CN106644957B - A kind of method that loquat adopts rear pulp soluble solid distribution imaging - Google Patents
A kind of method that loquat adopts rear pulp soluble solid distribution imaging Download PDFInfo
- Publication number
- CN106644957B CN106644957B CN201611001232.4A CN201611001232A CN106644957B CN 106644957 B CN106644957 B CN 106644957B CN 201611001232 A CN201611001232 A CN 201611001232A CN 106644957 B CN106644957 B CN 106644957B
- Authority
- CN
- China
- Prior art keywords
- pulp
- soluble solid
- loquat
- slicing
- stripping
- 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.)
- Active
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)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a kind of methods that loquat adopts rear pulp soluble solid distribution imaging, solve the problems, such as that existing detection method can not obtain the spatial distribution of soluble solid inside loquat fruit.Loquat fruit is cut squarely fritter according to spatial distribution by this method, the soluble solid content and spectrum mean value of each pulp stripping and slicing are obtained respectively, and soluble solid content is associated with spectrum mean value using equation of linear regression, and establish the prediction model of soluble solid content and spectral value, its corresponding soluble solid content is predicted according to the spectral value of each pixel of pulp stripping and slicing everywhere in prediction sample to be tested, Pixel-level distributed in three dimensions model of the soluble solid in sample to be tested is established according to the spatial distribution coordinate of each pixel of sample to be tested pulp stripping and slicing, realize that loquat adopts the spatial visualization imaging of rear interior flesh soluble solid distribution.
Description
Technical field
The invention belongs to spectral detection field, it is related to the side that a kind of loquat adopts rear pulp soluble solid distribution imaging
Method.
Background technique
Loquat is China's local product fruits, and pulp is full of nutrition, is loved by consumers.Loquat fruit still has life living after adopting
It is dynamic, it is accompanied by quality comparison.Wherein soluble solid and loquat fruit mouthfeel are closely related, are important the index of quality.Cause
This, further investigation loquat fruit adopts rear soluble solid change mechanism, adopts rear storage and transportation mode, extension fruit to existing pulp is improved
Meat shelf period reduces loss etc. after pulp is adopted, and is of great significance.
The soluble solid content measurement of loquat fruit usually first obtains fritter pulp, then squeezes out fruit juice and drips to folding
Acquisition is read after penetrating instrument prism surface.But the whole soluble solid that refractometer method is only capable of obtaining tested fritter pulp contains
Amount, belongs to spot measurement, can not obtain space distribution situation of the soluble solid inside loquat fruit.
High light spectrum image-forming technology blends hyperspectral analysis technology with image processing techniques, can obtain a series of spectrum
Optical imagery combination at wavelength is a kind of snap information acquisition, obtains the big modern analytical technique of data volume.Currently, bloom
Spectral imaging technology detects it has been reported that generally by using high light spectrum image-forming skill the soluble solid of loquat and other fruit
Art obtains fruit surface high spectrum image, to realize the Fast nondestructive evaluation of fruit soluble solid.The above method will
Spectral detection result rests on the surface layer of loquat fruit, is unable to get the spatial distribution of pulp interior flesh soluble solid
Figure, and in fact, distribution of the soluble solid inside loquat fruit has an important influence mouthfeel, only pass through the height of epidermis
Spectrum picture non-destructive testing obviously can not obtain the spatial distribution of soluble solid inside loquat fruit, even if being surveyed using multiple spot
The mode of amount carries out simulation spatial distribution state to obtain the soluble solid value of pulp different location, due to choosing measurement point
Positioning can not be accurate, acquired data also do not have continuity, and there is also errors for spatial distribution status data obtained
Greatly, it is soluble inside the fruit in growth and development and preservation and freshness stage to be also unable to satisfy further investigation for the problem of precision deficiency
The requirement of the change mechanism of solid content.
Summary of the invention
It is an object of the invention to the sky of soluble solid inside loquat fruit can not be obtained for existing detection method
Between the defect that is distributed, a kind of method that loquat adopts rear pulp soluble solid distribution imaging is proposed, by obtaining inside pulp
High spectrum image, and obtain after data processing loquat and adopt soluble solid distribution map inside rear pulp.
