CN109540892A - Duck variety discriminating method and system - Google Patents
Duck variety discriminating method and system Download PDFInfo
- Publication number
- CN109540892A CN109540892A CN201811525723.8A CN201811525723A CN109540892A CN 109540892 A CN109540892 A CN 109540892A CN 201811525723 A CN201811525723 A CN 201811525723A CN 109540892 A CN109540892 A CN 109540892A
- Authority
- CN
- China
- Prior art keywords
- duck
- image
- black
- high spectrum
- spectrum image
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The embodiment of the invention provides a kind of duck variety discriminating method and systems, by obtaining high spectrum image of the every kind of duck in default wave band, and high spectrum image is handled, obtain the image texture characteristic of predeterminable area, the classification that every kind of duck is automatically determined out based on default disaggregated model overcomes traditional sensory evaluation and chemical measurement method human error is big, process is cumbersome disadvantage.Detect that speed is fast, save the cost compared with existing chemical detection method, it is possible to reduce labor intensity simultaneously improves production efficiency.
Description
Technical field
The present embodiments relate to processings of farm products and detection studying technological domain, reflect more particularly, to duck kind
Other method and system.
Background technique
The kind of duck generally may include meat type duck, egg type duck and dual-purpose type duck.Wherein meat type duck may include north
Capital duck, cherry valley duck, the high duck of Di, kind duck and TIAN FU MEAT DUCK etc..It is Beijing duck delicious meat, unique flavor, full of nutrition, it can be with
Production raw material as " Beijing roast duck ".Beijing duck subcutaneous fat depth, the intramuscular fat content of orthodox school are high, however many businessmans,
Raiser pretends to be Beijing duck in order to pursue economic interests, with the cherry valley duck of low cost, causes the distortion of roast duck raw material spoiled, both damaged
Consumer's interests have been done harm to, while also having compromised the good reputation of Beijing roast duck.
Presently, there are duck variety discriminating method mainly based on physico-chemical analysis, be aided with artificial sense evaluation.These are passed
System method the disadvantages of long, at high cost, low efficiency, needs do different disposal to different measurement samples in the prevalence of analysis time,
It is not suitable for the real-time identification of batch samples.Therefore existing to be badly in need of providing a kind of duck variety discriminating method and system, to right
Various ducks are quickly identified.
Summary of the invention
In order to overcome the problems referred above or it at least is partially solved the above problem, the embodiment of the invention provides a kind of duck product
Kind discrimination method and system.
In a first aspect, the embodiment of the invention provides a kind of duck variety discriminating methods, comprising:
High spectrum image of the every kind of duck in default wave band is obtained respectively, and the high spectrum image of every kind of duck is carried out
Black and white correction;
The image texture characteristic of every kind of duck predeterminable area in the high spectrum image after black and white corrects is obtained, and by every kind
The image texture characteristic of duck is input in default disaggregated model, and the classification of every kind of duck is exported by the default disaggregated model;
Wherein, the default disaggregated model is used as input by the image texture characteristic of duck sample, the duck sample
Classification is obtained as output training.
Second aspect, the embodiment of the invention provides a kind of duck Variety identification systems, comprising:
Image collection module, for obtaining high spectrum image of the every kind of duck in default wave band respectively, and to every kind of duck
The high spectrum image of meat carries out black and white correction;
Category determination module, for obtaining the image of every kind of duck predeterminable area in the high spectrum image after black and white corrects
Textural characteristics, and the image texture characteristic of every kind of duck is input in default disaggregated model, it is defeated by the default disaggregated model
The classification of every kind of duck out;
Wherein, the default disaggregated model is used as input by the image texture characteristic of duck sample, the duck sample
Classification is obtained as output training.
The third aspect, the embodiment of the invention provides a kind of electronic equipment, comprising:
At least one processor, at least one processor, communication interface and bus;Wherein,
The processor, memory, communication interface complete mutual communication by the bus;
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to refer to
It enables, to execute the duck variety discriminating method of first aspect offer.
Fourth aspect, the embodiment of the invention provides a kind of non-transient computer readable storage medium, the non-transient meter
Calculation machine readable storage medium storing program for executing stores computer instruction, and the computer instruction makes the computer execute the duck that first aspect provides
Meat variety discriminating method.
