CN106940292A - Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology - Google Patents
Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology Download PDFInfo
- Publication number
- CN106940292A CN106940292A CN201710273539.8A CN201710273539A CN106940292A CN 106940292 A CN106940292 A CN 106940292A CN 201710273539 A CN201710273539 A CN 201710273539A CN 106940292 A CN106940292 A CN 106940292A
- Authority
- CN
- China
- Prior art keywords
- worms
- damaging
- bar denier
- optical spectrum
- imaging technology
- 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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (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 invention discloses a kind of bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, the wooden shell information of bar denier is obtained using multi-optical spectrum imaging technology, realization quickly and efficiently screens wormy fruit from normal fruit, while the Ba Danmu of different grades of damaging by worms can be recognized.The invention can accurately sort out the Ba Danmu of normal bar denier wood and damage by worms Ba Danmu and different grades of damaging by worms, meet requirement of the wooden on-line checking processing of bar denier in terms of the degree of accuracy, resolution and stability, Product Safety is improved, technical support is provided with improving the market competitiveness for Ba Danmu automation deep processing.The advantage of the invention is that can it is complete, consistent in the wooden profile of bar denier in the case of to wormy fruit and normal fruit is accurate sorts out, and it is easy to operate, do not destroy sample, it is free from environmental pollution, the interference of human factor in artificial evaluation and screening is also avoid simultaneously, it is as a result more objective, accurate.
Description
Technical field
The present invention relates to lossless detection method field, specifically a kind of bar denier wood of damaging by worms based on multi-optical spectrum imaging technology is former
Expect quick nondestructive discrimination method.
Background technology
Ba Danmu contains abundant bioactivator such as vitamin E, arginine, fiber, monounsaturated fatty acids, more not
Saturated fatty acid and other trace elements, there is certain prevention effect to cardiac-related diseases, cancer and diabetes B, plus
Upper fragrance and mouthfeel are unique, therefore as the Important Economic crop of consumption and trade both at home and abroad.
Influenceed by high temperature, high humidity environment, bar denier Muyi's insect infestation after harvesting, and Ba Danmu damages by worms phenomenon very
Complexity, different from Chinese chestnut, there is worm channel on surface, and larva can directly gnaw kernel without gnawing pericarp, and what these wounds had can expose
Out, what is had is then hidden, naked eyes None- identified.In order to find the phenomenon of damaging by worms of early stage, potential risk is eliminated, it is necessary to by worm
The wood graduation of bar denier is eaten into differentiate.By screening before the processing of bar denier wood products, the nut of insect pest is rejected, it is possible to reduce the storing phase
Between loss, nutrition, freshness and edible safety are kept to greatest extent, increases the attraction to consumer, while and
When handle the Ba Danmu that slightly damages by worms, prevent from further infecting, reduce potential risk.At present, the worm of Chinese commodity bar denier wood
Moth nut differentiate there are problems that time and effort consuming, speed it is slow, it is therefore, urgent in Ba Danmu process
Need a kind of convenient, quick discrimination method.
Multispectral imaging is a kind of Fast nondestructive evaluation technology widely used in recent years, with traditional high light spectrum image-forming technology
Compare, multi-optical spectrum imaging technology avoids the spectrum characteristic data of magnanimity, detected more suitable for the real-time online of quality of agricultural product.
At present, in the Non-Destructive Testing of agricultural product machine vision, near infrared spectrum etc. Preliminary Applications, in industrial on-line checking, but are used for
The relative commercial equipment of internal flaw detection is less.
The content of the invention
Differentiate it is an object of the invention to provide a kind of bar denier wood raw material quick nondestructive of damaging by worms based on multi-optical spectrum imaging technology
Method, to solve the problem of prior art is not applied to the multi-optical spectrum imaging technology of the wooden internal flaw detection of bar denier.
In order to achieve the above object, the technical solution adopted in the present invention is：
Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, it is characterised in that：Including with
Lower step：
(1) the spectrum picture letter of the wooden sample of normal bar denier and the wooden sample of bar denier of damaging by worms is obtained based on multi-optical spectrum imaging technology
Breath；
(2) according to degree of damaging by worms, wormy fruit is further divided into slight and serious two grades of damaging by worms, differentiates that difference is damaged by worms
The Ba Danmu of degree.
(3) spectral image information of the wooden sample of normal bar denier and the wooden sample of bar denier of damaging by worms is carried out at denoising successively respectively
After reason, background rejecting, image segmentation, the wooden sample of normal bar denier, the shell spectral image information of the wooden sample of bar denier of damaging by worms are obtained；
(4) using the original spectral data in step (3), combination supporting vector machine (SVM) Return Law sets up normal bar denier
The analysis model of the shell spectral image information of the wooden sample of wooden sample, bar denier of damaging by worms.Each bar denier wood is have recorded in initial data
The characteristic component of sample, different classes of sample provides class label respectively, and sample is randomly divided into two groups, one group of conduct first
Training set, one group as test set, is trained grader with training set afterwards, can obtain disaggregated model, then with obtained model
Class label prediction is carried out to test set, so as to realize the quick nondestructive discriminating to the Ba Danmu that damages by worms.
The described bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, it is characterised in that：
In step (1), the wooden sample of normal bar denier and the wooden sample profile of bar denier of damaging by worms of selection are complete.
The described bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, it is characterised in that：
Multi-optical spectrum imaging technology in step (1) is realized by multispectral survey instrument, and includes 405~970nm using multispectral survey instrument
In the range of 19 characteristic wavelengths spectral band (405,435,450,470,505,525,570,590,630,645,660,700,
780,850,870,890,910,940,970nm), to obtain the spectrum picture of the wooden sample of normal bar denier and the wooden sample of bar denier of damaging by worms
Information.
The described bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, it is characterised in that：
In step (3), denoising is carried out using VideometerLab softwares.
The described bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, it is characterised in that：
In step (3), background is completed using classical discriminant analysis and threshold value setting and rejected and image segmentation.
The described bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, it is characterised in that：
In step (4), the shell spectrum picture of the wooden sample of normal bar denier, the wooden sample of bar denier of damaging by worms is set up using Support vector regression method
The analysis model of information.
The present invention describes a kind of bar denier of damaging by worms based on multi-optical spectrum imaging technology for the complicated situation of damaging by worms of bar denier wood
Wood raw material quick nondestructive discrimination method, i.e., obtain the wooden shell signal of bar denier, by the Ba Danmu of acquisition using multi-optical spectrum imaging technology
Spectrum picture is realized and the quick nondestructive for the Ba Danmu that damages by worms is differentiated via image segmentation, data analysis and microcomputer modelling.This method
Have the advantages that it is easy to operate, quick, without breakage, be conducive to the Ba Danmu production that becomes more meticulous, meet consumer hard to high-quality
The pursuit of fruit.
The invention provides a kind of bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, it is
Multispectral imaging provides technical support in the lossless, real-time of nut inside quality, automatic detection field, can meet bar denier wood online
Detection processing is the automation deep processing of the wooden commodity of China's bar denier with carrying to the requirement in terms of the degree of accuracy, resolution and stability
The high market competitiveness provides technical support.
It is lossless, quick, pollution-free that the present invention utilizes multi-optical spectrum imaging technology to have the advantages that, compared with conventional method,
This method can it is complete, consistent in the wooden profile of bar denier in the case of the Ba Danmu that will damage by worms effectively identified from normal fruit,
Identification difference is damaged by worms the Ba Danmu of degree, and do not destroy sample, it is free from environmental pollution, artificial evaluate and screen while also avoid
In human factor interference, it is as a result more objective, accurate.
Brief description of the drawings
Normal and the Ba Danmu that damages by worms the average reflectance spectra figures of Fig. 1.
Fig. 2 normal and the wooden test set of bar denier of damaging by worms actual classification and prediction classification chart.
The actual classification and prediction classification chart of normal, the slight and serious wooden test sets of bar denier of damaging by worms of Fig. 3.
Embodiment
Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, comprises the following steps：
(1) the spectrum picture letter of the wooden sample of normal bar denier and the wooden sample of bar denier of damaging by worms is obtained based on multi-optical spectrum imaging technology
Breath；
(2) according to degree of damaging by worms, wormy fruit is further divided into slight and serious two grades of damaging by worms, differentiates that difference is damaged by worms
The Ba Danmu of degree.
(3) spectral image information of the wooden sample of normal bar denier and the wooden sample of bar denier of damaging by worms is carried out at denoising successively respectively
After reason, background rejecting, image segmentation, the wooden sample of normal bar denier, the shell spectral image information of the wooden sample of bar denier of damaging by worms are obtained；
(4) using the original spectral data in step (3), combination supporting vector machine (SVM) Return Law sets up normal bar denier
The analysis model of the shell spectral image information of the wooden sample of wooden sample, bar denier of damaging by worms.Each bar denier wood is have recorded in initial data
The characteristic component of sample, different classes of sample provides class label respectively, and sample is randomly divided into two groups, one group of conduct first
Training set, one group as test set, is trained grader with training set afterwards, can obtain disaggregated model, then with obtained model
Class label prediction is carried out to test set, so as to realize the quick nondestructive discriminating to the Ba Danmu that damages by worms.
In step (1), the wooden sample of normal bar denier and the wooden sample profile of bar denier of damaging by worms of selection are complete.
Multi-optical spectrum imaging technology in step (1) is realized by multispectral survey instrument, and includes 405 using multispectral survey instrument
In the range of~970nm 19 characteristic wavelengths spectral band (405,435,450,470,505,525,570,590,630,645,
660,700,780,850,870,890,910,940,970nm), to obtain the wooden sample of normal bar denier and the wooden sample of bar denier of damaging by worms
Spectral image information.
In step (3), denoising is carried out using VideometerLab softwares.
In step (3), background is completed using classical discriminant analysis and threshold value setting and rejected and image segmentation.
In step (4), the wooden sample of normal bar denier, the wooden sample of bar denier of damaging by worms are set up using Support vector regression method (SVM)
Shell spectral image information analysis model.
Embodiment
Experiment sample：
Prepare two groups of complete Ba Danmu of (A, B) shell, A groups kernel is normal, B group kernels are damaged by worms phenomenon；
1st, Fast nondestructive evaluation is normal and the Ba Danmu that damages by worms
Detecting step is as follows：
(1) 115,230 bar denier wood of B groups selection are randomly selected from A groups, with multispectral survey instrument (Videometer
A/S,Denmark, its spectral region is 405-970nm, specifically comprising 405,435,450,470,505,525,570,
590,630,645,660,700,780,850,870,890,910,940,970nm) obtain the wooden sample of above-mentioned bar denier and background letter
Breath, then carries out denoising using VideometerLab softwares, and completing background with classical discriminant analysis and threshold value setting picks
Remove and image segmentation, obtain the shell information of sample.
(2) divide using Support vector regression method (SVM) is wooden to above-mentioned Sample Establishing bar denier with corresponding spectral information
Analyse model.Two groups of A, B is randomly assigned 40 and 80 samples as test set respectively, and remaining sample is used as training set.Will be normal
The label of nut is set to 1, and the label for nut of damaging by worms is set to 2, first trains grader with test set, then with obtained model to test
Collection carries out class label prediction, and Fig. 2 is predicting the outcome for test set.
(3) table 1 is the testing result of normal bar denier wood and the wooden test set sample of bar denier of damaging by worms.
Table 1 is damaged by worms Ba Danmu quick nondestructive identification result
2nd, Fast nondestructive evaluation difference is damaged by worms the Ba Danmu of degree
Detecting step is as follows：
(1) the bar denier that will be damaged by worms in embodiment 1 wood sample is divided into slight and serious damage by worms two classes, each 115 samples.With light more
Spectrometry instrument (Videometer A/S,Denmark, its spectral region is 405-970nm, specifically comprising 405,435,
450,470,505,525,570,590,630,645,660,700,780,850,870,890,910,940,970nm) in acquisition
The wooden sample of bar denier and background information are stated, then denoising is carried out using VideometerLab softwares, with classical discriminant analysis
Background is completed with threshold value setting to reject and image segmentation, obtains the shell information of sample.
(2) the Ba Danmu classification foundation sample of damaging by worms is damaged by worms degree division, and concrete operations are as follows：
After spectrum picture is obtained, all samples pass through band shell and weigh, shell and weigh, and calculate kernel proportion.With it is normal
After Ba Danmu is compared, the kernel proportion using 50% is boundary, and being considered as more than 50% slightly damages by worms, being considered as less than or equal to 50%
Seriously damage by worms, and the spectrum that will be damaged by worms again with this feature is divided into slight and serious two class；
(3) divide using SVMs (SVM) Return Law is wooden to above-mentioned Sample Establishing bar denier with corresponding spectral information
Analyse model.Three class samples are randomly assigned 40 and 75 samples as test set and training set respectively.The label of normal nut is determined
For 1, the label for nut of slightly damaging by worms is set to 2, and the label for nut of seriously damaging by worms is set to 3, first trains grader with test set, then use
Obtained model carries out class label prediction to test set, and Fig. 3 is predicting the outcome for the wooden test set of three class bar denier.
(4) table 2 is the testing result of the different wooden test set samples of grade bar denier of damaging by worms.
The difference of table 2 damage by worms grade bar denier wood quick nondestructive identification result
As can be seen from Figure 1, the normal, Ba Danmu that damages by worms has obvious spectral discrimination between 405-970nm, as shown in Table 1,
Total correct decision rate of 120 measured results is that total correct decision rate of test set in 97.50%, table 2 is 93.33%, and from
Fig. 2, Fig. 3 can clearly find out normally, the misjudgement situation of damage by worms Ba Danmu and different grade bar denier wood of damaging by worms, be indicated above this hair
Bright utilization multispectral imaging differentiates it is feasible to the quick nondestructive for the Ba Danmu that damages by worms.
Claims (6)
1. the bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology, it is characterised in that：Including following
Step：
（1）The spectral image information of the wooden sample of normal bar denier and the wooden sample of bar denier of damaging by worms is obtained based on multi-optical spectrum imaging technology；
（2）Bar denier wood raw material quick nondestructive discrimination method of damaging by worms according to claim 1 based on multi-optical spectrum imaging technology,
It is characterized in that：Multi-optical spectrum imaging technology is except can accurately sort out normal bar denier wood and the Ba Danmu that damages by worms, according to degree of damaging by worms,
Wormy fruit is further divided into slight and serious two grades of damaging by worms, differentiates the Ba Danmu of different degree of damaging by worms, infringement is being rejected
While Ba Danmu, moreover it is possible in early detection problem of damaging by worms, processing in time reduces loss, improves product utilization rate；
（3）Denoising, the back of the body are carried out successively to the spectral image information of the wooden sample of normal bar denier and the wooden sample of bar denier of damaging by worms respectively
After scape rejecting, image segmentation, the wooden sample of normal bar denier, the shell spectral image information of the wooden sample of bar denier of damaging by worms are obtained；
（4）Utilize step（3）In original spectral data, combination supporting vector machine（SVM）The Return Law sets up the wooden sample of normal bar denier
Originally, the analysis model of the shell spectral image information of the wooden sample of bar denier of damaging by worms；
The characteristic component of the wooden sample of each bar denier is have recorded in initial data, different classes of sample provides class label respectively,
Sample is randomly divided into two groups first, one group as training set, one group, as test set, is trained grader with training set afterwards,
Disaggregated model can be obtained, then class label prediction is carried out to test set with obtained model, so as to realize to the Ba Danmu that damages by worms
Quick nondestructive differentiate.
2. the bar denier wood raw material quick nondestructive discrimination method of damaging by worms according to claim 1 based on multi-optical spectrum imaging technology,
It is characterized in that：Step（1）In, the wooden sample of normal bar denier and the wooden sample profile of bar denier of damaging by worms of selection are complete.
3. the bar denier wood raw material quick nondestructive discrimination method of damaging by worms according to claim 1 based on multi-optical spectrum imaging technology,
It is characterized in that：Step（1）In multi-optical spectrum imaging technology realized by multispectral survey instrument, and existed using multispectral survey instrument
The spectral band of 19 characteristic wavelengths in the range of 405 ~ 970 nm（405, 435, 450, 470, 505, 525, 570,
590, 630, 645, 660, 700, 780, 850, 870, 890, 910, 940, 970 nm）, to obtain normal bar denier
The spectral image information of wooden sample and the wooden sample of bar denier of damaging by worms.
4. the bar denier wood raw material quick nondestructive discrimination method of damaging by worms according to claim 1 based on multi-optical spectrum imaging technology,
It is characterized in that：Step（3）In, denoising is carried out using VideometerLab softwares.
5. the bar denier wood raw material quick nondestructive discrimination method of damaging by worms according to claim 1 based on multi-optical spectrum imaging technology,
It is characterized in that：Step（3）In, background is completed using classical discriminant analysis and threshold value setting and rejected and image segmentation.
6. the bar denier wood raw material quick nondestructive discrimination method of damaging by worms according to claim 1 based on multi-optical spectrum imaging technology,
It is characterized in that：Step（4）In, the wooden sample of normal bar denier, bar denier of damaging by worms wooden sample are set up using Support vector regression method
The analysis model of shell spectral image information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710273539.8A CN106940292A (en) | 2017-04-25 | 2017-04-25 | Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710273539.8A CN106940292A (en) | 2017-04-25 | 2017-04-25 | Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106940292A true CN106940292A (en) | 2017-07-11 |
Family
ID=59464114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710273539.8A Pending CN106940292A (en) | 2017-04-25 | 2017-04-25 | Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106940292A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107490550A (en) * | 2017-07-17 | 2017-12-19 | 安徽谱泉光谱科技有限公司 | A kind of online quality detecting method of macadamia |
| CN109540814A (en) * | 2019-01-12 | 2019-03-29 | 合肥工业大学 | A kind of iris gray mold early detection method based on multi-optical spectrum imaging technology |
| CN115575405A (en) * | 2022-10-24 | 2023-01-06 | 江西绿萌科技控股有限公司 | Fruit appearance quality detection method based on multispectral image characteristic quantity |
| CN117253122A (en) * | 2023-11-17 | 2023-12-19 | 云南大学 | Corn seed approximate variety screening method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103149163A (en) * | 2013-02-05 | 2013-06-12 | 南京农业大学 | Multispectral image textural feature-based beef tenderness detection device and method thereof |
| CN103543106A (en) * | 2013-09-30 | 2014-01-29 | 合肥工业大学 | Rapid non-destructive testing method for melon seed quality characteristic based on spectral imaging technique |
| CN106290171A (en) * | 2016-07-27 | 2017-01-04 | 内蒙古大学 | Based on SVM and the maize leaf chlorophyll content of regression analysis and phenotypic parameter assay method |
-
2017
- 2017-04-25 CN CN201710273539.8A patent/CN106940292A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103149163A (en) * | 2013-02-05 | 2013-06-12 | 南京农业大学 | Multispectral image textural feature-based beef tenderness detection device and method thereof |
| CN103543106A (en) * | 2013-09-30 | 2014-01-29 | 合肥工业大学 | Rapid non-destructive testing method for melon seed quality characteristic based on spectral imaging technique |
| CN106290171A (en) * | 2016-07-27 | 2017-01-04 | 内蒙古大学 | Based on SVM and the maize leaf chlorophyll content of regression analysis and phenotypic parameter assay method |
Non-Patent Citations (1)
| Title |
|---|
| 刘伟 等: "基于支持向量机的多光谱成像稻谷品种鉴别", 《农业工程学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107490550A (en) * | 2017-07-17 | 2017-12-19 | 安徽谱泉光谱科技有限公司 | A kind of online quality detecting method of macadamia |
| CN109540814A (en) * | 2019-01-12 | 2019-03-29 | 合肥工业大学 | A kind of iris gray mold early detection method based on multi-optical spectrum imaging technology |
| CN115575405A (en) * | 2022-10-24 | 2023-01-06 | 江西绿萌科技控股有限公司 | Fruit appearance quality detection method based on multispectral image characteristic quantity |
| CN117253122A (en) * | 2023-11-17 | 2023-12-19 | 云南大学 | Corn seed approximate variety screening method, device, equipment and storage medium |
| CN117253122B (en) * | 2023-11-17 | 2024-01-23 | 云南大学 | Corn seed approximate variety screening method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108663339B (en) | On-line detection method for mildewed corn based on spectrum and image information fusion | |
| CN103063585B (en) | Melon and fruit degree of ripeness Rapid non-destructive testing device and detection system method for building up | |
| CN110763698B (en) | Hyperspectral citrus leaf disease identification method based on characteristic wavelength | |
| CN102253052B (en) | Grain quality on-line detection apparatus based on field programmable gate array (FPGA) | |
| CN106940292A (en) | Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology | |
| CN108444924B (en) | Method for discriminating storage period of tea by applying hyperspectral image technology | |
| CN113008817A (en) | Method for rapidly identifying authenticity and quality of bitter apricot kernels based on hyperspectral imaging technology | |
| Saini et al. | Analysis of wheat grain varieties using image processing–a review | |
| Rafiq et al. | Application of computer vision system in food processing | |
| CN105628708A (en) | Quick nondestructive testing method for multi-parameter quality of south Xinjiang red dates | |
| CN103528967A (en) | Hyperspectral image based overripe Lonicera edulis fruit identification method | |
| Carolina et al. | Classification of oranges by maturity, using image processing techniques | |
| CN116559111A (en) | Sorghum variety identification method based on hyperspectral imaging technology | |
| Aredo et al. | Predicting of the Quality Attributes of Orange Fruit Using Hyperspec-tral Images | |
| Syazwan et al. | Categorization of watermelon maturity level based on rind features | |
| CN102749420B (en) | Peanut quality determination and evaluation methods suitable for gel type protein processing | |
| CN202083645U (en) | FPGA (field programmable gate array)-based food quality on-line detector | |
| Zhou et al. | Green plums surface defect detection based on deep learning methods | |
| CN106338488A (en) | Method for fast undamaged determination of transgenic soybean milk powder | |
| Ji et al. | Apple color automatic grading method based on machine vision | |
| CN110609011A (en) | Near-infrared hyperspectral detection method and system for starch content of single-kernel corn seeds | |
| CN110231300A (en) | A kind of lossless method for quickly identifying true and false Aksu red fuji apple | |
| Li | Classification of black tea leaf water content based on hyperspectral imaging | |
| Fu et al. | Distinguishing overripe berries of Japanese blue honeysuckle using hyperspectral imaging analysis | |
| Ravindran et al. | A review on non-destructive techniques for evaluating quality of fruits |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170711 |
|
| RJ01 | Rejection of invention patent application after publication |