The present invention solves scheme used by its technical problem: a kind of loquat adopts rear pulp soluble solid and is scattered in
The method of picture, which comprises the following steps:
Step 1: establishing the quantitative linearity regression equation based on loquat fruit spectral detection soluble solid content；
Step 1.1: n loquat sample of acquisition is denoted as M respectively1、M2、M3、…、Mn；
Step 1.2: for each loquat sample Mi, 1 < i < n, after removing exocarp, along pulp equatorial plane to cutting simultaneously
Stoning, removal endocarp, select the cutting planes parallel with equatorial plane to cut pulp, form two end fruit blocks and multiple rings
Shape fruit block, distance is 0.6 centimetre between cutting planes；Pulp both ends fruit block is no longer finely divided cutting, remaining each annular fruit
Block circumferential direction is cut into several pieces in parts, then is cut into several pieces in parts along pulp thickness direction, obtains the pulp stripping and slicing of m block altogether, point
M is not denoted as itI, j, 1 < j < m；
Step 1.3: acquiring each pulp stripping and slicing Mi,jEach side high spectrum image；
Step 1.4: each pulp stripping and slicing M is measured using national standard methodi,jSoluble solid content, and respectively
As pulp stripping and slicing Mi,jSoluble solid content reference value yi,j；According to national standard " NY/T 2637-2014 fruit and
The measurement of Soluble Solids of Vegetables "；
Step 1.5: for each pulp stripping and slicing Mi,j, choose 382nm, 387nm, 406nm, 408nm, 412nm, 456nm,
485nm, 510nm, 539nm, 562nm, 933nm, 967nm, 998nm, 1030nm wavelength are that loquat fruit soluble solid contains
The characteristic wavelength of detection is measured, and obtains pulp stripping and slicing Mi,jAll sides high spectrum image in pulp fraction all pixels point
In the spectrum mean value of each characteristic wavelength, it is denoted as respectively
Step 1.6: using multiple linear regression by pulp stripping and slicing M in step 1.5I, jEach characteristic wavelength spectrum it is average
Value and the pulp stripping and slicing M in step 1.4i,jSoluble solid reference value yi,jIt is associated fitting, establishes prediction model, is closed
Connection process is carried out using following equation of linear regression one:
Establish the quantitative linearity regression equation two for predicting loquat fruit spectral detection soluble solid content:
Step 2: obtaining the soluble solid content distribution map of loquat interior flesh to be measured；
Step 2.1: choosing loquat sample N to be measured；
Step 2.2: stripping and slicing being carried out to loquat sample N to be measured, block cutting method describes method according to step 1.2 and carries out, obtains
Nz, the total p block pulp stripping and slicing of 1 < z < p records pulp stripping and slicing NzIn the space coordinate of loquat sample N to be measured；
Step 2.3: acquisition pulp stripping and slicing NzEach section high spectrum image, and obtain each pixel in image and exist
Characteristic wavelength 382nm, 387nm, 406nm, 408nm, 412nm, 456nm, 485nm, 510nm, 539nm, 562nm, 933nm,
Spectral value at 967nm, 998nm, 1030nm, is denoted as respectively Wherein, (α, β,
It is γ) coordinate information of each pixel, α is abscissa information, and β is ordinate information, and γ is section identification information；
Step 2.4: by the loquat fruit stripping and slicing N to be measured in step 2.3zThe each pixel in each section in each characteristic wave
The spectral value of strong point substitutes into the quantitative linearity regression equation two of step 1.6, and the soluble solid of each pixel is calculated
Object predicted value yZ, (α, beta, gamma)', and the space coordinate according to each pixel in the high spectrum image of place section, form pulp
Stripping and slicing NzEach space coordinate soluble solid content distribution map；
Step 2.5: the pulp stripping and slicing N obtained according to step 2.4zEach section soluble solid content distribution
Figure and stripping and slicing NzSpace coordinate in sample N obtains soluble solid inside sample N using bicubic interpolation algorithm
The latticed space multistory distribution map of content realizes that loquat adopts the spacing-visible chemical conversion of rear interior flesh soluble solid distribution
Picture.
Preferably, each annular fruit block circumferential direction is cut into parts during several pieces in step 1.2, if annular fruit block
Race diameter < 1.2 centimetre are then cut into 4 pieces in parts, if 1.2 centimetres < annular fruit block race diameter < 2.4 centimetre, Deng cutting
8 pieces are cut into, if annular fruit block race diameter > 2.4 centimetre, are cut into 12 pieces in parts.
Preferably, in step 1.2, when being cut into several pieces in parts along pulp thickness direction, if pulp thickness < 0.6 li
Rice, then thickness direction is not cut, if 0.6 centimetre < pulp thickness < 1.2 centimetre, thickness direction is cut into 2 pieces in parts, if pulp
Thickness > 1.2 centimetre, then thickness direction is cut into 3 pieces in parts.
Loquat fruit is cut squarely fritter according to spatial distribution by the present invention, obtains the solubility of each pulp stripping and slicing respectively
Solid content and spectrum mean value, and correlation model is established, it can be each according to pulp stripping and slicing everywhere in prediction sample to be tested
The spectral value of pixel predicts the corresponding soluble solid content of each of which pixel, each according to sample to be tested pulp stripping and slicing
The spatial distribution coordinate of pixel establishes Pixel-level distributed in three dimensions model of the soluble solid in sample to be tested, realizes Pi
Rake adopts the spatial visualization imaging of rear interior flesh soluble solid distribution.
Specific embodiment
Below by specific embodiment, the present invention will be further described.
A kind of embodiment: method that loquat adopts rear pulp soluble solid distribution imaging, comprising the following steps:
Step 1: establishing the quantitative linearity regression equation based on loquat fruit spectral detection soluble solid content；
Step 1.1: n loquat sample of acquisition is denoted as M respectively1、M2、M3、…、Mn；
Step 1.2: for each loquat sample Mi, 1 < i < n, after removing exocarp, along pulp equatorial plane to cutting simultaneously
Stoning, removal endocarp, select the cutting planes parallel with equatorial plane to cut pulp, form two end fruit blocks and multiple rings
Shape fruit block, distance is 0.6 centimetre between cutting planes；Pulp both ends fruit block is no longer finely divided cutting, remaining each annular fruit
Block circumferential direction is cut into several pieces in parts, and each annular fruit block circumferential direction is cut into parts during several pieces, if annular fruit block outer ring
Diameter < 1.2 centimetre are then cut into 4 pieces in parts, if 1.2 centimetres < annular fruit block race diameter < 2.4 centimetre, are cut into 8 in parts
Block, if annular fruit block race diameter > 2.4 centimetre, are cut into 12 pieces in parts；It is cut into parts again along pulp thickness direction several
Block, if pulp thickness < 0.6 centimetre, thickness direction are not cut, if 0.6 centimetre < pulp thickness < 1.2 centimetre, thickness direction
It is cut into 2 pieces in parts, if pulp thickness > 1.2 centimetre, thickness direction is cut into 3 pieces in parts；The pulp stripping and slicing of m block is obtained altogether, point
M is not denoted as iti,j, 1 < j < m；
Step 1.3: acquiring each pulp stripping and slicing Mi,jEach side high spectrum image；
Step 1.4: each pulp stripping and slicing M is measured using national standard methodi,jSoluble solid content, and respectively
As pulp stripping and slicing Mi,jSoluble solid content reference value yi,j；
Step 1.5: for each pulp stripping and slicing Mi,j, choose 382nm, 387nm, 406nm, 408nm, 412nm, 456nm,
485nm, 510nm, 539nm, 562nm, 933nm, 967nm, 998nm, 1030nm wavelength are that loquat fruit soluble solid contains
The characteristic wavelength of detection is measured, and obtains pulp stripping and slicing Mi,jAll sides high spectrum image in pulp fraction all pixels point
In the spectrum mean value of each characteristic wavelength, it is denoted as respectively
Step 1.6: using multiple linear regression by pulp stripping and slicing M in step 1.5i,jEach characteristic wavelength spectrum it is average
Value and the pulp stripping and slicing M in step 1.4i,jSoluble solid reference value yi,jIt is associated fitting, establishes prediction model, is closed
Connection process is carried out using following equation of linear regression one:
Establish the quantitative linearity regression equation two for predicting loquat fruit spectral detection soluble solid content:
Step 2: obtaining the soluble solid content distribution map of loquat interior flesh to be measured；
Step 2.1: choosing loquat sample N to be measured；
Step 2.2: stripping and slicing being carried out to loquat sample N to be measured, block cutting method describes method according to step 1.2 and carries out, obtains
Nz, the total p block pulp stripping and slicing of 1 < z < p records pulp stripping and slicing NzIn the space coordinate of loquat sample N to be measured；
Step 2.3: acquisition pulp stripping and slicing NzEach section high spectrum image, and obtain each pixel in image and exist
Characteristic wavelength 382nm, 387nm, 406nm, 408nm, 412nm, 456nm, 485nm, 510nm, 539nm, 562nm, 933nm,
Spectral value at 967nm, 998nm, 1030nm, is denoted as respectively
Wherein, (α, beta, gamma) is the coordinate information of each pixel, and α is abscissa information, and β is ordinate information, and γ is
Section identification information；
Step 2.4: by the loquat fruit stripping and slicing N to be measured in step 2.3zThe each pixel in each section in each characteristic wave
The spectral value of strong point substitutes into the quantitative linearity regression equation two of step 1.6, and the soluble solid of each pixel is calculated
Object predicted value, and the space coordinate according to each pixel in the high spectrum image of place section form pulp stripping and slicing Nz's
The soluble solid content distribution map of each space coordinate；
Step 2.5: the pulp stripping and slicing N obtained according to step 2.4zEach section soluble solid content distribution
Figure and stripping and slicing NzSpace coordinate in sample N obtains soluble solid inside sample N using bicubic interpolation algorithm
The latticed space multistory distribution map of content realizes that loquat adopts the spacing-visible chemical conversion of rear interior flesh soluble solid distribution
Picture.
Claims (3)
1. a kind of method that loquat adopts rear pulp soluble solid distribution imaging, which comprises the following steps:
Step 1: establishing the quantitative linearity regression equation based on loquat fruit spectral detection soluble solid content；
Step 1.1: n loquat sample of acquisition is denoted as M respectively1、M2、M3、…、Mn；
Step 1.2: for each loquat sample Mi, 1 < i < n, remove exocarp after, along pulp equatorial plane to cut and be enucleated,
Endocarp is removed, the cutting planes parallel with equatorial plane is selected to cut pulp, forms two end fruit blocks and multiple annular fruits
Block, distance is 0.6 centimetre between cutting planes；Pulp both ends fruit block is no longer finely divided cutting, remaining each annular fruit block ring
Several pieces are cut into parts to being cut into several pieces in parts, then along pulp thickness direction, are obtained the pulp stripping and slicing of m block altogether, are remembered respectively
For MI, j, 1 < j < m；
Step 1.3: acquiring each pulp stripping and slicing MI, jEach side high spectrum image；
Step 1.4: each pulp stripping and slicing M is measured using national standard methodI, jSoluble solid content, and respectively as
Pulp stripping and slicing MI, jSoluble solid content reference value yi,j；
Step 1.5: for each pulp stripping and slicing MI, j, choose 382nm, 387nm, 406nm, 408nm, 412nm, 456nm,
485nm, 510nm, 539nm, 562nm, 933nm, 967nm, 998nm, 1030nm wavelength are that loquat fruit soluble solid contains
The characteristic wavelength of detection is measured, and obtains pulp stripping and slicing MI, jAll sides high spectrum image in pulp fraction all pixels point
In the spectrum mean value of each characteristic wavelength, it is denoted as respectively
Step 1.6: using multiple linear regression by pulp stripping and slicing M in step 1.5i,jEach characteristic wavelength spectrum mean value with
Pulp stripping and slicing M in step 1.4i,jSoluble solid reference value yi,jIt is associated fitting, establishes prediction model, was associated with
Cheng Caiyong or less equation of linear regression one carries out:
Establish the quantitative linearity regression equation two for predicting loquat fruit spectral detection soluble solid content:
Step 2: obtaining the soluble solid content distribution map of loquat interior flesh to be measured；
Step 2.1: choosing loquat sample N to be measured；
Step 2.2: stripping and slicing being carried out to loquat sample N to be measured, block cutting method describes method according to step 1.2 and carries out, and obtains Nz, 1 < z
The total p block pulp stripping and slicing of < p, records pulp stripping and slicing NzIn the space coordinate of loquat sample N to be measured；
Step 2.3: acquisition pulp stripping and slicing NzEach section high spectrum image, and obtain in image each pixel in feature
Wavelength 382nm, 387nm, 406nm, 408nm, 412nm, 456nm, 485nm, 510nm, 539nm, 562nm, 933nm, 967nm,
Spectral value at 998nm, 1030nm, is denoted as respectively Wherein, (α, β,
It is γ) coordinate information of each pixel, α is abscissa information, and β is ordinate information, and γ is section identification information；
Step 2.4: by the loquat fruit stripping and slicing N to be measured in step 2.3zThe each pixel in each section in each characteristic wave strong point
Spectral value substitute into step 1.6 quantitative linearity regression equation two in, the soluble solid that each pixel is calculated is pre-
Measured value yZ, (α, beta, gamma) ', and the space coordinate according to each pixel in the high spectrum image of place section, form pulp stripping and slicing
NzEach space coordinate soluble solid content distribution map；
Step 2.5: the pulp stripping and slicing N obtained according to step 2.4zEach section soluble solid content distribution map, and
Stripping and slicing NzSpace coordinate in sample N obtains the net of soluble solid content inside sample N using bicubic interpolation algorithm
Lattice space solid distribution map realizes that loquat adopts the spatial visualization imaging of rear interior flesh soluble solid distribution.
2. the method that a kind of loquat according to claim 1 adopts rear pulp soluble solid distribution imaging, feature exist
In in step 1.2, each annular fruit block circumferential direction is cut into parts during several pieces, if annular fruit block race diameter < 1.2 li
Rice, then be cut into 4 pieces in parts, if 1.2 centimetres < annular fruit block race diameter < 2.4 centimetre, are cut into 8 pieces in parts, if annular
Fruit block race diameter > 2.4 centimetre are then cut into 12 pieces in parts.
3. the method that a kind of loquat according to claim 1 adopts rear pulp soluble solid distribution imaging, feature exist
In in step 1.2, when being cut into several pieces in parts along pulp thickness direction, if pulp thickness < 0.6 centimetre, thickness direction is not
Cutting, if 0.6 centimetre<pulp thickness<1.2 centimetre, thickness direction are cut into 2 pieces in parts, if pulp thickness>1.2 centimetre,
Thickness direction is cut into 3 pieces in parts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611001232.4A CN106644957B (en) | 2016-11-14 | 2016-11-14 | A kind of method that loquat adopts rear pulp soluble solid distribution imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611001232.4A CN106644957B (en) | 2016-11-14 | 2016-11-14 | A kind of method that loquat adopts rear pulp soluble solid distribution imaging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106644957A CN106644957A (en) | 2017-05-10 |
| CN106644957B true CN106644957B (en) | 2019-04-05 |
Family
ID=58806224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611001232.4A Active CN106644957B (en) | 2016-11-14 | 2016-11-14 | A kind of method that loquat adopts rear pulp soluble solid distribution imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106644957B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102818777A (en) * | 2012-08-24 | 2012-12-12 | 北京农业智能装备技术研究中心 | Fruit maturity degree evaluation method based on spectrum and color measurement |
| 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 |
| CN103674838A (en) * | 2013-11-12 | 2014-03-26 | 浙江大学 | Hyperspectral imaging technology-based fish fat content distribution detection method |
| CN103822879A (en) * | 2014-02-24 | 2014-05-28 | 西北农林科技大学 | Nondestructive detection method of swelled kiwi fruits based on hyperspectral imaging technology |
| CN104048927A (en) * | 2014-06-27 | 2014-09-17 | 上海理工大学 | Method for detecting soluble solid content of apple |
| CN104062258A (en) * | 2013-05-07 | 2014-09-24 | 山东东阿阿胶股份有限公司 | Method for rapid determination of soluble solids in compound ass-hide glue pulp by near infrared spectroscopy |
| CN104062263A (en) * | 2014-07-11 | 2014-09-24 | 中国农业大学 | Near-infrared universal model detection method for quality indexes of fruits with similar optical and physical properties |
| CN105067531A (en) * | 2014-12-31 | 2015-11-18 | 广西师范学院 | Mango quality nondestructive detection method and mango quality nondestructive detection apparatus |
| CN105115910A (en) * | 2015-08-28 | 2015-12-02 | 中国农业科学院农产品加工研究所 | Method for detecting protein content distribution in peanuts based on hyperspectral imaging technology |
-
2016
- 2016-11-14 CN CN201611001232.4A patent/CN106644957B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102818777A (en) * | 2012-08-24 | 2012-12-12 | 北京农业智能装备技术研究中心 | Fruit maturity degree evaluation method based on spectrum and color measurement |
| 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 |
| CN104062258A (en) * | 2013-05-07 | 2014-09-24 | 山东东阿阿胶股份有限公司 | Method for rapid determination of soluble solids in compound ass-hide glue pulp by near infrared spectroscopy |
| CN103674838A (en) * | 2013-11-12 | 2014-03-26 | 浙江大学 | Hyperspectral imaging technology-based fish fat content distribution detection method |
| CN103822879A (en) * | 2014-02-24 | 2014-05-28 | 西北农林科技大学 | Nondestructive detection method of swelled kiwi fruits based on hyperspectral imaging technology |
| CN104048927A (en) * | 2014-06-27 | 2014-09-17 | 上海理工大学 | Method for detecting soluble solid content of apple |
| CN104062263A (en) * | 2014-07-11 | 2014-09-24 | 中国农业大学 | Near-infrared universal model detection method for quality indexes of fruits with similar optical and physical properties |
| CN105067531A (en) * | 2014-12-31 | 2015-11-18 | 广西师范学院 | Mango quality nondestructive detection method and mango quality nondestructive detection apparatus |
| CN105115910A (en) * | 2015-08-28 | 2015-12-02 | 中国农业科学院农产品加工研究所 | Method for detecting protein content distribution in peanuts based on hyperspectral imaging technology |
Non-Patent Citations (1)
| Title |
|---|
| "采后猕猴桃可溶性固形物含量的高光谱无损检测";董金磊 等;《食品科学》;20151231;第36卷(第6期);第101-106页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106644957A (en) | 2017-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cheng et al. | Pork biogenic amine index (BAI) determination based on chemometric analysis of hyperspectral imaging data | |
| Li et al. | Recent advances in nondestructive analytical techniques for determining the total soluble solids in fruits: a review | |
| CN109100323B (en) | Nondestructive quantitative evaluation method for transmission spectrum of apple water core disease | |
| Quevedo et al. | Determination of senescent spotting in banana (Musa cavendish) using fractal texture Fourier image | |
| CN103065149B (en) | Muskmelon Fruit phenotype is extracted and quantization method | |
| CN106023158B (en) | The fresh water pipless pearl pearly layer defect identification method of SD-OCT images | |
| Nicolaï et al. | Nondestructive evaluation: Detection of external and internal attributes frequently associated with quality and damage | |
| CN101769864B (en) | Inspection apparatus and method | |
| CN103528967B (en) | Overdone indigo fruit fruit identification method based on high spectrum image | |
| Eyarkai Nambi et al. | Comparison of various RGB image features for nondestructive prediction of ripening quality of “Alphonso” mangoes for easy adoptability in machine vision applications: a multivariate approach | |
| Saldaña et al. | Computer vision system in real-time for color determination on flat surface food | |
| CN105606473A (en) | Red globe grape hardness nondestructive detection method based on machine vision | |
| Motonaga et al. | A method of making digital fruit color charts for cultivation management and quality control | |
| CN108152231A (en) | Jujube fruit Inner Defect Testing method and device based on Vis/NIR | |
| Martinez-Vicente et al. | Sensitivity of a satellite algorithm for harmful algal bloom discrimination to the use of laboratory bio-optical data for training | |
| CN106644957B (en) | A kind of method that loquat adopts rear pulp soluble solid distribution imaging | |
| Qi et al. | Establishment of a comprehensive indicator to nondestructively analyze watermelon quality at different ripening stages | |
| Guo et al. | Hyperspectral image analysis for the evaluation of chilling injury in avocado fruit during cold storage | |
| Zhu et al. | Determination and visualization of fat contents in salmon fillets based on visible and near-infrared hyperspectral imagery | |
| Bermúdez et al. | Image analysis for automatic feature estimation of the Mangifera indica fruit | |
| Pan et al. | Prediction of shelled shrimp weight by machine vision | |
| CN111724350A (en) | Nondestructive testing method and device for freshness of fish body | |
| Portalés et al. | An image-based system to preliminary assess the quality of grape harvest batches on arrival at the winery | |
| CN110118735B (en) | Hyperspectral imaging detection method and device for detecting male and female bergamot pears | |
| Li et al. | Rapid assessment of ready-to-eat Xuxiang kiwifruit quality based on chroma recognition and GC-MS analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |