is within the scope of preset weight, if so, sending
Trigger signal sorts the current aquatic products to corresponding sorting controller.
The difference between this embodiment and the first embodiment lies in step S40 specifically includes step S401.
In step S401, preset weight range is received, judges that the pre- measured weight is within the scope of preset weight, if so,
Trigger signal is then sent to sort the current aquatic products to corresponding sorting controller.
Due to needing to classify according to the different weight of Larimichthys crocea, all there may be not for the weight of each Larimichthys crocea
Together, in the present embodiment, multiple weight sections can be set, for example, the first weight interval range, the second weight interval range,
Third weight interval range, each weight interval range are both provided with a sorting controller, when the pre- measured weight of Larimichthys crocea
When falling a weight interval range wherein, then sends trigger signal control sorting controller and the Larimichthys crocea is sorted to the weight
Section.
By the corresponding sorting controller of control, the Larimichthys crocea in different weight interval range can be distinguished,
At the same time it can also which multiple weight interval ranges are arranged, classification is more refined.
Embodiment three
With reference to figure 8, a kind of system construction drawing of the aquatic products categorizing system based on machine vision is present embodiments provided, is wrapped
It includes：
Image processing module 81：Image information for obtaining aquatic products carries out image preprocessing to described image information,
Obtain the image outline area of the aquatic products；
Weight acquisition module 82：Weight data for obtaining the aquatic products, according to the weight data of the aquatic products
And image outline area establishes prediction model；
Prediction module 83：For receiving category signal, the image outline area of current aquatic products is obtained, according to the prediction
Model obtains the pre- measured weight of current aquatic products；
Sort module 84：For the pre- measured weight according to the current aquatic products, classify to the current aquatic products.
The system further includes model foundation unit 85, for according to default Regression Equations prediction model, regression equation
For：
Y=a*xb
In above formula, y is the weight of aquatic products, and x is the image outline area of aquatic products, and a, b are predetermined coefficient.
When establishing prediction model, a plurality of rheum officinale can be obtained by image processing module 81 and Weight acquisition module 82
The contour area and weight data of fish, to analyze determining prediction model, in above formula, the concrete numerical value of a, b can quote reality
Apply the numerical value provided in example one, the present embodiment can also be analyzed by model foundation unit 85 contour area of a plurality of Larimichthys crocea with
And weight data is confirmed, ensures the accuracy of prediction model.
In the present embodiment, which further includes image acquisition units 80, for acquiring aquatic products by imaging sensor
Image information, and by the aquatic products into line label.
Image acquisition units 80 can be camera, by the way that light source is arranged around camera, ensure the quality of the picture of shooting,
In the present embodiment, since Larimichthys crocea is sorted in conveyer belt, the upper end in the forefront of conveyer belt can be arranged in camera, and
Shooting time interval is set, to shoot the image of lower Larimichthys crocea.
The case where for conveying a plurality of Larimichthys crocea simultaneously on conveyer belt, the image of next Larimichthys crocea is often shot, is required for
To Larimichthys crocea into line label, sequence of positions of the corresponding Larimichthys crocea in conveyer belt is recorded, sorting controller pair is enabled to
Larimichthys crocea is identified, and prevents from causing confusion in sorting, subsequent sort controller is facilitated accurately to be sorted.
Image processing module 81 needs to establish data connection between image acquisition units 80, for example, image acquisition units
80 directly by the image transmitting of shooting to computer, and image processing module 80 can be used as the image processing software in computer.
Image processing module 81 includes image processing unit 811.
Image processing unit 811：For described image information is carried out successively image background removal, gradation of image processing,
Image binaryzation processing, image outline area extraction.
Illustrated in embodiment one image background removal, gradation of image processing, image binaryzation processing with
And the concrete operations of image outline area extraction, the present embodiment do not illustrate, it needs to be understood that, pass through image processing unit
After 811 pairs of images are handled, image outline area, the i.e. contour area of Larimichthys crocea can be extracted, then by contour area
Data are sent to prediction module 83.
Prediction module 83 may be mounted in computer, after obtaining the contour area of Larimichthys crocea, directly pass through prediction
Model and regression equation
Y=a*xb
It is calculated the pre- measured weight of Larimichthys crocea, in above formula, y is the weight of aquatic products, and x is the image outline face of aquatic products
Product, a, b are predetermined coefficient.Wherein, the concrete numerical value of a, b can quote the numerical value provided in embodiment one.
Sort module 84 further includes range judging unit 841.
Range judging unit 841：For receiving preset weight range, judge whether the pre- measured weight is in preset weight
In range, the current aquatic products are sorted to corresponding sorting controller if so, sending trigger signal.