Duck variety discriminating method provided in an embodiment of the present invention and system, by obtaining every kind of duck in default wave band
High spectrum image, and high spectrum image is handled, obtains the image texture characteristic of predeterminable area, based on default classification mould
Type automatically determines out the classification of every kind of duck, overcomes that traditional sensory evaluation and chemical measurement method human error be big, process
Cumbersome disadvantage.Detect that speed is fast, save the cost compared with existing chemical detection method, it is possible to reduce labor intensity simultaneously improves
Production efficiency.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of duck variety discriminating method provided in an embodiment of the present invention;
Fig. 2 is the high spectrum image acquisition device used in a kind of duck variety discriminating method provided in an embodiment of the present invention
Structural schematic diagram;
Fig. 3 is a kind of structural schematic diagram of duck Variety identification system provided in an embodiment of the present invention;
Fig. 4 is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In the description of the embodiment of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right",
The orientation or positional relationship of the instructions such as "vertical", "horizontal", "inner", "outside" is to be based on the orientation or positional relationship shown in the drawings,
It is merely for convenience of the description embodiment of the present invention and simplifies description, rather than the device or element of indication or suggestion meaning must have
There is specific orientation, be constructed and operated in a specific orientation, therefore should not be understood as the limitation to the embodiment of the present invention.In addition,
Term " first ", " second ", " third " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
In the description of the embodiment of the present invention, it should be noted that unless otherwise clearly defined and limited, term " peace
Dress ", " connected ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integrally
Connection;It can be mechanical connection, be also possible to be electrically connected;Can be directly connected, can also indirectly connected through an intermediary,
It can be the connection inside two elements.For the ordinary skill in the art, above-mentioned art can be understood with concrete condition
The concrete meaning of language in embodiments of the present invention.
As shown in Figure 1, one embodiment of the invention provides a kind of duck variety discriminating method, comprising:
S1 obtains high spectrum image of the every kind of duck in default wave band respectively, and to the high spectrum image of every kind of duck
Carry out black and white correction;
S2 obtains the image texture characteristic of every kind of duck predeterminable area in the high spectrum image after black and white corrects, and will
The image texture characteristic of every kind of duck is input in default disaggregated model, and the class of every kind of duck is exported by the default disaggregated model
Not;
Wherein, the default disaggregated model is used as input by the image texture characteristic of duck sample, the duck sample
Classification is obtained as output training.
Specifically, the duck variety discriminating method provided in the embodiment of the present invention is mainly used for dividing a variety of ducks
Class determines the classification of every kind of duck.Executing subject in the embodiment of the present invention can be processor or computer etc..It can distinguish first
High spectrum image of the every kind of duck in default wave band is obtained, and black and white correction is carried out to the high spectrum image of every kind of duck.Its
In preset wave band be specifically as follows 400nm-1000nm visible light-near infrared band, high spectrum image can specifically pass through EO-1 hyperion
Imager obtains.Black and white correction is to instigate in high spectrum image each pixel value between 0-1, namely to high spectrum image
Carry out gray processing processing.Then the image texture for obtaining every kind of duck predeterminable area in the high spectrum image after black and white corrects is special
Sign, image texture characteristic here refer in the high spectrum image of predeterminable area for indicating the feature of duck grain distribution.
Every kind of duck in the high spectrum image after black and white corrects after the image texture characteristic of predeterminable area is being determined,
It is input in default disaggregated model, the classification of every kind of duck is exported by presetting disaggregated model.It wherein presets disaggregated model and is used for base
In the image texture characteristic of every kind of duck predeterminable area in the high spectrum image after black and white corrects, the class of every kind of duck is determined
Not, and then identification to every kind of duck in a variety of ducks is realized.Default disaggregated model is to be trained to obtain by duck sample,
Using the image texture characteristic of duck sample as input, the classification of duck sample is as output.
Duck sample particularly may be divided into training sample and verifying sample, and the classification of duck sample is it is known that and duck sample
Classification can include: Beijing duck, cherry valley duck, the high duck of Di, kind duck and TIAN FU MEAT DUCK etc..The duck sample of each classification has more
A, particular number can be set as needed, can also be determined as needed.Firstly the need of each duck sample of acquisition
High spectrum image in default wave band, and black and white correction is carried out to the high spectrum image of each duck sample, then determine
The image texture characteristic of each duck sample predeterminable area in the high spectrum image after black and white corrects.By each determining
Input of the image texture characteristic of training sample as default disaggregated model, the classification of each training sample are right as output
Default disaggregated model is trained, then by the image texture characteristic of each verifying sample as the defeated of default disaggregated model
Enter, the classification of each verifying sample as output, verify by the default disaggregated model obtained to training, repeats above-mentioned training
And verification process, until training terminates when default disaggregated model reaches default classification accuracy when verifying.
