CN102564964A - Spectral image-based meat quality visual non-contact detection method - Google Patents
Spectral image-based meat quality visual non-contact detection method Download PDFInfo
- Publication number
- CN102564964A CN102564964A CN2011104477942A CN201110447794A CN102564964A CN 102564964 A CN102564964 A CN 102564964A CN 2011104477942 A CN2011104477942 A CN 2011104477942A CN 201110447794 A CN201110447794 A CN 201110447794A CN 102564964 A CN102564964 A CN 102564964A
- Authority
- CN
- China
- Prior art keywords
- meat
- spectrum
- spectrum picture
- index
- sample
- 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
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a spectral image-based meat quality visual non-contact detection method. By means of spatial distribution information and spectral characteristic information which are contained in a spectral image and reflect the characteristics of an object to be detected, multiple indexes of meat quality (such as water content, water activity, volatile basic nitrogen, meat color, microorganism counts, acid value and pH value) are respectively or comprehensively evaluated, and evaluation results are given in an image mode according to spatial distribution conditions of specific indexes in the object to be detected. The method can be used for quick and non-contact inspection of meat production, processing, storage, transportation and marketing links, inspection results are accurate and objective, and the expression mode is intuitive, so that a guarantee means for supervising the production and marketing quality safety of meat is provided.
Description
Technical field
The present invention relates to a kind of method that detects to meat quality; Refer in particular to based on spectrum picture meat is carried out non-contact detection; Testing result adopts visual means to present the method for relevant quality in the distributed degrees situation of measured surface, belongs to food object technical field of nondestructive testing.
Background technology
China is the maximum economy of pork production and consumption, and the volume of production and marketing of pork occupies the No. 1 in the world throughout the year.But the measuring means to meat still rests on reduced levels; There are deficiencies such as subjectivity is big, index is single, length consuming time in traditional organoleptic detection, physics and chemistry and microorganism detection; The rig-site utilization inconvenience is so limited in the detection to meat of storage, transportation and sales section.
Emerging detection means has been as having opened up new approach based on the rise of detection methods such as Electronic Nose, conductivity, yellowish pink for the meat fast detecting, but these technology receive in varying degrees sample is had the restriction that destructiveness, testing result and traditional detection index receive factors such as the sample individual difference influences significantly.The harmless quick means of the multinomial index of quality of meat being carried out comprehensive detection still are in miss status at present.
Spectrum detection technique can realize that with it noncontact mode carries out inside quality to detected object and detect, and is applied in the fast detecting of agricultural and animal products.For example the averaged spectrum data of measurand are outputed to spectrum and carry out spectral detection through condenser lens and optical fiber; These class methods belong to " point " and detect, or " average " detection, only to make Quality Detection according to spectral space information, so owing to do not have spatial information can't make the detection of the space distribution degree of the index of quality.
Development along with hardware technology; Spectrum picture checkout equipment with spatial resolving power also begins to be applied in the Quality Detection of agricultural and animal products; But at present the spectrum picture The Application of Technology is not given full play to the advantage of its spatial resolving power, still continued to use traditional spectral detection thinking and adopt " average " to detect the index of quality detected value that obtains imaginary uniformity measurand.
Traditional Machine Vision Detection barment tag to measurand in visible-range detects, and possesses to detect the characteristic that index is described in the space distribution situation, but shows and can't realize owing to receiving the imaging spectral wave band for inside quality.
Summary of the invention
In order to solve the problem that exists in the prior art; The present invention proposes the visual non-contact detection method of a kind of meat quality based on spectrum picture; Space distribution information and spectral signature information by the reflection characteristics of objects to be measured that is comprised in the spectrum picture; A plurality of indexs (water percentage, water activity, VBN content, yellowish pink, microorganism count, acid value, pH value) to meat quality are distinguished or comprehensive assessment, and assessment result provides according to the mode of the space distribution situation of specific targets in measured target with image.Concrete steps of the present invention are following:
Purchasing has certain representational sample storehouse, the meat appearance in the sample storehouse should reflect wait to set up under the pairing storage condition of quality prediction model the index of quality to be measured all maybe distribution range, and sample index of quality degree distribution probability density is even as far as possible.
The sample storehouse is divided into two equal portions of mutual correspondence, aly uses word bank as traditional meat quality check, the parallel with it sample word bank of another part is used as the spectrum picture collection.Two meat appearance in every group parallel kind should be accomplished unanimity in each side such as meat storage condition, starting condition, index degree to be measured as far as possible.
Traditional detection obtains traditional Quality Detection index storehouse with the training sample word bank through traditional sense organ, physics and chemistry and microorganism detection.
The high spectrum image collection obtains spectrum picture with the sample in the parallel word bank of training meat through the spectrum picture acquisition system and deposits the spectrum picture storehouse in.Utilize the spectrum picture pre-service that the spectrum picture in the spectrum picture storehouse is carried out pre-service; And extract through effective surveyed area the effective surveyed area in the meat parallel samples to be measured is extracted, extract operation through effective surveyed area spectrum subsequently and the representative spectrum of effective coverage is extracted deposit library of spectra in.
The knowledge base that traditional detection index storehouse and library of spectra are formed comprises the spectroscopic data of the right traditional detection index result of mutual parallel samples one to one and effective surveyed area; Obtain the spectral prediction model of traditional detection index through the spectrum forecast modeling of traditional detection index; Can obtain the spectral prediction model of a plurality of different traditional detection indexs according to the different index of quality, different sample object type and different storage condition; These models are stored in the traditional detection index spectral prediction model storehouse, accomplish the foundation of model bank;
Gather the spectrum picture of tested meat sample; Extract the effective surveyed area of spectrum picture that obtains measurand through spectrum pre-service and effective surveyed area; Corresponding forecast model is done visual detection to effective surveyed area of tested meat object in the traditional detection index spectral prediction model storehouse that utilization has been set up, finally obtains the visual test result of meat quality index.