Prediction weight range can be divided into multiple range intervals according to different weight, such as the first prediction weight range,
Second prediction weight range, third predict that weight range, each range intervals are provided with corresponding sorting controller, work as rheum officinale
When the pre- measured weight of fish is in the range intervals, then the sorting controller of the range intervals is controlled, which is sorted out.
Sort module 84 receives the Larimichthys crocea that prediction module 83 is sent and predicts weight information, first to the predictor of Larimichthys crocea
Judged again, confirm which range intervals it is in, then control the sorting controller being arranged on the range intervals, is sorted
Controller will generate sorting operation, which be sorted out conveyer belt, sorting controller can be arranged directly on conveyer belt
The Larimichthys crocea is directly released conveyer belt, falls into and display column by side.
Modules work compound in system, the image acquisition units 80 in conveyer belt front end collect the image of Larimichthys crocea
Later, the weight of this Larimichthys crocea can be rapidly predicted by image processing module 81, prediction module 83, and according to pre- check weighing
Amount, classifies to the Larimichthys crocea in the rear end of conveyer belt, which can be convenient and efficient directly in flowing water on-line operation.
Specific embodiment described herein is only an example for the spirit of the invention.Technology belonging to the present invention is led
The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method
In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.
Claims (10)
1. a kind of aquatic products sorting technique based on machine vision, which is characterized in that including step：
S10：The image information for obtaining aquatic products carries out image preprocessing to described image information, obtains the figure of the aquatic products
As contour area；
S20：The weight data for obtaining the aquatic products is established pre- according to the weight data of the aquatic products and image outline area
Survey model；
S30：Category signal is received, the image outline area of current aquatic products is obtained, according to the prediction model, obtains current water
The pre- measured weight of product；
S40：According to the pre- measured weight of the current aquatic products, classify to the current aquatic products.
2. a kind of aquatic products sorting technique based on machine vision according to claim 1, which is characterized in that the step
Further include step before S10：
The image information of aquatic products is acquired by imaging sensor, and by the aquatic products into line label.
3. a kind of aquatic products sorting technique based on machine vision according to claim 1, which is characterized in that the step
S10 further includes step：
Carry out image background removal, gradation of image processing, image binaryzation processing, image outline face successively to described image information
Product extraction.
4. a kind of aquatic products sorting technique based on machine vision according to claim 1, which is characterized in that the step
S40 specifically includes step：
Preset weight range is received, judges the pre- measured weight whether within the scope of preset weight, if so, sending triggering letter
Number the current aquatic products are sorted to corresponding sorting controller.
5. a kind of aquatic products sorting technique based on machine vision according to claim 1, which is characterized in that the step
S20 further includes step：
According to prediction model described in default Regression Equations, the regression equation is：
Y=a*xb
In above formula, y is the weight of aquatic products, and x is the image outline area of aquatic products, and a, b are predetermined coefficient.
6. a kind of aquatic products categorizing system based on machine vision, which is characterized in that including：
Image processing module：Image information for obtaining aquatic products carries out image preprocessing to described image information, obtains institute
State the image outline area of aquatic products；
Weight acquisition module：Weight data for obtaining the aquatic products, according to the weight data and image of the aquatic products
Contour area establishes prediction model；
Prediction module：For receiving category signal, the image outline area of current aquatic products is obtained, according to the prediction model,
Obtain the pre- measured weight of current aquatic products；
Sort module：For the pre- measured weight according to the current aquatic products, classify to the current aquatic products.
7. a kind of aquatic products categorizing system based on machine vision according to claim 6, which is characterized in that the system
Further include：
Image acquisition units：Image information for acquiring aquatic products by imaging sensor, and by the aquatic products into rower
Number.
8. a kind of aquatic products categorizing system based on machine vision according to claim 6, which is characterized in that the system
Further include：
Image processing unit：For carrying out image background removal, gradation of image processing, image two-value successively to described image information
Change processing, image outline area extraction.
9. a kind of aquatic products categorizing system based on machine vision according to claim 6, which is characterized in that the classification
Module further includes：
Range judging unit：For receiving preset weight range, the pre- measured weight is judged whether within the scope of preset weight,
The current aquatic products are sorted to corresponding sorting controller if so, sending trigger signal.
10. a kind of aquatic products categorizing system based on machine vision according to claim 6, which is characterized in that the system
System further includes：
Model foundation unit：For being according to prediction model, the regression equation described in default Regression Equations：
Y=a*xb
In above formula, y is the weight of aquatic products, and x is the image outline area of aquatic products, and a, b are predetermined coefficient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810564167.9A CN108719424A (en) | 2018-06-04 | 2018-06-04 | A kind of aquatic products sorting technique and system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810564167.9A CN108719424A (en) | 2018-06-04 | 2018-06-04 | A kind of aquatic products sorting technique and system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108719424A true CN108719424A (en) | 2018-11-02 |
Family
ID=63931877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810564167.9A Pending CN108719424A (en) | 2018-06-04 | 2018-06-04 | A kind of aquatic products sorting technique and system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108719424A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109625195A (en) * | 2018-12-10 | 2019-04-16 | 威海海洋职业学院 | A kind of intelligence ship storage fish device |
| CN110378241A (en) * | 2019-06-25 | 2019-10-25 | 北京百度网讯科技有限公司 | Crop growthing state monitoring method, device, computer equipment and storage medium |
| CN110394785A (en) * | 2019-07-17 | 2019-11-01 | 浙江海洋大学 | A kind of sorting aquatic products grabbing device |
| CN110969149A (en) * | 2019-12-30 | 2020-04-07 | 韩山师范学院 | Intelligent image recognition device of chicken claw weighing machine and weighing method thereof |
| CN110991220A (en) * | 2019-10-15 | 2020-04-10 | 北京海益同展信息科技有限公司 | Egg detection method, egg image processing method, egg detection device, egg image processing device, electronic equipment and storage medium |
| CN111480606A (en) * | 2020-04-23 | 2020-08-04 | 舟山国家远洋渔业基地科技发展有限公司 | Marine product grading treatment system for ocean fishing ship |
| CN114612549A (en) * | 2022-01-14 | 2022-06-10 | 北京市农林科学院信息技术研究中心 | Method and device for predicting optimal fruiting picking time |
| CN114680163A (en) * | 2022-03-23 | 2022-07-01 | 宜宾职业技术学院 | Combined intelligent crayfish sorting device and sorting method |
| CN116740473A (en) * | 2023-08-10 | 2023-09-12 | 中国水产科学研究院南海水产研究所 | Automatic sorting method and system for fish catch based on machine vision |
| CN117592312A (en) * | 2024-01-18 | 2024-02-23 | 福建东水食品股份有限公司 | Electronic weighing method and system based on aquatic products |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2559336A1 (en) * | 2011-08-19 | 2013-02-20 | Asociación Industrial de Óptica, Color e Imagen - AIDO | System and method for automatic classification of fish alevins by means of optical methods |
| CN105195438A (en) * | 2015-09-25 | 2015-12-30 | 广东海洋大学 | Embedded type automatic pearl sorting device and method based on image recognition |
| CN105651776A (en) * | 2015-12-30 | 2016-06-08 | 中国农业大学 | Device and method for automatically grading beef carcass meat yield based on computer vision |
| CN106140648A (en) * | 2016-08-19 | 2016-11-23 | 南京农业大学 | A kind of chicken genetic ability for carcass weight automatic grading system based on machine vision and stage division |
| US20170372126A1 (en) * | 2014-10-14 | 2017-12-28 | Microsoft Technology Licensing, Llc | Depth From Time of Flight Camera |
| CN207138317U (en) * | 2016-12-31 | 2018-03-27 | 青岛有田农业发展有限公司 | A kind of fine graded feeding of modified carrot computer vision and blanking device |
-
2018
- 2018-06-04 CN CN201810564167.9A patent/CN108719424A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2559336A1 (en) * | 2011-08-19 | 2013-02-20 | Asociación Industrial de Óptica, Color e Imagen - AIDO | System and method for automatic classification of fish alevins by means of optical methods |
| US20170372126A1 (en) * | 2014-10-14 | 2017-12-28 | Microsoft Technology Licensing, Llc | Depth From Time of Flight Camera |
| CN105195438A (en) * | 2015-09-25 | 2015-12-30 | 广东海洋大学 | Embedded type automatic pearl sorting device and method based on image recognition |
| CN105651776A (en) * | 2015-12-30 | 2016-06-08 | 中国农业大学 | Device and method for automatically grading beef carcass meat yield based on computer vision |
| CN106140648A (en) * | 2016-08-19 | 2016-11-23 | 南京农业大学 | A kind of chicken genetic ability for carcass weight automatic grading system based on machine vision and stage division |
| CN207138317U (en) * | 2016-12-31 | 2018-03-27 | 青岛有田农业发展有限公司 | A kind of fine graded feeding of modified carrot computer vision and blanking device |
Non-Patent Citations (2)
| Title |
|---|