The duck variety discriminating method provided in the embodiment of the present invention, by obtaining height of the every kind of duck in default wave band
Spectrum picture, and high spectrum image is handled, the image texture characteristic of predeterminable area is obtained, certainly based on default disaggregated model
The dynamic classification for determining every kind of duck overcomes traditional sensory evaluation and chemical measurement method human error is big, process is cumbersome
The shortcomings that.Detect that speed is fast, save the cost compared with existing chemical detection method, it is possible to reduce labor intensity simultaneously improves production
Efficiency.
On the basis of the above embodiments, the duck variety discriminating method provided in the embodiment of the present invention, can be applied to
To the taxonomic history of Beijing duck and cherry valley duck.
Specifically, in the embodiment of the present invention when being trained to default disaggregated model, it can buy and reach from farm
List age in days (6-8 week old) Beijing duck and each 80 pieces of duck brisket of cherry valley duck, two kinds of duck briskets are solved under the conditions of 0-4 DEG C
Freeze for 24 hours, then be placed in room temperature 30min, and reject visible fat and connective tissue, every piece of duck brisket shaping is cut out into about 4cm × 2cm
The cuboid of × 1cm is as duck sample.Correspondingly, it when carrying out duck Variety identification using default disaggregated model, obtains respectively
High spectrum image of the every kind of duck brisket in default wave band is taken, and black and white correction is carried out to the high spectrum image of every kind of duck brisket;
Obtain the image texture characteristic of every kind of duck brisket predeterminable area in the high spectrum image after black and white corrects, and by every kind of duck brisket
Image texture characteristic be input in default disaggregated model, the classification of every kind of duck brisket is exported by the default disaggregated model.
On the basis of the above embodiments, the duck variety discriminating method provided in the embodiment of the present invention, it is described to obtain respectively
High spectrum image of the every kind of duck in default wave band is taken, is specifically included:
High spectrum image of the every kind of duck in default wave band is obtained respectively by high spectrum image acquisition device.
As shown in Fig. 2, the high spectrum image acquisition device used in the embodiment of the present invention includes: service band to be described pre-
If the camera lens 21 of wave band, diffusing reflection light source 22, hyperspectral imager 23, CCD camera 24, motorized precision translation stage 25 and camera bellows 26.Mirror
First 21, diffusing reflection light source 22, hyperspectral imager 23, CCD camera 24 and motorized precision translation stage 25 are arranged in camera bellows 26, electricity
The dynamic setting of translation stage 25 is successively set on electronic flat in 26 bottom of camera bellows, all ducks 27 along the translation direction of motorized precision translation stage 25
In moving stage 25;Diffusing reflection light source 22 is arranged on the side wall of camera bellows 26 by first support 28, and hyperspectral imager 23 passes through the
Two brackets 29 are vertically set on the top of motorized precision translation stage 25;Camera lens 21 is mounted on hyperspectral imager 23, CCD camera 24 with
Hyperspectral imager 23 connects.
Specifically, in the high spectrum image acquisition device provided in the embodiment of the present invention, locating for camera lens 21 and all ducks
The distance between plane can be 18.75cm, the translational velocity of motorized precision translation stage 25 can be 0.25cm/s.High light spectrum image-forming
The time for exposure of instrument 23 can be 19.8ms.Wherein, the time for exposure refers in order to which the light projection for issuing diffusing reflection light source 22 arrives
On the photosurface of photosensitive material in hyperspectral imager 23, shutter opens required duration, visual sense luminescent material every time
Sensitivity and diffusing reflection light source 22 to the illumination of photosurface depending on.The the time for exposure the long, the light that is projected on photosurface more
Situations that are more, being suitble to light condition poor, the time for exposure the short, and the light being projected on photosurface is fewer, is suitble to light condition
Relatively good situation.
It should be noted that every kind of duck is arranged when on motorized precision translation stage 25, the muscle fibre of every kind of duck can be made to hang down
Directly in the translation direction of motorized precision translation stage 25.