1. set up traditional detection index spectral prediction model storehouse
Choose the sample of certain population of detected object composition, position, storage mode and environment under object population to be measured, position, storage mode and the environment, the distribution range of the subject object qualitative character in the sample should cover intends the whole of sensing range.The qualitative character overall degree evenly distributes in sample as far as possible, and promptly the number of objects on each quality level is consistent as far as possible in the sample.
A plurality of samples are formed the sample storehouse, with the situation of detected object under reflection different population, position, storage mode and the environment.
Each sample in the sample storehouse is divided into two parts that quantity equates, and a for training the meat sample, another part is training meat parallel samples.Training meat sample obtains the traditional detection calibration value through traditional sense organ, physics and chemistry and microorganism detection, is stored in the traditional detection index storehouse; Training meat parallel samples through spectra collection, obtain spectrum picture and be stored in the spectrum picture storehouse, spectrum picture through the spectrum picture pre-service, effectively surveyed area extracts, effectively surveyed area spectrum extracts and obtains training the spectral information of meat parallel samples to be stored in the library of spectra; Traditional detection index storehouse and library of spectra are formed knowledge base jointly.The spectrum forecast modeling of knowledge base being carried out the traditional detection index obtains traditional detection index spectral prediction model, is stored in the traditional detection index spectral prediction model storehouse carrying out the spectral prediction models that the spectrum forecast modeling obtains many cover traditional detection indexs to the data of multiple traditional detection index or storage condition in the knowledge base.
2. carry out visual detection
To tested meat object carry out spectrum picture collection, spectrum picture pre-service, effectively surveyed area extracts the spectrum picture information of the effective surveyed area that obtains tested meat object, according to carrying out the visual test result that the visual detection of meat spectrum picture finally obtains the meat quality index with the spectral prediction model of the corresponding population of measurand, position, storage mode and environment in the traditional detection index spectral prediction model storehouse.
3. visual testing process
Comprise showing on the tested meat object index of quality of each subregion in the effective coverage, with reflect the index of quality on tested meat object the space distribution situation, display mode can adopt, but is not limited to pseudo-color or stereo data display packing.Show the granule size of subregion, promptly the spatial discrimination yardstick is regulated according to index characteristic distributions, user and equipment needs.The upper limit that this resolution yardstick is regulated is the measurand spectrum picture to be carried out the index of quality with the sub-pix yardstick detect and demonstration; The lower limit that this resolution yardstick is regulated is overall meat sample matter index to be carried out as a sub-domain in the effective coverage of whole measurand spectrum picture detect and demonstration, and the present invention's this moment is in minimum mode of operation.
4. effectively surveyed area extracts operation
Comprise spectrum picture is handled, therefrom extract effective surveyed area, get rid of irrelevant or inactive area in the spectrum picture.Extraneous areas refers to detect the incoherent meat of index zone with certain.For example, but be not limited to, background area and most of the detection between the index have nothing to do; Fat region and VBN content's index are irrelevant, because the latter is only to muscle region.Thereby inactive area refer to a certain detection index relevant range in cause the local invalid in certain coherent detection zone owing to certain or multiple reason cause some part quality of spectrum picture surveyed area to be lower than the subsequent treatment desired level.For example; But be not limited to, the part of certain muscle region in the meat appearance receives light source and imaging system relative angle and surperficial grease and moisture and in spectrum picture, demonstrates high reflective solar flare, and the spectrum picture at this place does not meet the imaging mode of intending; For example; But be not limited to, the surface diffuse reflectance image-forming condition is so belong to inactive area.
5. effectively surveyed area spectrum extracts operation
Comprise according to spectrum picture reaching the effective coverage that wherein extracts, obtain the spectral signature that the one or more representative curve of spectrum reflects effective coverage in this spectrum picture.Representational curve of spectrum extracting mode can but be not limited to and ask for this regional spectrum average curve, or spectrum intermediate value curve, or spectrum maximal value, minimum value and average curve, or average curve and average plus-minus standard deviation curve.
6. the spectrum forecast modeling of traditional detection index operation
Carry out the spectrum pre-service earlier: for example, but be not limited to, utilize the operations such as standardized normal distribution processing, spectrum smothing filtering and difference differentiate of spectroscopic data to improve the spectral space signal to noise ratio (S/N ratio).
Through the combination of offset minimum binary, multiple linear regression or offset minimum binary and multiple linear regression analysis method spectral image data is carried out feature selecting and feature extraction then and set up spectroscopic data and traditional index between regression model.
Beneficial effect
Present testing result with visual means, reflection directly perceived detects the space distribution situation of the degree difference of index on the measurand detection faces.The expression way that reflects whole object than traditional single numerical value is more near the heteropical actual conditions of meat interior tissue composition.
The present invention can carry out fast the meat object, can't harm, non-contact detecting, and the comprehensive detection result of meat quality individual event or many index is provided.Break through meat quality tradition sense organ, physics and chemistry and the limitation of microorganism detection aspect subjectivity, rapidity and non-destructive.
Detect as the basis with multispectral image, this checkout equipment carries out Quality Detection according to the caused photonic absorption change of frequency of the internal component difference of meat, and evaluation result is objective.
To be detected with pick-up unit between do not contact, sample is not had destructiveness, belong to Non-Destructive Testing.
Detection need not pre-treatment, simplifies the operation, and saves time.
A surface sweeping can obtain multinomial detection index, meat quality is detected comprehensively many index make accurate evaluation.
Description of drawings
Fig. 1 is based on the visual non-contact detection method block diagram of the meat quality of spectrum picture.
Embodiment
The visual non-contact detection method of a kind of meat quality based on spectrum picture, step comprises:
1) sets up traditional detection index spectral prediction model storehouse;
2) meat object to be detected is carried out the spectrum picture collection;
3) to step 2) spectrum picture that obtains carries out pre-service;
4) spectrum picture that step 3) is obtained extracts the effective surveyed area in the spectrum picture;
5) utilize corresponding traditional detection index spectral prediction model in the model bank that step 1) sets up, effective surveyed area of tested meat object is done visual detection, finally obtain the visual test result of meat quality index;
In the said step 1), the establishment step in traditional detection index spectral prediction model storehouse is following:
101) set up the sample storehouse:
Choose the detected object under object population to be measured, position, storage mode and the environment, form the sample of certain population, position, storage mode and environment;
A plurality of samples are formed the sample storehouse, with the situation of detected object under reflection different population, position, storage mode and the environment;
Each sample in the sample storehouse is divided into two parts that quantity equates, and a for training the meat sample, another part is training meat parallel samples; Two types of samples are formed the sample storehouse;
102) set up knowledge base,
Said training meat sample is that meat obtains the traditional detection calibration value through traditional sense organ, physics and chemistry and microorganism detection, is stored in the traditional detection index storehouse; Training meat parallel samples is meat process spectra collection, obtains spectrum picture, is stored in the spectrum picture storehouse;
Spectrum picture in the spectrum picture storehouse obtains training the spectral information of meat parallel samples to be stored in the library of spectra through spectrum picture pre-service, effectively surveyed area extraction and effectively surveyed area spectrum extraction;
Traditional detection index storehouse and library of spectra are formed knowledge base jointly;
103) set up traditional detection index spectral prediction model storehouse
To carrying out the spectrum forecast modeling to the data of various traditional detection indexs or storage condition in the knowledge base, obtain the spectral prediction model of corresponding many covers traditional detection index, these models are stored in the traditional detection index spectral prediction model storehouse.
Specifically; The modeling method of spectral prediction model can be to utilize multivariate statistics homing method, partial least-square regression method, cluster intelligence homing method or Artificial Neural Network that the corresponding data collection in traditional detection index storehouse and the library of spectra is set up spectral prediction model.
In the said step 1), the distribution range of the subject object qualitative character in the sample covers intends the whole of sensing range; The qualitative character overall degree evenly distributes in sample, and promptly the number of objects on each quality level is consistent in the sample.
The preprocess method of spectrum picture is to utilize standardized normal distribution processing, spectrum smothing filtering and the difference differentiate operation of spectroscopic data to improve the spectral space signal to noise ratio (S/N ratio) earlier; Then through offset minimum binary perhaps, the combination of multiple linear regression or offset minimum binary and multiple linear regression analysis method, spectral image data is carried out feature selecting and feature extraction, and sets up the regression model between spectroscopic data and the traditional index.
The method of carrying out effective surveyed area extraction is:
According to measured target and gather between the background, the difference of characteristics such as the brightness in certain or some characteristic wave bands images of effective coverage and inactive area, area, form; Spectrum picture is carried out image segmentation; Therefrom extract effective surveyed area, get rid of extraneous areas and inactive area in the spectrum picture.Extraneous areas refers to detect the incoherent meat of index zone with certain; Inactive area refer to a certain detection index relevant range in, cause the local invalid in certain coherent detection zone thereby some part quality of spectrum picture surveyed area is lower than the subsequent treatment desired level.Cause quality to be lower than the reason of subsequent treatment desired level; Be since the spectrum picture of input this in local because external factor such as noise, environmental disturbances; Or in the spectrum picture processing procedure because some operator that adopts (as at target and background border place execution mean filter etc.), cause the decay of the image local quality of data.
Reach the effective coverage that wherein extracts according to spectrum picture, obtain the spectral signature that the one or more representative curve of spectrum reflects effective coverage in this spectrum picture; Representational curve of spectrum extracting mode comprises asks for this regional spectrum average curve, or spectrum intermediate value curve, or spectrum maximal value, minimum value and average curve, or average curve and average plus-minus standard deviation curve.
In the said step 3),
Show on the tested meat object index of quality of each subregion in the effective coverage, with the space distribution situation of the reflection index of quality on tested meat object;
The granule size that shows subregion is the spatial discrimination yardstick, regulates according to index characteristic distributions, user and equipment needs;
The upper limit that this resolution yardstick is regulated is the measurand spectrum picture to be carried out the index of quality with the sub-pix yardstick detect and demonstration;
The lower limit that this resolution yardstick is regulated is overall meat sample matter index to be carried out as a sub-domain in the effective coverage of whole measurand spectrum picture detect and demonstration, and this moment, this method was in minimum mode of operation.
The index of quality of each subregion in the effective coverage on the tested meat object of said demonstration, its display mode is pseudo-color or stereo data display packing.
Said spectrum picture is to possess several images to a hundreds of continuous or discontinuous wave band spectral information, and the spatial information and the spectral information of reflection measurand comprise multispectral image and high spectrum image.
Specify the present invention below in conjunction with a kind of embodiment and accompanying drawing, but embodiment of the present invention is not limited in this kind embodiment.
Visual detection index: VBN content.
Visual detected object, population: pork; Position: the not logical ridge section of place to go skin and back fat; Storage condition: 4 ℃ of storages of cold fresh meat; Terms of packing: PE seal package.
The logical ridge section from 10 pigs of batch production is together chosen in detection, gets rid of PSE and DFD meat when noting choosing, and is divided into training sample and trains parallel samples.Two are included into training sample and training parallel samples respectively about the same tangent plane of same logical ridge, are being consistent with training sample aspect the starting condition to guarantee parallel samples.All sample standard deviations adopt packing, the storing temperature of unified specification identical with condition, and are consistent with the parallel samples storage condition to guarantee training sample.
Took out one group of training sample and the parallel samples of every pig in per 24 hours, gather the spectrum picture of training sample, and with the triumphant formula nitriding of semimicro according to GB GB/T5009.44---the VBN numerical value of 1996 collection parallel sampleses.Gathered 10 groups of meat appearance in per 24 hours, meat appearance is only used once, and each the collection with physics and chemistry detection back destroyed meat appearance.After 14 days collections and physics and chemistry detection, obtain the spectrum picture storehouse that the logical ridge of these 10 pigs is cut into slices under same terms of packing, identical storing temperature changed with the holding time, and the traditional detection index storehouse of corresponding parallel meat appearance.
Image in the spectrum picture storehouse obtain through the spectrum picture pre-service, after effectively surveyed area extracts, effectively surveyed area spectrum extracts the logical ridge section of these 10 pigs under same terms of packing, identical storing temperature is with effective surveyed area spectrum that the holding time changes, and it is stored into library of spectra.
Employed spectrum picture preprocessing process comprises: reject the low signal-to-noise ratio wave band, carry out image noise reduction, carry out background removal through image segmentation and only keep meat appearance part in the image.
Effectively the surveyed area leaching process is little with fat and pork skin regional relation because the VBN content's index reflects that mainly protein decomposites the putrescine total amount in the muscle decay process, so effective surveyed area is the muscle region in the meat appearance in this detects.Find that through the artificial light analysis of spectrum muscle and fat, pork skin have notable difference at the absorption peak at 575nm place,, obtain the muscle region of tested meat appearance so the pretreated meat appearance spectrum picture of process is carried out Threshold Segmentation according to the height of 575nm place absorption peak.After adopting 5 * 5 mean filter methods to carry out the operation of spatial filtering noise reduction, for guaranteeing the quality of effective coverage marginal information, it is as the effective coverage behind 5 the erosion operation that muscle region is carried out radius.
Employed spectrum leaching process comprises: ask for the spectrum average in effective surveyed area, and carry out necessary noise reduction, adopt 3 smothing filtering noise reductions in this example.Carry out standardization at last and obtain effective surveyed area spectrum.
By the knowledge base that the spectroscopic data in effective surveyed area in total volatile basic nitrogen content's index in the traditional detection index storehouse and the pairing library of spectra thereof is formed, set up total volatile basic nitrogen content prediction model A through partial least-squares regression method.Total volatile basic nitrogen is contained numerical quantity and spectroscopic data differential data set up total volatile basic nitrogen content prediction Model B through partial least-squares regression method.Adopt leaving-one method that forecast model A and forecast model B are carried out modelling verification respectively, get wherein prediction effect preferably model be stored in the traditional detection index spectral prediction model storehouse as total volatile basic nitrogen spectrum prediction work model.
Gather tested meat object spectrum picture after the spectrum picture pre-service, concrete steps when setting up the spectrum picture storehouse used step with.After effectively surveyed area extracts, used step obtained the spectrum picture of the effective surveyed area of measurand together when concrete steps were set up library of spectra together, and it is carried out the visual detection of meat spectrum picture, and its concrete steps are:
At first image-region is carried out 3 level and smooth spectral filterings; Adopt when setting up the spectral prediction model storehouse the spectral filtering identical parameters; The total volatile basic nitrogen spectrum prediction work model of transferring then in the traditional detection index spectral prediction model storehouse is predicted the spectrum predicted value that obtains the total volatile basic nitrogen of effective picture element in the effective surveyed area of measurand, and adopts pseudo-color to predict the outcome with the image mode demonstration.
Claims (7)
1. visual non-contact detection method of the meat quality based on spectrum picture is characterized in that step comprises:
1) sets up traditional detection index spectral prediction model storehouse;
2) meat object to be detected is carried out the spectrum picture collection;
3) to step 2) spectrum picture that obtains carries out pre-service;
4) spectrum picture that step 3) is obtained extracts the effective surveyed area in the spectrum picture;
5) utilize corresponding traditional detection index spectral prediction model in the model bank that step 1) sets up, effective surveyed area of tested meat object is done visual detection, finally obtain the visual test result of meat quality index;
In the said step 1), the establishment step in traditional detection index spectral prediction model storehouse is following:
101) set up the sample storehouse:
Choose the detected object under object population to be measured, position, storage mode and the environment, form the sample of certain population, position, storage mode and environment;
A plurality of samples are formed the sample storehouse, with the situation of detected object under reflection different population, position, storage mode and the environment;
Each sample in the sample storehouse is divided into two parts that quantity equates, and a for training the meat sample, another part is training meat parallel samples; Two types of samples are formed the sample storehouse;
102) set up knowledge base,
Said training meat sample is that meat obtains the traditional detection calibration value through traditional sense organ, physics and chemistry and microorganism detection, is stored in the traditional detection index storehouse; Training meat parallel samples is meat process spectra collection, obtains spectrum picture, is stored in the spectrum picture storehouse;
Spectrum picture in the spectrum picture storehouse obtains training the spectral information of meat parallel samples to be stored in the library of spectra through spectrum picture pre-service, effectively surveyed area extraction and effectively surveyed area spectrum extraction;
Traditional detection index storehouse and library of spectra are formed knowledge base jointly;
103) set up traditional detection index spectral prediction model storehouse,
To carrying out the spectrum forecast modeling to the data of various traditional detection indexs or storage condition in the knowledge base, obtain the spectral prediction model of corresponding many covers traditional detection index, these models are stored in the traditional detection index spectral prediction model storehouse.
2. the visual non-contact detection method of the meat quality based on spectrum picture according to claim 1 is characterized in that: characteristic is in the said step 1), and the distribution range of the subject object qualitative character in the sample covers intends the whole of sensing range; The qualitative character overall degree evenly distributes in sample, and promptly the number of objects on each quality level is consistent in the sample.
3. the visual non-contact detection method of the meat quality based on spectrum picture according to claim 1; It is characterized in that: the preprocess method of spectrum picture is to utilize standardized normal distribution processing, spectrum smothing filtering and the difference differentiate operation of spectroscopic data to improve the spectral space signal to noise ratio (S/N ratio) earlier; Then through offset minimum binary perhaps, the combination of multiple linear regression or offset minimum binary and multiple linear regression analysis method, spectral image data is carried out feature selecting and feature extraction, and sets up the regression model between spectroscopic data and the traditional index.
4. the visual non-contact detection method of the meat quality based on spectrum picture according to claim 1 is characterized in that the method for carrying out effective surveyed area extraction is:
According to measured target and gather between the background, the difference of characteristics such as effective coverage and inactive area brightness in the characteristic wave bands image, position, area, form; Spectrum picture is carried out image segmentation; From spectrum picture, extract effective surveyed area, get rid of irrelevant or inactive area in the spectrum picture;
Extraneous areas refers to detect the incoherent meat of index zone with certain;
Inactive area refer to a certain detection index relevant range in, cause the local invalid in certain coherent detection zone thereby some part quality of spectrum picture surveyed area is lower than the subsequent treatment desired level.
5. the visual non-contact detection method of the meat quality based on spectrum picture according to claim 4; It is characterized in that; Reach the effective coverage that wherein extracts according to spectrum picture, obtain the spectral signature that the one or more representative curve of spectrum reflects effective coverage in this spectrum picture;
Representational curve of spectrum extracting mode comprises asks for this regional spectrum average curve, or spectrum intermediate value curve, or spectrum maximal value, minimum value and average curve, or average curve and average plus-minus standard deviation curve.
6. the visual non-contact detection method of the meat quality based on spectrum picture according to claim 4 is characterized in that in the said step 3),
Show on the tested meat object index of quality of each subregion in the effective coverage, with the space distribution situation of the reflection index of quality on tested meat object;
The granule size that shows subregion is the spatial discrimination yardstick, regulates according to index characteristic distributions, user and equipment needs;
The upper limit that this resolution yardstick is regulated is the measurand spectrum picture to be carried out the index of quality with the sub-pix yardstick detect and demonstration;
The lower limit that this resolution yardstick is regulated is overall meat sample matter index to be carried out as a sub-domain in the effective coverage of whole measurand spectrum picture detect and demonstration, and this moment, this method was in minimum mode of operation.
The index of quality of each subregion in the effective coverage on the tested meat object of said demonstration, its display mode is pseudo-color or stereo data display packing.
7. the visual non-contact detection method of the meat quality based on spectrum picture according to claim 1; Its characteristic is: said spectrum picture; Be to possess several images to a hundreds of continuous or discontinuous wave band spectral information; The spatial information and the spectral information of reflection measurand comprise multispectral image and high spectrum image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110447794.2A CN102564964B (en) | 2011-12-29 | 2011-12-29 | Spectral image-based meat quality visual non-contact detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110447794.2A CN102564964B (en) | 2011-12-29 | 2011-12-29 | Spectral image-based meat quality visual non-contact detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102564964A true CN102564964A (en) | 2012-07-11 |
| CN102564964B CN102564964B (en) | 2014-07-30 |
Family
ID=46410958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110447794.2A Expired - Fee Related CN102564964B (en) | 2011-12-29 | 2011-12-29 | Spectral image-based meat quality visual non-contact detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102564964B (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103900972A (en) * | 2014-04-04 | 2014-07-02 | 江南大学 | Multi-feature fusion-based meat freshness hyperspectral image visual detection |
| CN104089881A (en) * | 2013-12-17 | 2014-10-08 | 浙江工商大学 | Pseudosciaena crocea storage time detection method |
| CN104502519A (en) * | 2014-12-23 | 2015-04-08 | 厦门海荭兴科技股份有限公司 | Thin-layer chromatography pesticide residue rapid detection method based on image processing |
| CN103439271B (en) * | 2013-08-29 | 2015-10-28 | 华南理工大学 | The visible detection method of the ripe situation of a kind of pork |
| CN105719246A (en) * | 2016-01-13 | 2016-06-29 | 华南理工大学 | Spectrum imaging visual preprocessing method for detecting open water |
| CN105866042A (en) * | 2016-04-27 | 2016-08-17 | 南京林业大学 | Detection method for spatial distribution of biological quality indexes based on pixel index unbiased estimation method |
| CN105954205A (en) * | 2016-04-27 | 2016-09-21 | 南京林业大学 | Spectral imaging-based green plum sugar content and acidity fast non-destructive detection device |
| CN105973833A (en) * | 2016-04-28 | 2016-09-28 | 江南大学 | Refrigerated pork storage day number detection system and method thereof |
| GB2541895A (en) * | 2015-09-01 | 2017-03-08 | Univ Liverpool John Moores | Apparatus and method for measuring water activity in food products |
| CN107003253A (en) * | 2014-07-21 | 2017-08-01 | 7386819曼尼托巴有限公司 | The method and apparatus scanned for bone in meat |
| CN107271375A (en) * | 2017-07-21 | 2017-10-20 | 石河子大学 | A kind of high spectral image detecting method of quality of mutton index |
| CN108572150A (en) * | 2018-04-16 | 2018-09-25 | 成都大学 | A method of atriphos and bacterial population in sausage are detected based on EO-1 hyperion |
| CN108613941A (en) * | 2018-03-19 | 2018-10-02 | 河南科技学院 | The method of on-line quick detection chicken ash content |
| CN108613942A (en) * | 2018-03-19 | 2018-10-02 | 河南科技学院 | The method of on-line quick detection chicken hardness |
| CN108627475A (en) * | 2018-03-19 | 2018-10-09 | 河南科技学院 | Application in high light spectrum image-forming technology on-line checking chicken content of microorganisms |
| CN108627471A (en) * | 2018-03-19 | 2018-10-09 | 河南科技学院 | The method that on-line quick detection chicken heat kills rope silk bacterial content |
| CN108645798A (en) * | 2018-03-19 | 2018-10-12 | 河南科技学院 | The method of on-line quick detection chicken content of lactic acid bacteria |
| CN108663331A (en) * | 2017-03-27 | 2018-10-16 | 青岛海尔智能技术研发有限公司 | Detect the method and refrigerator of food freshness in refrigerator |
| CN108872137A (en) * | 2018-03-19 | 2018-11-23 | 河南科技学院 | Method based on multispectral on-line checking chicken thiobarbituricacidα- |
| CN108872138A (en) * | 2018-03-19 | 2018-11-23 | 河南科技学院 | The method of on-line quick detection chicken enterobacteriaceae content |
| CN110441268A (en) * | 2019-08-07 | 2019-11-12 | 南京林业大学 | The test method of moisture distribution in a kind of Cold Recycling Mixtures with Foamed Asphalt |
| CN110879955A (en) * | 2018-09-06 | 2020-03-13 | 埃森哲环球解决方案有限公司 | Digital quality control using computer vision with deep learning |
| CN111307798A (en) * | 2018-12-11 | 2020-06-19 | 成都智叟智能科技有限公司 | Article checking method adopting multiple acquisition technologies |
| CN111751297A (en) * | 2020-07-06 | 2020-10-09 | 广东智芯光电科技有限公司 | Method and system for identifying quality of fresh product based on camera |
| CN112557328A (en) * | 2020-12-23 | 2021-03-26 | 浙江农林大学 | Pork quality nondestructive testing device and method |
| US20220123848A1 (en) * | 2019-01-21 | 2022-04-21 | Nec Corporation | Wireless communication quality visualization system, wireless communication quality visualization device, and measurement apparatus |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6560546B1 (en) * | 2000-08-07 | 2003-05-06 | Infrasoft Llc | Remote analysis system |
| 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 |
| JP2008089529A (en) * | 2006-10-05 | 2008-04-17 | Fisheries Research Agency | Nondestructive measurement method of frozen ground fish meat component by near infrared analysis |
| CN101178356A (en) * | 2007-12-03 | 2008-05-14 | 中国农业大学 | Ultra-optical spectrum image-forming system and testing methods of meat product tenderness nondestructive testing |
| CN101251526A (en) * | 2008-02-26 | 2008-08-27 | 浙江大学 | Method and apparatus for nondestructively testing food synthetic quality |
| CN101710067A (en) * | 2009-12-14 | 2010-05-19 | 中国农业大学 | System and method for detecting quality of livestock meat |
| CN101806703A (en) * | 2010-01-07 | 2010-08-18 | 中国农业大学 | Non-destructive inspection method of total amount of meat bacteria |
| JP2010210355A (en) * | 2009-03-09 | 2010-09-24 | Kobe Univ | Method and apparatus for nondestructive measurement of component of vegetable etc. using near-infrared spectroscopy |
| CN102181514A (en) * | 2011-03-11 | 2011-09-14 | 中国农业大学 | Method for rapidly and nondestructively detecting colony count of chilled meat |
-
2011
- 2011-12-29 CN CN201110447794.2A patent/CN102564964B/en not_active Expired - Fee Related
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6560546B1 (en) * | 2000-08-07 | 2003-05-06 | Infrasoft Llc | Remote analysis system |
| JP2008089529A (en) * | 2006-10-05 | 2008-04-17 | Fisheries Research Agency | Nondestructive measurement method of frozen ground fish meat component by near infrared analysis |
| 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 |
| CN101178356A (en) * | 2007-12-03 | 2008-05-14 | 中国农业大学 | Ultra-optical spectrum image-forming system and testing methods of meat product tenderness nondestructive testing |
| CN101251526A (en) * | 2008-02-26 | 2008-08-27 | 浙江大学 | Method and apparatus for nondestructively testing food synthetic quality |
| JP2010210355A (en) * | 2009-03-09 | 2010-09-24 | Kobe Univ | Method and apparatus for nondestructive measurement of component of vegetable etc. using near-infrared spectroscopy |
| CN101710067A (en) * | 2009-12-14 | 2010-05-19 | 中国农业大学 | System and method for detecting quality of livestock meat |
| CN101806703A (en) * | 2010-01-07 | 2010-08-18 | 中国农业大学 | Non-destructive inspection method of total amount of meat bacteria |
| CN102181514A (en) * | 2011-03-11 | 2011-09-14 | 中国农业大学 | Method for rapidly and nondestructively detecting colony count of chilled meat |
Non-Patent Citations (3)
| Title |
|---|
| 万新民: "基于近红外光谱分析技术和计算机视觉技术的猪肉品质检测的研究", 《中国优秀硕士学问论文全文数据库 信息科技辑》, no. 5, 15 May 2011 (2011-05-15) * |
| 伍学千: "基于计算机视觉技术的猪肉品质检测与分级研究", 《中国优秀硕士学位全文数据库 信息科技辑》, no. 2, 15 February 2011 (2011-02-15) * |
| 蔡健荣等: "近红外光谱法快速检测猪肉中挥发性盐基氮的含量", 《光学学报》, vol. 29, no. 10, 31 October 2009 (2009-10-31), pages 2808 - 2812 * |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103439271B (en) * | 2013-08-29 | 2015-10-28 | 华南理工大学 | The visible detection method of the ripe situation of a kind of pork |
| CN104089881A (en) * | 2013-12-17 | 2014-10-08 | 浙江工商大学 | Pseudosciaena crocea storage time detection method |
| CN103900972B (en) * | 2014-04-04 | 2017-01-18 | 江南大学 | Multi-feature fusion-based meat freshness hyperspectral image visual detection |
| CN103900972A (en) * | 2014-04-04 | 2014-07-02 | 江南大学 | Multi-feature fusion-based meat freshness hyperspectral image visual detection |
| US11353439B2 (en) | 2014-07-21 | 2022-06-07 | 7386819 Manitoba Ltd. | Method for bone scan in meat |
| CN107003253A (en) * | 2014-07-21 | 2017-08-01 | 7386819曼尼托巴有限公司 | The method and apparatus scanned for bone in meat |
| CN104502519A (en) * | 2014-12-23 | 2015-04-08 | 厦门海荭兴科技股份有限公司 | Thin-layer chromatography pesticide residue rapid detection method based on image processing |
| US10942136B2 (en) | 2015-09-01 | 2021-03-09 | Liverpool John Moores University | Apparatus and method for measuring water activity in food products |
| GB2541895A (en) * | 2015-09-01 | 2017-03-08 | Univ Liverpool John Moores | Apparatus and method for measuring water activity in food products |
| GB2541895B (en) * | 2015-09-01 | 2019-12-18 | Univ Liverpool John Moores | Apparatus and method for measuring water activity in food products |
| CN105719246B (en) * | 2016-01-13 | 2018-06-29 | 华南理工大学 | A kind of light spectrum image-forming visualization pre-treating method for detecting open water |
| CN105719246A (en) * | 2016-01-13 | 2016-06-29 | 华南理工大学 | Spectrum imaging visual preprocessing method for detecting open water |
| CN105954205A (en) * | 2016-04-27 | 2016-09-21 | 南京林业大学 | Spectral imaging-based green plum sugar content and acidity fast non-destructive detection device |
| CN105866042B (en) * | 2016-04-27 | 2018-06-01 | 南京林业大学 | Based on pixel index unbiased esti-mator method biology index of quality spatial distribution detection method |
| CN105866042A (en) * | 2016-04-27 | 2016-08-17 | 南京林业大学 | Detection method for spatial distribution of biological quality indexes based on pixel index unbiased estimation method |
| CN105954205B (en) * | 2016-04-27 | 2018-11-13 | 南京林业大学 | Green plum pol based on light spectrum image-forming and acidity Rapid non-destructive testing device |
| CN105973833A (en) * | 2016-04-28 | 2016-09-28 | 江南大学 | Refrigerated pork storage day number detection system and method thereof |
| CN108663331A (en) * | 2017-03-27 | 2018-10-16 | 青岛海尔智能技术研发有限公司 | Detect the method and refrigerator of food freshness in refrigerator |
| CN107271375A (en) * | 2017-07-21 | 2017-10-20 | 石河子大学 | A kind of high spectral image detecting method of quality of mutton index |
| CN107271375B (en) * | 2017-07-21 | 2019-10-01 | 石河子大学 | A kind of high spectral image detecting method of quality of mutton index |
| CN108627471A (en) * | 2018-03-19 | 2018-10-09 | 河南科技学院 | The method that on-line quick detection chicken heat kills rope silk bacterial content |
| CN108872137A (en) * | 2018-03-19 | 2018-11-23 | 河南科技学院 | Method based on multispectral on-line checking chicken thiobarbituricacidα- |
| CN108872138A (en) * | 2018-03-19 | 2018-11-23 | 河南科技学院 | The method of on-line quick detection chicken enterobacteriaceae content |
| CN108627475A (en) * | 2018-03-19 | 2018-10-09 | 河南科技学院 | Application in high light spectrum image-forming technology on-line checking chicken content of microorganisms |
| CN108645798A (en) * | 2018-03-19 | 2018-10-12 | 河南科技学院 | The method of on-line quick detection chicken content of lactic acid bacteria |
| CN108613942A (en) * | 2018-03-19 | 2018-10-02 | 河南科技学院 | The method of on-line quick detection chicken hardness |
| CN108613941A (en) * | 2018-03-19 | 2018-10-02 | 河南科技学院 | The method of on-line quick detection chicken ash content |
| CN108572150A (en) * | 2018-04-16 | 2018-09-25 | 成都大学 | A method of atriphos and bacterial population in sausage are detected based on EO-1 hyperion |
| CN110879955A (en) * | 2018-09-06 | 2020-03-13 | 埃森哲环球解决方案有限公司 | Digital quality control using computer vision with deep learning |
| CN110879955B (en) * | 2018-09-06 | 2024-05-14 | 埃森哲环球解决方案有限公司 | Digital quality control using computer vision with deep learning |