| 张志强: "基于机器视觉的淡水鱼品种识别及重量预测研究", 《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 (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109625195B (en) * | 2018-12-10 | 2020-09-08 | 威海海洋职业学院 | Intelligent boats and ships store up fish device |
| CN109625195A (en) * | 2018-12-10 | 2019-04-16 | 威海海洋职业学院 | A kind of intelligence ship storage fish device |
| CN110378241A (en) * | 2019-06-25 | 2019-10-25 | 北京百度网讯科技有限公司 | Crop growthing state monitoring method, device, computer equipment and storage medium |
| CN110378241B (en) * | 2019-06-25 | 2022-04-29 | 北京百度网讯科技有限公司 | Crop growth state monitoring method and device, computer equipment and storage medium |
| CN110394785A (en) * | 2019-07-17 | 2019-11-01 | 浙江海洋大学 | A kind of sorting aquatic products grabbing device |
| CN110991220B (en) * | 2019-10-15 | 2023-11-07 | 京东科技信息技术有限公司 | Egg detection and image processing method and device, electronic equipment and storage medium |
| CN110991220A (en) * | 2019-10-15 | 2020-04-10 | 北京海益同展信息科技有限公司 | Egg detection method, egg image processing method, egg detection device, egg image processing device, electronic equipment and storage medium |
| CN110969149A (en) * | 2019-12-30 | 2020-04-07 | 韩山师范学院 | Intelligent image recognition device of chicken claw weighing machine and weighing method thereof |
| CN111480606A (en) * | 2020-04-23 | 2020-08-04 | 舟山国家远洋渔业基地科技发展有限公司 | Marine product grading treatment system for ocean fishing ship |
| CN114612549A (en) * | 2022-01-14 | 2022-06-10 | 北京市农林科学院信息技术研究中心 | Method and device for predicting optimal fruiting picking time |
| CN114612549B (en) * | 2022-01-14 | 2024-06-07 | 北京市农林科学院信息技术研究中心 | Fruiting picking optimal time prediction method and device |
| CN114680163A (en) * | 2022-03-23 | 2022-07-01 | 宜宾职业技术学院 | Combined intelligent crayfish sorting device and sorting method |
| CN116740473A (en) * | 2023-08-10 | 2023-09-12 | 中国水产科学研究院南海水产研究所 | Automatic sorting method and system for fish catch based on machine vision |
| CN116740473B (en) * | 2023-08-10 | 2024-01-09 | 中国水产科学研究院南海水产研究所 | Automatic sorting method and system for fish catch based on machine vision |
| CN117592312A (en) * | 2024-01-18 | 2024-02-23 | 福建东水食品股份有限公司 | Electronic weighing method and system based on aquatic products |
| CN117592312B (en) * | 2024-01-18 | 2024-04-16 | 福建东水食品股份有限公司 | Electronic weighing method and system based on aquatic products |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108719424A (en) | A kind of aquatic products sorting technique and system based on machine vision | |
| Kılıç et al. | A classification system for beans using computer vision system and artificial neural networks | |
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN108287010B (en) | Crab multi-index grading device and method | |
| CN109598715B (en) | Material granularity online detection method based on machine vision | |
| CN101907453B (en) | Online measurement method and device of dimensions of massive agricultural products based on machine vision | |
| CN104256882B (en) | Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision | |
| US20140168411A1 (en) | Shrimp processing system and methods | |
| CN105009731B (en) | Corn seed investigating method and its system | |
| CN104198325B (en) | Stem ratio measuring method in pipe tobacco based on computer vision | |
| CN113145492A (en) | Visual grading method and grading production line for pear appearance quality | |
| CN107993203B (en) | Poultry carcass image grading method and grading system thereof | |
| CN113820325B (en) | Corn grain direct-harvest impurity-containing rate and breakage rate online detection system and method | |
| Roseleena et al. | Assessment of palm oil fresh fruit bunches using photogrammetric grading system. | |
| CN106370667A (en) | Visual detection apparatus and method for quality of corn kernel | |
| CN104056789A (en) | Carrot defect image quantitative detection method and carrot sorting apparatus | |
| WO1998014046A1 (en) | Method and apparatus for the quality assessment of seed | |
| JPS61107139A (en) | Apparatus for measuring grade of grain of rice | |
| Thinh et al. | Mango classification system based on machine vision and artificial intelligence | |
| CN114378002A (en) | Hericium erinaceus grading system and grading method based on machine vision | |
| Chao et al. | Design of a dual-camera system for poultry carcasses inspection | |
| CN113245222B (en) | Visual real-time detection and sorting system and sorting method for foreign matters in panax notoginseng | |
| CN115218790A (en) | Bar detection method, device and system | |
| WO2022041501A1 (en) | Frozen fish sorting device | |
| CN219460229U (en) | Full-automatic sorting system for quality grading and defective product removal of large yellow croaker |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181102 |
|
| RJ01 | Rejection of invention patent application after publication |