The available high spectrum image of hyperspectral imager 23 in the embodiment of the present invention obtains height in hyperspectral imager 23
It is input in CCD camera after spectrum picture, the optics shadow in high spectrum image for obtained hyperspectral imager 23 by CCD camera
As data conversion digital signal.
The high spectrum image acquisition device provided in the embodiment of the present invention needs to guarantee at work warm in locating environment
Degree and humidity do not change over time, and to prevent the quality to the high spectrum image got from having an impact, and then influence to the end
The identification result of duck.Temperature in environment locating for high spectrum image acquisition device can be made to be maintained at 23 in the embodiment of the present invention
Between DEG C -25 DEG C, humidity is maintained at relative constant value 60%.
On the basis of the above embodiments, the high spectrum image acquisition device provided in the embodiment of the present invention further includes external
High spectrum image acquisition device can be connect, by CCD by interface by external interface and data line with processor or computer
High spectrum image after camera processing is sent to processor or computer, and device or computer for processing are based on the high-spectrum received
As identifying to all ducks on motorized precision translation stage, the classification of every kind of duck is determined.
On the basis of the above embodiments, in the high spectrum image acquisition device provided in the embodiment of the present invention, further include
Objective table, objective table are arranged on motorized precision translation stage, and all ducks can be placed on objective table.Objective table can be set to
Black prevents objective table reflected light by mirror so that the light that diffusing reflection light source issues is absorbed when being radiated on objective table by objective table
Head is received and is transmitted in hyperspectral imager, is adversely affected to the classification results of duck.
On the basis of the above embodiments, the duck variety discriminating method provided in the embodiment of the present invention, it is described to every kind
The high spectrum image of duck carries out black and white correction, specifically includes:
Standard white plate image and all black picture are obtained, is based on the standard white plate image and all black picture, respectively
Black and white correction is carried out to the high spectrum image of every kind of duck.
Specifically, the black and white bearing calibration provided in the embodiment of the present invention specifically can be by following formula respectively to every kind
The high spectrum image of duck carries out black and white correction:
Wherein, I is the high spectrum image of every kind of duck after black and white correction, IingThe bloom of every kind of duck before being corrected for black and white
Spectrogram picture, IdarkFor all black picture, IwhiteFor the standard white plate image, DN is the bloom of every kind of duck before black and white corrects
Brightness maxima in spectrogram picture.
In the embodiment of the present invention, the specific value of DN can be 4096.It is every in high spectrum image after carrying out black and white correction
A pixel value is between 0-1.
On the basis of the above embodiments, the duck variety discriminating method provided in the embodiment of the present invention, it is described to obtain often
The image texture characteristic of kind duck predeterminable area in the high spectrum image after black and white corrects, specifically includes:
Determine the sliding side of the sliding window of pre-set dimension, the default step pitch of the sliding window and the sliding window
To;
Based on the sliding window, the default step pitch and the glide direction, determine that every kind of duck is corrected through black and white
It is used to indicate described image in the gray level co-occurrence matrixes of predeterminable area and the gray level co-occurrence matrixes in high spectrum image afterwards
The image texture characteristic parameter of textural characteristics.
Specifically, it can determine predeterminable area in the embodiment of the present invention by ENVI software first, can specifically use
Rectangle region domain method chooses the range of 1cm × 1cm in the high spectrum image after black and white corrects as predeterminable area, avoids connective group
It knits and bright spot.After determining predeterminable area, further the high spectrum image of predeterminable area can be pre-processed, to eliminate noise
Improve signal-to-noise ratio.Finally, being based on the sliding window, the default step pitch and the glide direction, gray scale symbiosis square is determined
For indicating the image texture characteristic parameter of image texture characteristic in battle array and gray level co-occurrence matrixes.
Image texture characteristic in the embodiment of the present invention refers to the feature for indicating duck grain distribution.In high-spectrum
The image texture characteristic that expression duck grain distribution is determined as in needs to carry out texture analysis to high spectrum image.The present invention
Image texture characteristic in embodiment is embodied by textural characteristics parameter, i.e. texture analysis is actually to calculate textural characteristics ginseng
Several specific values.
Firstly the need of the glide direction for determining the sliding window of a pre-set dimension, default step pitch and sliding window.This
Pre-set dimension can be set to 1mm × 1mm in inventive embodiments, default step pitch can be set to 1mm.The sliding of sliding window
Direction, which can according to need, to be chosen, it should be noted that is obtained due to carrying out texture analysis according to different glide directions
Textural characteristics parameter it is not identical, in order to parameter have rotational invariance, to 0 °, 45 °, 90 ° and 135 ° of 4 glide directions
The value of upper calculated textural characteristics parameter is averaged, and obtained average value is as final textural characteristics parameter.
On the basis of the above embodiments, the duck variety discriminating method provided in the embodiment of the present invention, described image line
Reason feature specifically includes: the mean value of all pixels value, variance, homogeney, contrast, entropy, second order in the predeterminable area
One of square and correlation are a variety of.
It specifically, can be from the mean value of all pixels value, variance, homogeney, contrast, entropy in the embodiment of the present invention
It is chosen in this 8 textural characteristics parameters of value, second moment and correlation one or more for characterizing the line between every kind of duck
Distributional difference is managed, and then realizes classification.
As shown in figure 3, providing a kind of duck Variety identification system on the basis of the above embodiments, in the embodiment of the present invention
System, comprising: image collection module 31 and category determination module 32.
Wherein, image collection module 31 is used to obtain high spectrum image of the every kind of duck in default wave band respectively, and right
The high spectrum image of every kind of duck carries out black and white correction;
Category determination module 32 is used to obtain the figure of every kind of duck predeterminable area in the high spectrum image after black and white corrects
As textural characteristics, and the image texture characteristic of every kind of duck is input in default disaggregated model, by the default disaggregated model
Export the classification of every kind of duck;
Wherein, the default disaggregated model is used as input by the image texture characteristic of duck sample, the duck sample
Classification is obtained as output training.
Specifically, the effect of each module and above method class in the duck Variety identification system provided in the embodiment of the present invention
The process flow of each step is one-to-one in embodiment, and the effect reached is also consistent, to this in the embodiment of the present invention
It is not especially limited.
As shown in figure 4, providing a kind of electronic equipment in the embodiment of the present invention, electronic equipment includes: processor
(processor) 401, memory (memory) 402, communication interface (Communications Interface) 403 and bus
404;Wherein,
The processor 401, memory 402, communication interface 403 complete mutual communication by bus 404.It is described to deposit
Reservoir 402 is stored with the program instruction that can be executed by the processor 401, and processor 401 is used to call the journey in memory 402
Sequence instruction, to execute method provided by above-mentioned each method embodiment, for example, S1 obtains every kind of duck default respectively
High spectrum image in wave band, and black and white correction is carried out to the high spectrum image of every kind of duck;S2 obtains every kind of duck through black and white
The image texture characteristic of predeterminable area in high spectrum image after correction, and the image texture characteristic of every kind of duck is input to pre-
If in disaggregated model, the classification of every kind of duck is exported by the default disaggregated model.
Logical order in memory 402 can be realized by way of SFU software functional unit and as independent product pin
It sells or in use, can store in a computer readable storage medium.Based on this understanding, technical side of the invention
Substantially the part of the part that contributes to existing technology or the technical solution can be with the shape of software product in other words for case
Formula embodies, which is stored in a storage medium, including some instructions are used so that a calculating
Machine equipment (can be personal computer, server or the network equipment etc.) executes each embodiment the method for the present invention
All or part of the steps.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (Read-Only Memory,
ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. are various can store program
The medium of code.
On the basis of the above embodiments, a kind of non-transient computer readable storage medium is provided in the embodiment of the present invention
Matter, the non-transient computer readable storage medium store computer instruction, and the computer instruction executes the computer
Method provided by above-mentioned each method embodiment, for example, S1 obtains EO-1 hyperion of the every kind of duck in default wave band respectively
Image, and black and white correction is carried out to the high spectrum image of every kind of duck;S2 obtains EO-1 hyperion of the every kind of duck after black and white corrects
The image texture characteristic of predeterminable area in image, and the image texture characteristic of every kind of duck is input in default disaggregated model,
The classification of every kind of duck is exported by the default disaggregated model.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of duck variety discriminating method characterized by comprising
High spectrum image of the every kind of duck in default wave band is obtained respectively, and black and white is carried out to the high spectrum image of every kind of duck
Correction;
Obtain the image texture characteristic of every kind of duck predeterminable area in the high spectrum image after black and white corrects, and by every kind of duck
Image texture characteristic be input in default disaggregated model, the classification of every kind of duck is exported by the default disaggregated model;
Wherein, the default disaggregated model is by the image texture characteristic of duck sample as input, the classification of the duck sample
It is obtained as output training.
2. duck variety discriminating method according to claim 1, which is characterized in that described to obtain every kind of duck respectively pre-
If the high spectrum image in wave band, specifically includes:
High spectrum image of the every kind of duck in default wave band is obtained respectively by high spectrum image acquisition device;
The high spectrum image acquisition device includes: camera lens, the diffusing reflection light source, EO-1 hyperion that service band is the default wave band
Imager, CCD camera, motorized precision translation stage and camera bellows;
The camera lens, the diffusing reflection light source, the hyperspectral imager, the CCD camera and the motorized precision translation stage are equal
It is arranged in the camera bellows, the motorized precision translation stage is arranged in the camera bellows bottom, and all ducks are along the motorized precision translation stage
Translation direction is successively set on the motorized precision translation stage;The camera bellows is arranged in by first support in the diffusing reflection light source
On side wall, the hyperspectral imager is vertically set on the top of the motorized precision translation stage by second support;The camera lens peace
On the hyperspectral imager, the CCD camera is connect with the hyperspectral imager.
3. duck variety discriminating method according to claim 1, which is characterized in that the high-spectrum to every kind of duck
As progress black and white correction, specifically include:
Standard white plate image and all black picture are obtained, the standard white plate image and all black picture are based on, respectively to every
The high spectrum image of kind duck carries out black and white correction.
4. duck variety discriminating method according to claim 3, which is characterized in that described to be based on the standard white plate image
With all black picture, black and white correction is carried out to the high spectrum image of every kind of duck respectively, is specifically included:
Black and white correction is carried out to the high spectrum image of every kind of duck respectively by following formula:
Wherein, I is the high spectrum image of every kind of duck after black and white correction, IingThe high-spectrum of every kind of duck before being corrected for black and white
Picture, IdarkFor all black picture, IwhiteFor the standard white plate image, DN is the high-spectrum of every kind of duck before black and white corrects
Brightness maxima as in.
5. duck variety discriminating method according to claim 1, which is characterized in that every kind of duck of the acquisition is through black and white school
The image texture characteristic of predeterminable area in high spectrum image after just, specifically includes:
Determine the glide direction of the sliding window of pre-set dimension, the default step pitch of the sliding window and the sliding window;
Based on the sliding window, the default step pitch and the glide direction, determine every kind of duck after black and white corrects
It is used to indicate described image texture in the gray level co-occurrence matrixes of predeterminable area and the gray level co-occurrence matrixes in high spectrum image
The image texture characteristic parameter of feature.
6. duck variety discriminating method according to claim 5, which is characterized in that described image textural characteristics parameter is specific
It include: the mean value of all pixels value, variance, homogeney, contrast, entropy, second moment and correlation in the predeterminable area
One of property is a variety of.
7. duck variety discriminating method according to claim 1 to 6, which is characterized in that the predeterminable area tool
Body is pre-set dimension and the rectangular area without connective tissue and bright spot.
8. a kind of duck Variety identification system characterized by comprising
Image collection module, for obtaining high spectrum image of the every kind of duck in default wave band respectively, and to every kind of duck
High spectrum image carries out black and white correction;
Category determination module, for obtaining the image texture of every kind of duck predeterminable area in the high spectrum image after black and white corrects
Feature, and the image texture characteristic of every kind of duck is input in default disaggregated model, it is exported by the default disaggregated model every
The classification of kind duck;
Wherein, the default disaggregated model is by the image texture characteristic of duck sample as input, the classification of the duck sample
It is obtained as output training.
9. a kind of electronic equipment characterized by comprising
At least one processor, at least one processor, communication interface and bus;Wherein,
The processor, memory, communication interface complete mutual communication by the bus;
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program instruction,
To execute such as duck variety discriminating method of any of claims 1-7.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute such as duck product of any of claims 1-7
Kind discrimination method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811525723.8A CN109540892A (en) | 2018-12-13 | 2018-12-13 | Duck variety discriminating method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811525723.8A CN109540892A (en) | 2018-12-13 | 2018-12-13 | Duck variety discriminating method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109540892A true CN109540892A (en) | 2019-03-29 |
Family
ID=65854785
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811525723.8A Pending CN109540892A (en) | 2018-12-13 | 2018-12-13 | Duck variety discriminating method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109540892A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110501310A (en) * | 2019-05-07 | 2019-11-26 | 华南理工大学 | A kind of food detection method based on non-model optical correction EO-1 hyperion |
CN113207935A (en) * | 2021-03-03 | 2021-08-06 | 吴燕 | Type-analysis-based adaptive machining system and method |
CN113516193A (en) * | 2021-07-19 | 2021-10-19 | 中国农业大学 | Red date defect identification and classification method and device based on image processing |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1995987A (en) * | 2007-02-08 | 2007-07-11 | 江苏大学 | Non-destructive detection method and device for agricultural and animal products based on hyperspectral image technology |
CN103063585A (en) * | 2013-01-05 | 2013-04-24 | 石河子大学 | Rapid nondestructive lemon and fruit maturity testing device and testing system establishment method |
-
2018
- 2018-12-13 CN CN201811525723.8A patent/CN109540892A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1995987A (en) * | 2007-02-08 | 2007-07-11 | 江苏大学 | Non-destructive detection method and device for agricultural and animal products based on hyperspectral image technology |
CN103063585A (en) * | 2013-01-05 | 2013-04-24 | 石河子大学 | Rapid nondestructive lemon and fruit maturity testing device and testing system establishment method |
Non-Patent Citations (2)
Title |
---|
冯建辉等: "基于灰度共生矩阵提取纹理特征图像的研究", 《北京测绘》 * |
黄祥林等: "《图像检索原理与实践》", 30 June 2014, 中国传媒大学出版社 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110501310A (en) * | 2019-05-07 | 2019-11-26 | 华南理工大学 | A kind of food detection method based on non-model optical correction EO-1 hyperion |
CN110501310B (en) * | 2019-05-07 | 2020-12-22 | 华南理工大学 | Food detection method based on non-model optical correction hyperspectrum |
CN113207935A (en) * | 2021-03-03 | 2021-08-06 | 吴燕 | Type-analysis-based adaptive machining system and method |
CN113516193A (en) * | 2021-07-19 | 2021-10-19 | 中国农业大学 | Red date defect identification and classification method and device based on image processing |
CN113516193B (en) * | 2021-07-19 | 2024-03-01 | 中国农业大学 | Image processing-based red date defect identification and classification method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111308448B (en) | External parameter determining method and device for image acquisition equipment and radar | |
US20240110877A1 (en) | System and method of unique identifying a gemstone | |
CN109540892A (en) | Duck variety discriminating method and system | |
CN107869954B (en) | Binocular vision volume weight measurement system and implementation method thereof | |
CN104535588B (en) | Egg freshness nondestructive testing system based on Android system and egg freshness nondestructive testing method | |
CN109492714A (en) | Image processing apparatus and its method | |
CN110766656B (en) | Method, device, equipment and storage medium for screening fundus macular region abnormality | |
CN107816943B (en) | Logistics box volume and weight measurement system and implementation method thereof | |
US10796141B1 (en) | Systems and methods for capturing and processing images of animals for species identification | |
CN112232978B (en) | Aquatic product length and weight detection method, terminal equipment and storage medium | |
CN113608378B (en) | Full-automatic defect detection method and system based on LCD (liquid crystal display) process | |
CN111122590B (en) | Ceramic surface defect detection device and detection method | |
CN113533256B (en) | Method, device and equipment for determining spectral reflectivity | |
CN108960344A (en) | Difference detecting method, device and the terminal device of cultural relic images | |
CN113176270B (en) | Dimming method, device and equipment | |
CN104198325A (en) | Method for measuring ratio of cut stem to cut tobacco based on computer vision | |
CN107576600B (en) | Quick detection method for matcha granularity grade | |
CN113409379B (en) | Method, device and equipment for determining spectral reflectivity | |
CN112800888B (en) | Target reporting method and device based on image recognition | |
CN113008380B (en) | Intelligent AI body temperature early warning method, system and storage medium | |
CN111879791B (en) | Machine vision system and method for enhancing raised features on pattern surface | |
CN107220972B (en) | A kind of quality of poultry eggs discrimination method based on infrared image | |
CN207181307U (en) | A kind of stereoscopic image acquisition device | |
CN116758170B (en) | Multi-camera rapid calibration method for livestock and poultry phenotype 3D reconstruction and storage medium | |
CN211509130U (en) | Image acquisition device, equipment and system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |