CN109827908B - Method for judging rot degree of Fuji apples by using spectral data - Google Patents
Method for judging rot degree of Fuji apples by using spectral data Download PDFInfo
- Publication number
- CN109827908B CN109827908B CN201811583297.3A CN201811583297A CN109827908B CN 109827908 B CN109827908 B CN 109827908B CN 201811583297 A CN201811583297 A CN 201811583297A CN 109827908 B CN109827908 B CN 109827908B
- Authority
- CN
- China
- Prior art keywords
- spectral data
- hyperspectral
- data
- quality coefficient
- image pixel
- 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
Landscapes
- Spectrometry And Color Measurement (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention belongs to the technical field of information extraction, and particularly relates to a method for judging the rotten degree of Fuji red apples by using spectral data, which comprises the following steps: the method comprises the following steps: adjusting the position of an object to be screened; step two: preprocessing the spectral data; step three: converting the spectral data into hyperspectral raster image pixel data; step four: collecting pixel data of a hyperspectral raster image of a specific waveband; step five: calculating the quality coefficient H of the object to be measured; step seven: analyzing the quality coefficient H of the object to be detected. According to the invention, the rot degree of the red Fuji apples is automatically screened and judged by using the spectral data processing method, so that the data processing speed and the information extraction precision are improved, and the error of artificial judgment is reduced.
Description
Technical Field
The invention belongs to the technical field of information extraction, and particularly relates to a method for judging the rotten degree of Fuji red apples by using spectral data.
Background
At present, the quality screening of the red Fuji apples in China is mainly carried out by manual screening means, and the efficiency is very low. The current spectrum processing method mainly adopts spectrum full-band matching or spectrum matching of partial continuous bands, specific algorithms comprise spectrum angles, mixed demodulation filtering and the like, the methods are easily influenced by other spectrums or noise in the information extraction process, and the information extraction precision is low. Secondly, the existing spectral information extraction method has many manual operation steps, and increases the manual judgment error. Therefore, how to judge the rotting degree of the red Fuji apples, reduce the influence of other ground objects or noise, the influence of manual operation errors and the like in the rotting judging process, accelerate the development of the automatic screening technology of the rotting degree of the red Fuji apples, and become the leading-edge technology of the current spectral data processing research of the red Fuji apples.
Disclosure of Invention
The invention aims to provide a method for judging the rotten degree of red Fuji apples by using spectral data, and solves the technical problem that other ground objects or noise interfere the apple screening accuracy by using a spectral data processing method to judge the rotten degree of the red Fuji apples.
The technical scheme adopted by the invention is as follows:
a method for distinguishing the rotten degree of Fuji apple by using spectral data comprises the following steps:
the method comprises the following steps: adjusting the position of an object to be screened;
step two: preprocessing the spectral data;
step three: converting the spectral data into hyperspectral raster image pixel data;
step four: collecting pixel data of a hyperspectral raster image of a specific waveband;
step five: calculating the quality coefficient H of the object to be measured;
step six: analyzing the quality coefficient H of the object to be detected.
The first step is as follows: adjusting the position of the object to be screened, comprising: the red Fuji apples to be screened are flatly placed, the distance between a probe of a spectrum measuring instrument and the red Fuji apples to be screened is 5 cm-10 cm, and the probe does not shield sunlight or an artificial light source.
The second step is as follows: the spectral data preprocessing further comprises: and (4) correcting atmosphere, and acquiring the reflectivity data of the sample or the ground object spectrum.
The third step is that: the spectral data batch conversion still includes to hyperspectral grid image data: and converting the spectral data into hyperspectral raster image pixel data, wherein each piece of hyperspectral raster image pixel data corresponds to one piece of spectral data, and each piece of spectral data corresponds to one red Fuji apple to be screened.
The fourth step is that: gather specific wave band hyperspectral grid image pixel data, include: and respectively extracting hyperspectral raster image pixel data of 714nm and 375nm in specific wave bands.
The fifth step is as follows: calculating the quality coefficient H of the object to be measured, comprising the following steps: and dividing the third power of the image pixel value of the 714nm image of the specific wave band by the 375nm image pixel value of the specific wave band to obtain the quality coefficient H of the object to be detected.
Analyzing the quality coefficient H of the substance to be detected, comprising the following steps: if the quality coefficient H of the object to be detected is less than 2, the surface of the red Fuji apple is rotten; if the quality coefficient H of the object to be detected is more than or equal to 2 and less than or equal to 10, the red Fuji apple has a rotting tendency, and if the quality coefficient H of the object to be detected is more than 10, the red Fuji apple is a normal apple.
The invention has the beneficial effects that:
the method for judging the rotten degree of the Fuji apples by using the spectral data automatically screens and judges the rotten degree of the Fuji apples by using the spectral processing method, improves the data processing speed and the accuracy of information extraction, and reduces the error of artificial judgment.
Detailed Description
A method for distinguishing the rotten degree of Fuji apple by using spectral data comprises the following steps:
the method comprises the following steps: adjusting the position of an object to be screened;
step two: preprocessing the spectral data;
step three: converting the spectral data into hyperspectral raster image pixel data;
step four: collecting pixel data of a hyperspectral raster image of a specific waveband;
step five: calculating the quality coefficient H of the object to be measured;
step six: analyzing the quality coefficient H of the object to be detected.
The first step is as follows: adjusting the position of the object to be screened, comprising: the red Fuji apples to be screened are flatly placed, the distance between a probe of a spectrum measuring instrument and the red Fuji apples to be screened is 5 cm-10 cm, and the probe does not shield sunlight or an artificial light source.
The second step is as follows: the spectral data preprocessing further comprises: and (4) correcting atmosphere, and acquiring the reflectivity data of the sample or the ground object spectrum.
The third step is that: the spectral data batch conversion still includes to hyperspectral grid image data: and converting the spectral data into hyperspectral raster image pixel data, wherein each piece of hyperspectral raster image pixel data corresponds to one piece of spectral data, and each piece of spectral data corresponds to one red Fuji apple to be screened.
The fourth step is that: gather specific wave band hyperspectral grid image pixel data, include: and respectively extracting hyperspectral raster image pixel data of 714nm and 375nm in specific wave bands.
The fifth step is as follows: calculating the quality coefficient H of the object to be measured, comprising the following steps: and dividing the third power of the image pixel value of the 714nm image of the specific wave band by the 375nm image pixel value of the specific wave band to obtain the quality coefficient H of the object to be detected.
Analyzing the quality coefficient H of the substance to be detected, comprising the following steps: if the quality coefficient H of the object to be detected is less than 2, the surface of the red Fuji apple is rotten; if the quality coefficient H of the object to be detected is more than or equal to 2 and less than or equal to 10, the red Fuji apple has a rotting tendency, and if the quality coefficient H of the object to be detected is more than 10, the red Fuji apple is a normal apple. The selection of the threshold value can also be adjusted according to the actual situation, and the position selection of the wave band only needs to have a value error smaller than 5nm with the selected wave band.
The present invention has been described in detail with reference to the embodiments, which are one preferred embodiment of the present invention, but the present invention is not limited to the embodiments, and various changes can be made without departing from the spirit of the present invention within the knowledge of those skilled in the art. The prior art can be adopted in the content which is not described in detail in the invention.
Claims (5)
1. A method for distinguishing the rotten degree of Fuji apples by using spectral data is characterized in that: the method comprises the following steps:
the method comprises the following steps: adjusting the position of an object to be screened;
step two: preprocessing the spectral data;
step three: converting the spectral data into hyperspectral raster image pixel data;
step four: collecting pixel data of a hyperspectral raster image of a specific waveband;
step five: calculating the quality coefficient H of the object to be measured; the method comprises the following steps: dividing the third power of the image pixel value of the 714nm image of the specific wave band by the 375nm image pixel value of the specific wave band to obtain a quality coefficient H of the object to be measured;
step six: analyzing the analyte quality coefficient H, comprising: if the quality coefficient H of the object to be detected is less than 2, the surface of the red Fuji apple is rotten; if the quality coefficient H of the object to be detected is more than or equal to 2 and less than or equal to 10, the red Fuji apple has a rotting tendency, and if the quality coefficient H of the object to be detected is more than 10, the red Fuji apple is a normal apple.
2. The method of claim 1, wherein the spectral data is used to determine the degree of decay of Fuji apples: the first step is as follows: adjusting the position of the object to be screened, comprising: the red Fuji apples to be screened are flatly placed, the distance between a probe of a spectrum measuring instrument and the red Fuji apples to be screened is 5 cm-10 cm, and the probe does not shield sunlight or an artificial light source.
3. The method of claim 2, wherein the spectral data is used to determine the degree of decay of Fuji apples: the second step is as follows: the spectral data preprocessing further comprises: and (4) correcting atmosphere, and acquiring the reflectivity data of the sample or the ground object spectrum.
4. The method of claim 3, wherein the spectral data is used to determine the degree of decay of Fuji apples: the third step is that: the spectral data batch conversion still includes to hyperspectral grid image data: and converting the spectral data into hyperspectral raster image pixel data, wherein each piece of hyperspectral raster image pixel data corresponds to one piece of spectral data, and each piece of spectral data corresponds to one red Fuji apple to be screened.
5. The method of claim 4, wherein the spectral data is used to determine the degree of decay of Fuji apples: the fourth step is that: gather specific wave band hyperspectral grid image pixel data, include: and respectively extracting hyperspectral raster image pixel data of 714nm and 375nm in specific wave bands.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811583297.3A CN109827908B (en) | 2018-12-24 | 2018-12-24 | Method for judging rot degree of Fuji apples by using spectral data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811583297.3A CN109827908B (en) | 2018-12-24 | 2018-12-24 | Method for judging rot degree of Fuji apples by using spectral data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109827908A CN109827908A (en) | 2019-05-31 |
CN109827908B true CN109827908B (en) | 2021-04-13 |
Family
ID=66860808
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811583297.3A Active CN109827908B (en) | 2018-12-24 | 2018-12-24 | Method for judging rot degree of Fuji apples by using spectral data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109827908B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2874482Y (en) * | 2005-12-09 | 2007-02-28 | 江西农业大学 | High spectrum image collector for fruit |
CN102072883A (en) * | 2010-07-07 | 2011-05-25 | 北京农业智能装备技术研究中心 | Device and method for detecting comprehensive quality of crop seeds |
CN102890092A (en) * | 2012-10-12 | 2013-01-23 | 浙江大学 | Characteristic angle cosine value method for detecting defects of honey peach brown rot |
CN103900965A (en) * | 2012-12-25 | 2014-07-02 | 核工业北京地质研究院 | Hyperspectral image processing method used for extracting calcite information |
CN105527244A (en) * | 2015-10-26 | 2016-04-27 | 沈阳农业大学 | Near infrared spectrum-based Hanfu apple quality nondestructive test method |
CN105956612A (en) * | 2016-04-25 | 2016-09-21 | 西安电子科技大学 | Hyperspectral image classification method based on active learning and semi-supervised learning |
US9466122B1 (en) * | 2014-08-25 | 2016-10-11 | Raytheon Company | Independent covariance estimation and decontamination |
CN106525732A (en) * | 2016-10-25 | 2017-03-22 | 沈阳农业大学 | Apple interior and exterior quality fast nondestructive testing method based on hyperspectral imaging technology |
KR20180106639A (en) * | 2017-03-21 | 2018-10-01 | 한국세라믹기술원 | Analysis method for the determination of sulfur content in graphene |
CN108955620A (en) * | 2018-02-13 | 2018-12-07 | 中国科学院遥感与数字地球研究所 | A kind of method and system of farmland irrigated area area Remotely sensed acquisition |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8930015B2 (en) * | 2012-11-20 | 2015-01-06 | Bratney Companies | Sorting system for damaged product |
US9593982B2 (en) * | 2012-05-21 | 2017-03-14 | Digimarc Corporation | Sensor-synchronized spectrally-structured-light imaging |
-
2018
- 2018-12-24 CN CN201811583297.3A patent/CN109827908B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN2874482Y (en) * | 2005-12-09 | 2007-02-28 | 江西农业大学 | High spectrum image collector for fruit |
CN102072883A (en) * | 2010-07-07 | 2011-05-25 | 北京农业智能装备技术研究中心 | Device and method for detecting comprehensive quality of crop seeds |
CN102890092A (en) * | 2012-10-12 | 2013-01-23 | 浙江大学 | Characteristic angle cosine value method for detecting defects of honey peach brown rot |
CN103900965A (en) * | 2012-12-25 | 2014-07-02 | 核工业北京地质研究院 | Hyperspectral image processing method used for extracting calcite information |
US9466122B1 (en) * | 2014-08-25 | 2016-10-11 | Raytheon Company | Independent covariance estimation and decontamination |
CN105527244A (en) * | 2015-10-26 | 2016-04-27 | 沈阳农业大学 | Near infrared spectrum-based Hanfu apple quality nondestructive test method |
CN105956612A (en) * | 2016-04-25 | 2016-09-21 | 西安电子科技大学 | Hyperspectral image classification method based on active learning and semi-supervised learning |
CN106525732A (en) * | 2016-10-25 | 2017-03-22 | 沈阳农业大学 | Apple interior and exterior quality fast nondestructive testing method based on hyperspectral imaging technology |
KR20180106639A (en) * | 2017-03-21 | 2018-10-01 | 한국세라믹기술원 | Analysis method for the determination of sulfur content in graphene |
CN108955620A (en) * | 2018-02-13 | 2018-12-07 | 中国科学院遥感与数字地球研究所 | A kind of method and system of farmland irrigated area area Remotely sensed acquisition |
Non-Patent Citations (2)
Title |
---|
Detection of Early Rottenness on Apples by Using Hyperspectral Imaging Combined with Spectral Analysis and Image Processing;Baohua Zhang;《Food Anal. Methods》;20150125;全文 * |
用高光谱成像和PCA检测苹果的损伤和早期腐烂;张保华 等;《红外与激光工程》;20131231;第42卷(第S2期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN109827908A (en) | 2019-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110441249B (en) | Method for building pit mud total acid prediction model based on hyperspectral image technology | |
CN109540831B (en) | Wolfberry variety identification method based on hyperspectral imaging technology | |
CN110441248B (en) | Method for building pit mud moisture prediction model based on hyperspectral image technology | |
CN109085136B (en) | Method for measuring content of oxide components in cement raw material by near-infrared diffuse reflection spectrum | |
CN109001218A (en) | Apple surface defect quick nondestructive recognition methods based on high light spectrum image-forming technology | |
CN104965973B (en) | A kind of Apple Mould Core multiple-factor Non-Destructive Testing discrimination model and method for building up thereof | |
CN108801975A (en) | A kind of preprocessing procedures of micromation near infrared spectrometer detection vinasse ingredient | |
CN101936894B (en) | Near infrared spectrum and microscopic adipose cell data fusion-based pork freshness non-destructive testing technology | |
CN201041553Y (en) | Fruit quality non-damage detection system base on multi-spectrum imaging technology | |
CN103344597A (en) | Anti-flavored-interference near infrared non-destructive testing method for internal components of lotus roots | |
Syahrir et al. | Color grading in tomato maturity estimator using image processing technique | |
CN107202784B (en) | Method for detecting process nodes in rice seed soaking and germination accelerating process | |
CN116559111A (en) | Sorghum variety identification method based on hyperspectral imaging technology | |
CN112906740B (en) | Method for removing batch-to-batch differences aiming at tissue mass spectrum imaging result | |
CN109827908B (en) | Method for judging rot degree of Fuji apples by using spectral data | |
CN113655027A (en) | Method for rapidly detecting tannin content in plant by near infrared | |
CN109827909B (en) | Method for screening quality of Fuji apples by using spectral data | |
CN113267458A (en) | Method for establishing quantitative prediction model of soluble protein content of sweet potatoes | |
CN102788796B (en) | Nutrient diagnosis device and nutrient diagnosis method for nitrogen of crops based on multi-information integration of high spectral images and fluorescent images | |
CN105891130B (en) | A method of the different spectral informations of correction determine material information error | |
CN109164069B (en) | Identification method for leaf surface disease grade of fruit tree | |
CN109829464B (en) | Method for screening red Fuji apples by using spectral data | |
CN104181125A (en) | Method for rapidly determining Kol-bach value of beer malt | |
CN115146219A (en) | Raman spectrum spike removing method and system based on derivative spectrum and cubic smoothing | |
CN112229817A (en) | Method for establishing soda saline-alkali soil heavy metal quantitative inversion model |
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 |