CN105067531A - Mango quality nondestructive detection method and mango quality nondestructive detection apparatus - Google Patents
Mango quality nondestructive detection method and mango quality nondestructive detection apparatus Download PDFInfo
- Publication number
- CN105067531A CN105067531A CN201510298541.1A CN201510298541A CN105067531A CN 105067531 A CN105067531 A CN 105067531A CN 201510298541 A CN201510298541 A CN 201510298541A CN 105067531 A CN105067531 A CN 105067531A
- Authority
- CN
- China
- Prior art keywords
- mango
- information
- unit
- image
- quality
- 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
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The present invention discloses a multi-source information fusion mango internal and external quality intelligent automatic detection method and a multi-source information fusion mango internal and external quality intelligent automatic detection apparatus. The apparatus comprises an illumination system, a hyperspectral imaging system, a bionic electronic nose system and an analysis treatment and control unit. According to the present invention, with the apparatus, the information collected by various separated sensors are subjected to reasonable screening and optimal combination to carry out fault tolerance and complementation so as to carry out comprehensive decision making, such that the discrimination precision and the effectiveness of the whole fusion system are improved so as to establish the automatic evaluation system with characteristics of high precision, high robustness, objective property and rapidness; and with the detection method and the detection apparatus, the detection result consistency of is good, the automation degree is high, the non-contact type non-destructive detection can be achieved, the labor can be released, the human subjective factors can be eliminated, the production efficiency can be improved, and the production cost can be reduced.
Description
Technical field
The present invention relates to fruit quality intelligent automation detection method and device.
Background technology
At present, the research of the Aulomatizeted Detect process in postpartum of domestic and international mango is relative with achievement less.The particularly defects detection aspect of mango, the main unaided eye discrimination by people.For this reason, how fully to explore and the method for the science of excavation is extracted the every qualitative characteristics information of mango with carrying out intelligent automation, analysis and synthesis evaluation, differentiating the quality rank of mango, is the important method using state-of-the-art technology to improve the processing of mango postharvest treatment.
Due to computer technology and electronic technology fast development, the development of the detection technique of fruit external sort is now increasingly mature, photoelectricity classification based on computer vision has been carried out applying widely at fruit external sort detection field, domestic China Agricultural University, Zhejiang University, Agricultural University Of South China, the colleges and universities such as Jiangsu University self-developing have developed the multiple fruit external sort on-line checkingi hierarchy system based on computer vision technique, and carry out industrialization, automatically fruit size is completed once, shape, color, the detection of the external sorts such as defected surface and judge, greatly improve sharpness of separation.
People [2], the Zhang Lihua [3] etc. such as the people such as Wang Jiangfeng [1], PanitnatYimyam, yellow brave equality people [4] have studied the methods and applications detected based on the Mango Weight of computer vision technique and defected surface and corrupted respectively; The common radiothermy near infrared spectrum (700 ~ 1100nm) of scholar Sirinnapa and SumioKawano of Thailand and Japan etc. [5] has carried out transmission spectrum analysis to mango, and establishing the mathematical model of dry matter content, soluble solid and transmitted spectrum respectively, related coefficient is respectively 0.96 and 0.93; The people [7] such as the people such as Yu Jiajia [6], Cao Xia apply the Non-Destructive Testing research that near infrared spectrum data analytical technology carries out mango acidity and pol respectively; Slaughter the detect delay that people [8] the application Near-Infrared Quantitative Analysis technology such as Zhenhua have carried out mango inside quality, by partial least-square regression method in 580 ~ 1000nm spectral range, establish the Near-Infrared Quantitative Analysis model of mango soluble solid (pol) and hardness respectively; The people such as Hui Guohua have studied the method detecting mango freshness with Electronic Nose and surface acoustic wave detection examination respectively, and apply for Patents (Hui Guohua, Wu Yuling, Ye Dandan, Ding Wenwen, utilize a method for detection by electronic nose mango freshness, application publication number CN102621192A; Hui Guohua, Ding Wenwen, Ye Dandan, Wu Yuling, a kind of method utilizing surface acoustic wave detection instrument to detect mango freshness, application publication number CN102608215A); The people [10] such as strong equality people [9], Yang Zhiwei utilize computer vision analysis technology automatically to detect mango respectively and classification is studied, but detected object and classification foundation are only utilize mango surface characteristics, do not consider the inside quality feature of mango.
Although the fruit external sort detection technique based on traditional computer vision is ripe gradually, its inside quality to fruit detects helpless.Machine vision analysis and detection technology only can detect exterior color, shape, size and surface imperfection, and easily by defect area with, not easily detect the inherent vices such as slight damage, internal injury and disease infection; Inner Defect Testing often adopts disruptive method to inspect by random samples, and fruit, once destroyed, just loses commercial value, and this method can not ensure the fruit zero defect do not inspected by random samples.Spectral technique especially near-infrared spectrum technique is the quantitative measurement carried out the Absorption Characteristics characteristic of near infrared spectrum according to a certain chemical composition, is applicable to very much the defects detection of fruit physics and chemistry composition detection, fruit metamorphic types, as rotten defect etc.But near-infrared spectrum technique can not gather the spatial information of measurand, can only detect in a region, larger error may be caused like this, and easily may bring much noise interfere information by environmental factor (as factor impacts such as temperature and humidities) impact, and the efficiency that impact detects and precision.
List of references:
[1] Wang Jiangfeng, Luo Xiwen, Hong Tiansheng etc. the application of computer vision technique in Mango Weight and fruit face corrupted detect. Transactions of the Chinese Society of Agricultural Engineering .1998,14 (4): 186-18
[2]PYimyam,TChalidabhongse,PSirisomboon,eta.lPhysicalpropertiesanalysisofmangousingcomputervision[C]//ProceedingofInternationalConferenceonControlAutomationandSystems(ICCAS.05).Korea,2005.
[3] Zhang Lihua, the mango detection method of surface flaw based on computer vision studies [D], Nanning: Guangxi University, 2006
[4] Huang Yongping, article brightness, Liu Jing. appliance computer vision studies [J] to the differentiation of mango surface imperfection, Fujian hotwork science and technology, 2008,33 (1): 4-6.
[5]SirinnapaSaranwong,JindaSornsrivichai,SumioKawano.Predictionofripe-stageeatingqualityofmangofruitfromitsharvestqualitymeasurednondestructivelybynearinfraredspectroscopy[J].PostharvestBiologyandTechnology,2004,31(2):137-145
[6] Yu Jiajia, He Yong, Bao Yidan. based on mango pol acidity Study on nondestructive detection method [J] of spectral technique, spectroscopy and spectral analysis, 2008,128 (112): 2839-2842.
[7] Cao Xia, Zhou Xuecheng, Fan Pinliang. based on the mango pol Study on nondestructive detection method [J] of near-infrared diffuse reflection spectrum technology, agricultural research, 2013,1:177-180.
[8] slaughter Zhenhua, nationality is kept tie, Meng Chaoying, Zhu great Zhou, Shi Bolin, and celebrating million is female. the CCD-NIR non destructive testing research [J] of mango inside quality, spectroscopy and spectral analysis, 2008,28 (10): 111-112.
[9] Zhang Lieping, Zeng Aiqun, Chen Ting. the mango based on computer vision and neural network detects and grade separation [J], agricultural research, 2008,10:57-60. is (by processing the mango surface image obtained, be extracted 9 characteristic parameters, the geometry depicting mango is more all sidedly levied, and using each characteristic parameter as input, creates the surface imperfection of 3 layers of BP neural network model identification mango based on MATLAB)
[10] Yang Zhiwei, Yin Xiuhua. the application of image procossing in mango sorts automatically [J], hubei agricultural science, 2009,48 (8): 1992-1995. (shooting digital photo take Computer imaging analysis system as means, gathers mango color parameter.Study Color Characteristic relevant to mango quality comparison in 3 kinds of color model, summarize relational expression between suitable color parameter and mango quality index values, for the degree of ripeness of mango of deriving; And through image procossing and computing, extract required physical dimension and the data of mutable site, the foundation as sample classification)
Tang Huizhou. the progress [J] that Electronic Nose is applied in fruit quality evaluation system, packaging and food machinery, 2011,29 (1): 51-54
Summary of the invention
The deficiency in mango quality is being detected for prior art, the object of the present invention is to provide a kind of relevant information that can obtain mango from multiple angle such as image, spectrum and smell, and much information fusion is got up mango quality to be carried out to the method and apparatus of intelligent automation detection.In order to realize the image information of goal of the invention the present invention by Hyperspectral imager acquisition mango, then from image information, extract the surface of mango, and collect the spectral information of mango, from spectral information, extract the internal feature of mango; From smell sensor, gather the smell response spectra information that smell sensor evaporates mango, the characteristic information such as composition and concentration therefrom extracting the smell that mango evaporates judges mango partial interior quality; Finally, by the characteristics of image of mango and spectral signature and odor characteristics by information fusion technology, classification differentiation is carried out to integrated quality inside and outside mango.
In order to realize foregoing invention object, the invention provides a kind of mango quality damage-free detection method, it is characterized in that comprising the following steps:
Step 1, mango sample choice, by manually choosing the ripe mango of a collection of a certain kind as training sample, and carries out handmarking to the quality of these mango;
Step 2, carries out the collection of spectrum and image information to mango;
Step 3, to spectrum and Image Information Processing;
Step 4, to the extraction of spectrum and image information;
Step 5, utilizes bionic electronic nose to gather the odiferous information of mango;
Step 6, extracts the odor characteristics information of mango;
Step 7, through process and extract EO-1 hyperion and odiferous information carry out multi-source information Fusion Features;
Step 8, builds mango quality Multi-source Information Fusion evaluation model;
Step 9, carries out the operational processes of step (2) to step (7) successively to mango to be detected;
Step 10, evaluates the model of step (9) acquired results input step (8) gained, finally obtains the mango quality judging result that evaluation model exports.
In described step 1, sample preferably at least chooses 30.
The disposal route of spectral information described in step 3 is that data and curves black and white corrects or Savitzky-Golay convolution smoothing method.
The disposal route of image information described in step 3 comprises image rectification, Image Denoising by Use, the image zooming-out in characteristic wave bands region, image enhaucament and content analysis process.
The extraction of hyperspectral information described in step 4 comprises the information of the fruit stone size of mango, acidity, hardness and soluble solid.
Image information described in step 4 extract comprise mango size, fruit shape, painted, appearance defect characteristic parameter and defect area geometry state information.
Information described in step 6 comprises the degree of ripeness of mango, corrupt information of rotting and disease and insect information.
The method merged described in step 7 is mapped to higher dimensional space by unified approach to carry out the process of multi-source information Fusion Features.
The method building model described in step 8 passes through Nonlinear Modeling.
Present invention also offers a kind of mango quality nondestructive testing device, comprising: for gathering the unit of mango spectral information; For the unit to spectral information process; For the unit to withdrawing spectral information; For the unit of the image information collecting to mango; For the unit to the mango Image Information Processing of collecting; For the unit extracted further treated mango image information; Bionic electronic nose unit; To the unit that the odiferous information of bionic electronic nose collection extracts; EO-1 hyperion through processing and extract and odiferous information are carried out the unit of multi-source information Fusion Features; Mango quality Multi-source Information Fusion evaluation model construction unit; For the control module of the input and output of data between unit; Mango quality judging result output unit.
Beneficial effect of the present invention shows:
(1) the simple deficiency relying on certain single automatic testing method is overcome, the relevant information of mango inside and outside quality can be obtained from multiple angle such as the image information of mango, spectral information, volatile gas information, and much information is merged to get up to carry out Intelligent Measurement, utilize complementarity and the redundancy of above-mentioned 3 kinds of information, mutually empirical test is carried out between each information, mutually make up, and then improve the accuracy that checkout equipment detects mango inside and outside quality, avoid the blindness in checkout equipment testing process;
(2) corresponding device can be arranged on laboratory and mango aft-loaded airfoil process for producing line and realize online automatic detection, assist and replace professional, compared with artificial sense detection method, testing result consistance is good, and automaticity is high, can realize contactless, Non-Destructive Testing, liberation labour, gets rid of artificial subjective factor, can enhance productivity, reduce production cost.
Accompanying drawing illustrates:
Fig. 1 is apparatus of the present invention structural representations;
Fig. 2 is the process flow diagram of mango quality damage-free detection method;
Fig. 3 is high-spectral data preprocessing process figure;
Fig. 4 is high spectrum image preprocessing process figure;
Fig. 5 is multi-source feature information extraction thinking figure.
Embodiment:
The invention provides is a kind of mango inside and outside quality autonomous detection method and device of Multi-source Information Fusion, the information of the sensor collection of each separation is rationally screened and optimal combination, so that decision making package is carried out in fault-tolerant, complementation, and then improve the precision differentiated and the validity improving whole emerging system.A kind of pinpoint accuracy, high robust, objective, automatic Evaluation system fast can be set up, greatly can improve the gentle level of intelligence of Automated water of mango postharvest treatment processing, significant economic benefit and social benefit can be obtained.
Embodiment 1
This method comprises two total steps, the modeling process 101 of the training of first sample and mango testing process 102, and obtain concrete testing result in the model that 101 processes that then substituted into by 102 acquired results generate, its detailed process is as follows:
(1) choose the ripe mango of a collection of a certain kind as training sample according to country or industry about mango quality standard by artificial, and carry out handmarking to the quality of these mango, each qualities selects the mango sample of 30;
(2) Hyperspectral imager is utilized to gather spectroscopic data information and the image information of mango; And gather with the smell sensor of bionic nasus system the smell response spectra data message that mango evaporates;
(3) spectroscopic data pre-service, comprise data and curves black and white correct and with Savitzky-Golay convolution smoothing method (the detail with reference beam ease official communication of more Savitzky-Golay convolution smoothing methods and Yu Ruqin " analytical chemistry handbook (10)--the Chemical Measurement " of writing. Beijing: chemical industry publishing house, 2001) the spectrum curve of spectrum baseline wander that becomes the impact of the non-quality information in image information (as the diffuse transmission influence that surperficial inequality has been tempted) and instrument noise and dark current to cause ingeniously and anisomerism is removed, between heterogeneity, mutual thousand disturb the multicollinearity and contextual factor that cause to the impact of the curve of spectrum, and carry out curve of spectrum analysis, find and select all kinds of quality mango curve of spectrum to have the wave band of marked difference as characteristic wave bands (concrete steps and thinking are as Fig. 4),
Wherein, the computing formula of Savitzky-Golay convolution smoothing method is as follows:
(4) Image semantic classification, comprises the process (concrete steps and thinking are as Fig. 5) such as image rectification, Image Denoising by Use, the image zooming-out of characteristic wave bands area-of-interest, image enhaucament and content analysis;
(5) carry out spectral signature information extraction, image feature information extracts and smell feature information extraction operates, and comprises following content of operation:
1. to analyze from high-spectral data and the characteristic information extracted comprises fruit stone size, acidity, the characteristic information such as hardness and soluble solid of mango;
2. to analyze from high spectrum image and the characteristic information extracted comprises the characteristic informations such as the size of mango, fruit shape, painted, appearance defect characteristic parameter and defect area geometry state;
3. the characteristic information also extracted from the mango smell response spectra data analysis of smell sensor comprises the degree of ripeness of mango, the rotten characteristic information such as corrupt information and disease and insect information;
(6) multi-source information Fusion Features is carried out.The spectral signature information of extraction, image feature information and smell characteristic information are mapped to higher dimensional space by unified approach and carry out the process of multi-source information Fusion Features;
(7) take out by principal component analysis (PCA) the fusion feature space that some crucial virtual feature variablees characterize higher-dimension, with convenient modelling operability and raising model quality;
(8) utilize the non-linear modeling methods such as neural network, build mango quality Multi-source Information Fusion evaluation model;
(9) operational processes of step (2) to step (7) is carried out successively to mango to be detected;
(10) model of step (9) acquired results input step (8) gained is evaluated, finally obtain the mango quality judging result that evaluation model exports.
Embodiment 2
Present invention also offers a kind of mango quality nondestructive testing device as shown in Figure 1, comprising:
Gather the device of mango spectral information;
For the unit to spectral information process;
For the unit to withdrawing spectral information;
The image information collecting device of mango;
For the unit to the mango Image Information Processing of collecting;
For the unit extracted further treated mango image information;
Bionic nasal devices;
To the device that the odiferous information of bionic electronic nose collection extracts;
EO-1 hyperion through processing and extract and odiferous information are carried out the unit of multi-source information Fusion Features;
Mango quality Multi-source Information Fusion evaluation model construction unit;
For the control module of the input and output of data between unit;
Mango quality judging result output unit.
Claims (10)
1. a mango quality damage-free detection method, is characterized in that comprising the following steps:
Step 1, mango sample choice, by manually choosing the ripe mango of a collection of a certain kind as training sample, and carries out handmarking to the quality of these mango;
Step 2, carries out the collection of spectrum and image information to mango;
Step 3, to spectrum and Image Information Processing;
Step 4, to the extraction of spectrum and image information;
Step 5, utilizes bionic electronic nose to gather the odiferous information of mango;
Step 6, extracts the odor characteristics information of mango;
Step 7, through process and extract EO-1 hyperion and odiferous information carry out multi-source information Fusion Features;
Step 8, builds mango quality Multi-source Information Fusion evaluation model;
Step 9, carries out the operational processes of step (2) to step (7) successively to mango to be detected;
Step 10, evaluates the model of step (9) acquired results input step (8) gained, finally obtains the mango quality judging result that evaluation model exports.
2. the method for claim 1, is characterized in that: in described step 1, sample at least chooses 30.
3. the method for claim 1, is characterized in that: the disposal route of spectral information described in step 3 is that data and curves black and white corrects or Savitzky-Golay convolution smoothing method.
4. the method for claim 1, is characterized in that: the disposal route of image information described in step 3 comprises image rectification, Image Denoising by Use, the image zooming-out in characteristic wave bands region, image enhaucament and content analysis process.
5. the method for claim 1, is characterized in that: the extraction of hyperspectral information described in step 4 comprises the information of the fruit stone size of mango, acidity, hardness and soluble solid.
6. the method for claim 1, is characterized in that: image information described in step 4 extract comprise mango size, fruit shape, painted, appearance defect characteristic parameter and defect area geometry state information.
7. the method for claim 1, is characterized in that: information described in step 6 comprises the degree of ripeness of mango, corrupt information of rotting and disease and insect information.
8. the method for claim 1, is characterized in that: the method merged described in step 7 is mapped to higher dimensional space by unified approach to carry out the process of multi-source information Fusion Features.
9. the method for claim 1, is characterized in that: the method building model described in step 8 passes through Nonlinear Modeling.
10. a mango quality nondestructive testing device, comprising: for gathering the unit of mango spectral information; For gathering the unit of mango image information; For the unit to spectral information process; For the unit to withdrawing spectral information; For the unit of the image information collecting to mango; For the unit to the mango Image Information Processing of collecting; For the unit extracted further treated mango image information; Bionic electronic nose unit; To the unit that the odiferous information of bionic electronic nose collection extracts; EO-1 hyperion through processing and extract and odiferous information are carried out the unit of multi-source information Fusion Features; Mango quality Multi-source Information Fusion evaluation model construction unit; For the control module of the input and output of data between unit; Mango quality judging result output unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510298541.1A CN105067531A (en) | 2014-12-31 | 2015-06-04 | Mango quality nondestructive detection method and mango quality nondestructive detection apparatus |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410848082 | 2014-12-31 | ||
| CN201510298541.1A CN105067531A (en) | 2014-12-31 | 2015-06-04 | Mango quality nondestructive detection method and mango quality nondestructive detection apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105067531A true CN105067531A (en) | 2015-11-18 |
Family
ID=54496955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510298541.1A Pending CN105067531A (en) | 2014-12-31 | 2015-06-04 | Mango quality nondestructive detection method and mango quality nondestructive detection apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105067531A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106290238A (en) * | 2016-08-09 | 2017-01-04 | 西北农林科技大学 | A kind of apple variety method for quick identification based on high light spectrum image-forming |
| CN106644957A (en) * | 2016-11-14 | 2017-05-10 | 浙江大学 | Pulp soluble solid distribution imaging method of loquat after picking |
| CN107300536A (en) * | 2017-08-25 | 2017-10-27 | 天津商业大学 | Soluble solid content Forecasting Methodology after mango impact injury based on EO-1 hyperion |
| CN107609111A (en) * | 2017-09-13 | 2018-01-19 | 福建省农业科学院果树研究所 | The search method that a kind of loquat Variety identification, quality grading and maturity judge |
| CN108760829A (en) * | 2018-03-20 | 2018-11-06 | 天津大学 | A kind of electronic nose recognition methods based on bionical olfactory bulb model and convolutional neural networks |
| CN109145685A (en) * | 2017-06-19 | 2019-01-04 | 南京农业大学 | Fruits and vegetables EO-1 hyperion quality detecting method based on integrated study |
| CN109342331A (en) * | 2018-11-05 | 2019-02-15 | 贵阳学院 | Plum rigidity nondestructive testing method based on Vis/NIR technology |
| CN109374538A (en) * | 2018-11-12 | 2019-02-22 | 沈阳农业大学 | A kind of colorimetric card determining Blueberry maturity grade |
| CN109562585A (en) * | 2016-09-30 | 2019-04-02 | 米其林集团总公司 | The method leaked by odor detection tire-mold bladder |
| CN110020604A (en) * | 2019-03-11 | 2019-07-16 | 潍坊学院 | A kind of quality of vegetable detection method and system |
| CN111161237A (en) * | 2019-12-27 | 2020-05-15 | 中山德著智能科技有限公司 | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof |
| CN111632852A (en) * | 2020-05-30 | 2020-09-08 | 安徽昭日农业科技有限公司 | Dehydrated vegetable raw material quality detection system |
| CN112697984A (en) * | 2020-12-11 | 2021-04-23 | 河北工业大学 | Fruit defect nondestructive testing method based on neural network and fruit grading method |
| CN114354508A (en) * | 2021-12-31 | 2022-04-15 | 深圳铯敏发科技有限公司 | Wisdom agricultural plant support system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1995987A (en) * | 2007-02-08 | 2007-07-11 | 江苏大学 | Non-destructive detection method and device for agricultural and animal products based on hyperspectral image technology |
| JP2012122876A (en) * | 2010-12-09 | 2012-06-28 | Yanmar Co Ltd | Internal quality inspection device for long agricultural product |
| CN102788794A (en) * | 2012-07-30 | 2012-11-21 | 江苏大学 | Device and method for detecting pesticide residues on leaves of leaf vegetables on basis of multi-sensed information fusion |
| CN103278464A (en) * | 2013-04-18 | 2013-09-04 | 北京工商大学 | Method and device for fish flesh detection |
-
2015
- 2015-06-04 CN CN201510298541.1A patent/CN105067531A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1995987A (en) * | 2007-02-08 | 2007-07-11 | 江苏大学 | Non-destructive detection method and device for agricultural and animal products based on hyperspectral image technology |
| JP2012122876A (en) * | 2010-12-09 | 2012-06-28 | Yanmar Co Ltd | Internal quality inspection device for long agricultural product |
| CN102788794A (en) * | 2012-07-30 | 2012-11-21 | 江苏大学 | Device and method for detecting pesticide residues on leaves of leaf vegetables on basis of multi-sensed information fusion |
| CN103278464A (en) * | 2013-04-18 | 2013-09-04 | 北京工商大学 | Method and device for fish flesh detection |
Non-Patent Citations (1)
| Title |
|---|
| 徐爽 等: "高光谱图像技术在水果品质检测中的研究进展", 《食品研究与开发》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106290238A (en) * | 2016-08-09 | 2017-01-04 | 西北农林科技大学 | A kind of apple variety method for quick identification based on high light spectrum image-forming |
| CN109562585A (en) * | 2016-09-30 | 2019-04-02 | 米其林集团总公司 | The method leaked by odor detection tire-mold bladder |
| CN106644957B (en) * | 2016-11-14 | 2019-04-05 | 浙江大学 | A kind of method that loquat adopts rear pulp soluble solid distribution imaging |
| CN106644957A (en) * | 2016-11-14 | 2017-05-10 | 浙江大学 | Pulp soluble solid distribution imaging method of loquat after picking |
| CN109145685A (en) * | 2017-06-19 | 2019-01-04 | 南京农业大学 | Fruits and vegetables EO-1 hyperion quality detecting method based on integrated study |
| CN109145685B (en) * | 2017-06-19 | 2021-11-12 | 南京农业大学 | Fruit and vegetable hyperspectral quality detection method based on ensemble learning |
| CN107300536A (en) * | 2017-08-25 | 2017-10-27 | 天津商业大学 | Soluble solid content Forecasting Methodology after mango impact injury based on EO-1 hyperion |
| CN107609111A (en) * | 2017-09-13 | 2018-01-19 | 福建省农业科学院果树研究所 | The search method that a kind of loquat Variety identification, quality grading and maturity judge |
| CN107609111B (en) * | 2017-09-13 | 2020-11-20 | 福建省农业科学院果树研究所 | Retrieval method for variety identification, quality grading and maturity judgment of loquat fruits |
| CN108760829A (en) * | 2018-03-20 | 2018-11-06 | 天津大学 | A kind of electronic nose recognition methods based on bionical olfactory bulb model and convolutional neural networks |
| CN109342331A (en) * | 2018-11-05 | 2019-02-15 | 贵阳学院 | Plum rigidity nondestructive testing method based on Vis/NIR technology |
| CN109374538A (en) * | 2018-11-12 | 2019-02-22 | 沈阳农业大学 | A kind of colorimetric card determining Blueberry maturity grade |
| CN110020604A (en) * | 2019-03-11 | 2019-07-16 | 潍坊学院 | A kind of quality of vegetable detection method and system |
| CN110020604B (en) * | 2019-03-11 | 2021-09-17 | 潍坊学院 | Vegetable quality detection method and system |
| CN111161237A (en) * | 2019-12-27 | 2020-05-15 | 中山德著智能科技有限公司 | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof |
| CN111632852A (en) * | 2020-05-30 | 2020-09-08 | 安徽昭日农业科技有限公司 | Dehydrated vegetable raw material quality detection system |
| CN112697984A (en) * | 2020-12-11 | 2021-04-23 | 河北工业大学 | Fruit defect nondestructive testing method based on neural network and fruit grading method |
| CN114354508A (en) * | 2021-12-31 | 2022-04-15 | 深圳铯敏发科技有限公司 | Wisdom agricultural plant support system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105067531A (en) | Mango quality nondestructive detection method and mango quality nondestructive detection apparatus | |
| CN105092579A (en) | Mango quality non-destructive testing device | |
| CN101251526B (en) | Method and apparatus for nondestructively testing food synthetic quality | |
| CN101949686A (en) | Online nondestructive testing (NDT) method and device for comprehensive internal/external qualities of fruits | |
| CN107478598A (en) | A kind of near-infrared spectral analytical method based on one-dimensional convolutional neural networks | |
| CN106841103A (en) | Near infrared spectrum detects fruit internal quality method and dedicated test system | |
| CN101915744A (en) | Near infrared spectrum nondestructive testing method and device for material component content | |
| CN106442525B (en) | Online detection method for walnut internal shriveling defect | |
| CN102788794A (en) | Device and method for detecting pesticide residues on leaves of leaf vegetables on basis of multi-sensed information fusion | |
| CN106872370A (en) | Anthocyanin content method for measuring in a kind of red bayberry based on EO-1 hyperion | |
| CN105628708A (en) | Quick nondestructive testing method for multi-parameter quality of south Xinjiang red dates | |
| CN115184283B (en) | Intelligent screening method and system for traditional Chinese medicine decoction pieces | |
| CN102937575B (en) | Watermelon sugar degree rapid modeling method based on secondary spectrum recombination | |
| Wang et al. | NIR based wireless sensing approach for fruit monitoring | |
| CN103868857A (en) | Pesticide residue detection method, device and system | |
| CN103411895B (en) | Pseudo-near infrared spectrum identification method mixed by pearl powder | |
| CN111537469A (en) | Apple quality rapid nondestructive testing method based on near-infrared technology | |
| CN201156043Y (en) | Non-destruction detector for synthetic quality of food | |
| CN106950186A (en) | Countryside Egg or foreign egg kind detection means and its method based on fiber spectrum | |
| CN105738311A (en) | Apple sweetness non-damage quick detection method based on near-infrared spectrum technology | |
| CN105158178A (en) | Rapid modeling method for detecting sugar content of navel orange based on spectral peak area in high spectral transmission technology | |
| CN108398400B (en) | Method for nondestructive testing of fatty acid content in wheat by terahertz imaging | |
| Zhang et al. | Analysis of moisture and total sugar content of Huizao based on surface images | |
| CN113933247A (en) | Construction method of fruit maturity detection model | |
| CN105699302A (en) | Method for determining main nutritional ingredients of apples by means of spectral method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151118 |