CN210533976U - Kiwi fruit maturity fast discrimination device - Google Patents
Kiwi fruit maturity fast discrimination device Download PDFInfo
- Publication number
- CN210533976U CN210533976U CN201920687163.XU CN201920687163U CN210533976U CN 210533976 U CN210533976 U CN 210533976U CN 201920687163 U CN201920687163 U CN 201920687163U CN 210533976 U CN210533976 U CN 210533976U
- Authority
- CN
- China
- Prior art keywords
- maturity
- box body
- spectrophotometer
- image acquisition
- hyperspectral image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 235000009436 Actinidia deliciosa Nutrition 0.000 title claims abstract description 29
- 244000298697 Actinidia deliciosa Species 0.000 title claims abstract description 28
- 238000003384 imaging method Methods 0.000 claims description 12
- 238000012546 transfer Methods 0.000 claims description 6
- 238000013519 translation Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 19
- 235000013399 edible fruits Nutrition 0.000 abstract description 9
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 2
- 230000003595 spectral effect Effects 0.000 description 16
- 238000011156 evaluation Methods 0.000 description 13
- 238000000034 method Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 244000298715 Actinidia chinensis Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000005078 fruit development Effects 0.000 description 1
- 230000005571 horizontal transmission Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000050 nutritive effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The utility model discloses a rapid kiwi fruit maturity judging device, which relates to the technical field of fruit detection and solves the problems that the existing kiwi fruit maturity detection method is not only tedious and time-consuming, but also can not collect a large number of samples; in addition, the current detection method also damages fruits and has lower accuracy of prediction results, and the technical scheme has the key points that: comprises a computer, a box body and a horizontal conveying piece arranged in the box body; the inner wall of the box body is provided with a spectrophotometer, a hyperspectral image acquisition component and at least one light source component; the spectrophotometer and the hyperspectral image acquisition part are connected with the computer, and the kiwi fruit maturity detection system has the effects of quickly, accurately, nondestructively and massively detecting the maturity of kiwi fruits and improving the actual production efficiency of kiwi fruits.
Description
Technical Field
The utility model relates to a fruit detects technical field, and more specifically says that it relates to a quick discriminating gear of kiwi fruit maturity.
Background
The kiwi fruit has high nutritive value and the reputation of 'the king of fruit'. The Chinese kiwi fruit cultivation area is the first world, and the species accounts for 90% of the world. Generally, in the actual production process, the kiwi fruits which are not ripe yet are frequently picked so as to prolong the storage period of the kiwi fruits; however, if the fruits are picked too early, the fruits are too hard and hard to affect the taste, and are easily damaged by cold; if picked too late, the fruit is too soft, rotten and difficult to store. Therefore, the key to reducing storage loss and ensuring the quality of the kiwi fruits is to determine the proper picking maturity.
At present, the mode for determining the ripeness of the kiwi fruit at home and abroad is mainly to determine the ripeness of the kiwi fruit by combining chemical analysis and instruments and detecting indexes such as sugar degree, hardness, moisture and the like in the fruit development process. These methods are not only cumbersome and time consuming, but also unable to collect a large number of samples; in addition, the current detection method also damages fruits, and the accuracy of prediction results is low.
Therefore, how to design a device capable of rapidly and nondestructively detecting the maturity of the kiwi fruit is a problem which is urgently needed to be solved at present.
SUMMERY OF THE UTILITY MODEL
The utility model aims at providing a quick discriminating gear of kiwi fruit maturity has and carries out quick, accurate, harmless, batch detection to the kiwi fruit maturity, improves the effect of kiwi fruit actual production efficiency.
The above technical purpose of the present invention can be achieved by the following technical solutions: a device for rapidly judging the maturity of kiwi fruits comprises a computer, a box body and a horizontal conveying member arranged in the box body; the inner wall of the box body is provided with a spectrophotometer, a hyperspectral image acquisition component and at least one light source component; and the spectrophotometer and the hyperspectral image acquisition component are both connected with a computer.
By adopting the technical scheme, the hyperspectral image acquisition component and the spectrophotometer respectively acquire the spectral data and the color information of the detected object and transmit the spectral data and the color information to the maturity judging model in the computer; the maturity judging model carries out prediction evaluation on the maturity of the detected object according to the spectral data and the color information and outputs a corresponding prediction evaluation result; the maturity of the detected object can be detected quickly, accurately, nondestructively and in batches, and the actual production efficiency of the detected object is improved.
The utility model discloses further set up to: the spectrophotometer is a Ci7860 desktop spectrophotometer.
By adopting the technical scheme, the accuracy of color information acquisition of the detection object is convenient to improve.
The utility model discloses further set up to: the hyperspectral image acquisition part comprises a lens, an imaging spectrometer and a camera connected with a computer, wherein the lens is connected with the imaging spectrometer, and the imaging spectrometer is connected with the camera.
By adopting the technical scheme, the hyperspectral image acquisition operation of the detected object is convenient by utilizing the lens, the imaging spectrometer and the camera.
The utility model discloses further set up to: the box body is provided with two light source pieces which are symmetrically arranged on the side wall of the box body; both of the light source members are obliquely directed to the horizontal transfer member.
By adopting the technical scheme, the detection dead angle of the detection object can be reduced conveniently, and the accuracy of judging the maturity of the detection object is improved.
The utility model discloses further set up to: the light source is a diffuse reflection light source.
By adopting the technical scheme, the hyperspectral image acquired by the hyperspectral image acquisition part is clearer.
The utility model discloses further set up to: the horizontal conveying piece is a precise dustproof electric translation table.
By adopting the technical scheme, the stability of the detection object in the horizontal conveying process is convenient to enhance.
The utility model discloses further set up to: the hyperspectral image acquisition piece is vertically arranged on the top wall of the box body, and the spectrophotometer is vertically connected with the side wall of the box body through a driving cylinder; the driving cylinder is electrically connected with the horizontal conveying member.
By adopting the technical scheme, after the horizontal conveying piece is started, the horizontal conveying piece intermittently conveys the detection object; when the horizontal conveying member stops intermittently, the driving cylinder is started immediately and drives the spectrophotometer to horizontally approach the detected object; after the spectrophotometer collects the color information of the detection object, the driving cylinder returns to the initial position, and the horizontal conveying member is started to continue conveying the detection object, so that the influence of exposure on the color information collection accuracy of the spectrophotometer is reduced.
To sum up, the utility model discloses following beneficial effect has: the hyperspectral image acquisition component and the spectrophotometer respectively acquire spectral data and color information of a detected object and transmit the spectral data and the color information to a maturity judging model in the computer; the maturity judging model carries out prediction evaluation on the maturity of the detected object according to the spectral data and the color information and outputs a corresponding prediction evaluation result; the maturity of the detected object is convenient to carry out rapid, accurate, nondestructive and batch detection, and the actual production efficiency of the detected object is improved; when the horizontal conveying member stops intermittently, the driving cylinder is started immediately to drive the spectrophotometer to horizontally approach to the detection object, so that the influence of exposure on the accuracy of color information acquisition of the spectrophotometer is reduced.
Drawings
Fig. 1 is a schematic structural diagram in an embodiment of the present invention.
In the figure: 1. a box body; 11. a hyperspectral image acquisition component; 12. a camera; 13. an imaging spectrometer; 14. a lens; 15. a light source element; 16. a spectrophotometer; 17. a horizontal transfer member; 18. The cylinder is driven.
Detailed Description
The present invention will be described in further detail with reference to fig. 1.
Example 1: a device for rapidly judging the maturity of kiwi fruits is shown in figure 1 and comprises a computer (not shown in the figure), a box body 1 and a horizontal conveying member 17 arranged in the box body 1. The inner wall of the box body 1 is provided with a spectrophotometer 16, a hyperspectral image acquisition component 11 and at least one light source component 15. The spectrophotometer 16 and the hyperspectral image acquisition part 11 are both connected with a computer. The hyperspectral image acquisition component 11 and the spectrophotometer 16 respectively acquire spectral data and color information of a detected object and transmit the spectral data and the color information to a maturity judging model in a computer. The maturity judging model carries out prediction evaluation on the maturity of the detected object according to the spectral data and the color information, and outputs a corresponding prediction evaluation result, so that the maturity of the detected object can be rapidly, accurately, nondestructively detected in batches, and the actual production efficiency of the detected object is improved. The detector in this embodiment is kiwi fruit, still can be other fruit or agricultural product.
In this embodiment, the spectrophotometer 16 is a Ci7860 desktop spectrophotometer 16, which facilitates to improve the accuracy of color information collection of the detected object.
The hyperspectral image acquisition part 11 comprises a lens 14, an imaging spectrometer 13 and a camera 12 connected with a computer, wherein the lens 14 is connected with the imaging spectrometer 13, and the imaging spectrometer 13 is connected with the camera 12. The lens 14, the imaging spectrometer 13 and the camera 12 are utilized, so that the hyperspectral image acquisition operation of the detected object is convenient.
The box body 1 is provided with two light source parts 15 which are symmetrically arranged on the side wall of the box body 1. The two light source parts 15 are inclined to point to the horizontal conveying part 17, so that the situation that detection dead angles exist in the detected object is reduced, and the accuracy of judging the maturity of the detected object is improved.
In this embodiment, the light source 15 is a diffuse reflection light source, so that the hyperspectral image acquired by the hyperspectral image acquisition component 11 is clearer.
In this embodiment, the horizontal transfer member 17 is a precise dustproof electric translation stage, which is convenient for enhancing the stability of the detected object in the horizontal transfer process.
The hyperspectral image acquisition component 11 is vertically arranged on the top wall of the box body 1, and the spectrophotometer 16 is vertically connected with the side wall of the box body 1 through the driving cylinder 18. The driving cylinder 18 is electrically connected to the horizontal transfer member 17. After the horizontal conveyance member 17 is started, the horizontal conveyance member 17 intermittently conveys the test object. When the horizontal transmission member 17 stops intermittently, the driving cylinder 18 is immediately started to drive the spectrophotometer 16 to horizontally approach the test object. After the spectrophotometer 16 finishes collecting the color information of the detected object, the driving cylinder 18 returns to the initial position and the horizontal conveying member 17 is started to continue conveying the detected object, so that the influence of the exposure of the spectrophotometer 16 on the accuracy of collecting the color information is reduced.
In this embodiment, the operation steps of the maturity rapid determination apparatus are as follows:
step 1, performing spectrum scanning on a detected object through a hyperspectral image acquisition part 11, and performing black and white correction on an acquired hyperspectral image of the detected object.
And 2, extracting the spectral reflectivity of the hyperspectral image interesting area through ENVI5.4 image processing software to obtain a spectral curve of the detected object.
And 3, preprocessing the original spectrum of the detected object by adopting standard normal transformation to eliminate the influence of surface scattering and optical path change on the spectrum.
And 4, acquiring color information of the detected object through a spectrophotometer 16, wherein the color information is a color LAB value.
And 5, establishing a maturity judging model according to a least square algorithm and chemometrics, and setting a maturity judging value in the maturity judging model.
And 6, performing maturity prediction evaluation on the spectral data and the color information of the detected object according to the maturity discrimination value by the maturity discrimination model, and outputting a corresponding prediction evaluation result, so that the maturity of the detected object can be rapidly, accurately, nondestructively detected in batches, and the actual production efficiency of the detected object is improved.
In step 5, the setting of the maturity judging value is specifically as follows:
and 51, picking a batch of detection samples with uniform size and intact, respectively selecting immature samples, semi-mature samples, mature samples and over-mature samples, and respectively numbering the four types of samples.
And step 52, after the four types of samples are respectively processed by S1, S2, S3 and S4, combining the preprocessed spectral data and color information, and dividing the detection sample into a correction set and a prediction set according to the ratio of 3:1 by adopting an SPXY algorithm.
And 53, performing prediction evaluation on the four samples through the maturity judging model, and assigning the prediction evaluation results of the corresponding samples to be used as the maturity judging value of the detected object, so that the prediction evaluation results of the maturity judging model on the detected object are accurate and reliable.
The working principle is as follows: the hyperspectral image acquisition component 11 and the spectrophotometer 16 respectively acquire spectral data and color information of a detected object and transmit the spectral data and the color information to a maturity judging model in a computer. The maturity judging model carries out prediction evaluation on the maturity of the detected object according to the spectral data and the color information, and outputs a corresponding prediction evaluation result, so that the maturity of the detected object can be rapidly, accurately, nondestructively detected in batches, and the actual production efficiency of the detected object is improved.
The present embodiment is only for explaining the present invention, and it is not limited to the present invention, and those skilled in the art can make modifications to the present embodiment without inventive contribution as required after reading the present specification, but all of them are protected by patent laws within the scope of the claims of the present invention.
Claims (7)
1. The utility model provides a quick discriminating gear of kiwi fruit maturity which characterized by: comprises a computer, a box body (1) and a horizontal conveying piece (17) arranged in the box body (1); the inner wall of the box body (1) is provided with a spectrophotometer (16), a hyperspectral image acquisition part (11) and at least one light source part (15); the spectrophotometer (16) and the hyperspectral image acquisition component (11) are both connected with a computer.
2. The device for rapidly judging the maturity of the kiwi fruits according to claim 1, which is characterized in that: the spectrophotometer (16) is a Ci7860 desktop spectrophotometer (16).
3. The device for rapidly judging the maturity of the kiwi fruits according to claim 1, which is characterized in that: the hyperspectral image acquisition part (11) comprises a lens (14), an imaging spectrometer (13) and a camera (12) connected with a computer, wherein the lens (14) is connected with the imaging spectrometer (13), and the imaging spectrometer (13) is connected with the camera (12).
4. The device for rapidly judging the maturity of the kiwi fruits according to claim 1, which is characterized in that: the box body (1) is provided with two light source pieces (15) which are symmetrically arranged on the side wall of the box body (1); both of the light source members (15) are obliquely directed to the horizontal transfer member (17).
5. The device for rapidly judging the maturity of the kiwi fruits according to claim 1, which is characterized in that: the light source element (15) is a diffuse reflection light source.
6. The device for rapidly judging the maturity of the kiwi fruits according to claim 1, which is characterized in that: the horizontal conveying piece (17) is a precise dustproof electric translation table.
7. The device for rapidly judging the maturity of the kiwi fruits according to claim 1, which is characterized in that: the hyperspectral image acquisition component (11) is vertically arranged on the top wall of the box body (1), and the spectrophotometer (16) is vertically connected with the side wall of the box body (1) through a driving cylinder (18); the driving air cylinder (18) is electrically connected with the horizontal conveying member (17).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201920687163.XU CN210533976U (en) | 2019-05-14 | 2019-05-14 | Kiwi fruit maturity fast discrimination device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201920687163.XU CN210533976U (en) | 2019-05-14 | 2019-05-14 | Kiwi fruit maturity fast discrimination device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN210533976U true CN210533976U (en) | 2020-05-15 |
Family
ID=70593192
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201920687163.XU Expired - Fee Related CN210533976U (en) | 2019-05-14 | 2019-05-14 | Kiwi fruit maturity fast discrimination device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN210533976U (en) |
-
2019
- 2019-05-14 CN CN201920687163.XU patent/CN210533976U/en not_active Expired - Fee Related
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wu et al. | Determination of toxigenic fungi and aflatoxins in nuts and dried fruits using imaging and spectroscopic techniques | |
Lü et al. | Detection of hidden bruise on kiwi fruit using hyperspectral imaging and parallelepiped classification | |
CN100480680C (en) | Multiple spectrum meat freshness artificial intelligence measurement method and system | |
CN110146516B (en) | Fruit grading device based on orthogonal binocular machine vision | |
CN110031408A (en) | A kind of Kiwi berry maturity fast discriminating device and method | |
CN101059452A (en) | Fruit quality damage-free detection method and system based on multiple spectral imaging technique | |
CN101692052B (en) | Hyperspectrum image technique-based method and hyperspectrum image technique-based device for identifying true and false famous tea | |
CN101308086A (en) | Fruit internal quality on-line checking method and apparatus based on near infrared spectra technology | |
CN102072883A (en) | Device and method for detecting comprehensive quality of crop seeds | |
JP2006170669A (en) | Quality inspection device of vegetables and fruits | |
CN109781622B (en) | Portable intelligent metal ore type quick distinguishing instrument | |
JP2010112887A (en) | Principal component analysis method, principal component analyzer, different kind article detection device, principal component analysis program, and recording medium for recording the principal component analysis program | |
CN210071686U (en) | Fruit grading plant based on orthogonal binocular machine vision | |
CN201041553Y (en) | Fruit quality non-damage detection system base on multi-spectrum imaging technology | |
Baek et al. | A novel hyperspectral line-scan imaging method for whole surfaces of round shaped agricultural products | |
CN110009609B (en) | Method for rapidly detecting yellow rice | |
CN101021488A (en) | Method and apparatus for detecting rice damage | |
CN105606610A (en) | Bio-speckle technology based method for nondestructive detection of apple internal quality | |
CN210533976U (en) | Kiwi fruit maturity fast discrimination device | |
CN110376154A (en) | Fruit online test method and system based on spectrum correction | |
AU2017222946B2 (en) | A method and apparatus for the detection of the presence of mycotoxins in cereals | |
CN110991469B (en) | Fruit soluble solid online detection method and system | |
CN106940292A (en) | Bar denier wood raw material quick nondestructive discrimination method of damaging by worms based on multi-optical spectrum imaging technology | |
CN113640229B (en) | Rapid nondestructive testing method and device for soybean quality with multiple parameters | |
CN113624759A (en) | Apple nondestructive testing method based on machine learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200515 |