| CN111307798A (en) * | 2018-12-11 | 2020-06-19 | 成都智叟智能科技有限公司 | Article checking method adopting multiple acquisition technologies |
| US20220123848A1 (en) * | 2019-01-21 | 2022-04-21 | Nec Corporation | Wireless communication quality visualization system, wireless communication quality visualization device, and measurement apparatus |
| CN110441268A (en) * | 2019-08-07 | 2019-11-12 | 南京林业大学 | The test method of moisture distribution in a kind of Cold Recycling Mixtures with Foamed Asphalt |
| CN110441268B (en) * | 2019-08-07 | 2021-09-21 | 南京林业大学 | Method for testing water distribution in foamed asphalt cold-recycling mixture |
| CN111751297A (en) * | 2020-07-06 | 2020-10-09 | 广东智芯光电科技有限公司 | Method and system for identifying quality of fresh product based on camera |
| CN112557328B (en) * | 2020-12-23 | 2022-05-31 | 浙江农林大学 | Pork quality nondestructive testing device and method |
| CN112557328A (en) * | 2020-12-23 | 2021-03-26 | 浙江农林大学 | Pork quality nondestructive testing device and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102564964B (en) | 2014-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102564964B (en) | Spectral image-based meat quality visual non-contact detection method | |
| Kamruzzaman et al. | Potential of hyperspectral imaging and pattern recognition for categorization and authentication of red meat | |
| Nyalala et al. | Weight and volume estimation of poultry and products based on computer vision systems: a review | |
| Khulal et al. | Intelligent evaluation of total volatile basic nitrogen (TVB-N) content in chicken meat by an improved multiple level data fusion model | |
| CN1995987B (en) | Non-destructive detection method for agricultural and animal products based on hyperspectral image technology | |
| ElMasry et al. | Non-destructive determination of water-holding capacity in fresh beef by using NIR hyperspectral imaging | |
| Yao et al. | Nondestructive detection for egg freshness grade based on hyperspectral imaging technology | |
| CN102799903B (en) | High-spectrum automatic cloud detection method based on space and spectral information | |
| Cheng et al. | Data fusion and hyperspectral imaging in tandem with least squares-support vector machine for prediction of sensory quality index scores of fish fillet | |
| Li et al. | Detection of early decayed oranges based on multispectral principal component image combining both bi-dimensional empirical mode decomposition and watershed segmentation method | |
| Zhu et al. | Support vector machine and YOLO for a mobile food grading system | |
| Zhang et al. | Comparison of spectral and image morphological analysis for egg early hatching property detection based on hyperspectral imaging | |
| Bansal et al. | Green citrus detection using fast Fourier transform (FFT) leakage | |
| CN105548028A (en) | Fowl egg freshness optical fiber spectroscopic grading detection device and method | |
| CN201392319Y (en) | Meat online lossless detecting device based on the combination of images and spectrum information | |
| Wang et al. | Visualizing quantitatively the freshness of intact fresh pork using acousto-optical tunable filter-based visible/near-infrared spectral imagery | |
| CN103760110A (en) | Method for rapidly identifying meat with different animal sources | |
| CN104237235A (en) | Rapid detection method based on near-infrared imaging technology for food-borne pathogens | |
| Zhang et al. | Fire detection and identification method based on visual attention mechanism | |
| Sun et al. | Research of moldy tea identification based on RF-RFE-Softmax model and hyperspectra | |
| Chen et al. | Real-time defect and freshness inspection on chicken eggs using hyperspectral imaging | |
| Park et al. | Line-scan imaging analysis for rapid viability evaluation of white-fertilized-egg embryos | |
| Zuñiga et al. | Grape maturity estimation based on seed images and neural networks | |
| Lin et al. | A pH-Responsive colourimetric sensor array based on machine learning for real-time monitoring of beef freshness | |
| Bu et al. | Rapid nondestructive detecting of sorghum varieties based on hyperspectral imaging and convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20120711 Assignee: Anhui Arrow Electronics Co., Ltd. Assignor: Nanjing Forestry University Contract record no.: 2018320000282 Denomination of invention: Spectral image-based meat quality visual non-contact detection method Granted publication date: 20140730 License type: Common License Record date: 20181101 Application publication date: 20120711 Assignee: Chuzhou Monte tech Environmental Protection Technology Co., Ltd. Assignor: Nanjing Forestry University Contract record no.: 2018320000280 Denomination of invention: Spectral image-based meat quality visual non-contact detection method Granted publication date: 20140730 License type: Common License Record date: 20181101 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190809 Address after: 221631 People's Government of Zhangzhuang Town, Peixian County, Xuzhou City, Jiangsu Province Patentee after: Peixian Hantang Construction Development Co., Ltd. Address before: Longpan road Xuanwu District of Nanjing city of Jiangsu Province, No. 159 210037 Patentee before: Nanjing Forestry University |
|
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140730 Termination date: 20201229 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |