Development of Noninvasive Classification Methods for Different Roasting Degrees of Coffee Beans Using Hyperspectral Imaging
This study aimed to develop an approach for quickly and noninvasively differentiating the roasting degrees of coffee beans using hyperspectral imaging (HSI). The qualitative properties of seven roasting degrees of coffee beans (unroasted, light, moderately light, light medium, medium, moderately dar...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/4/1259 |
| _version_ | 1798024595298582528 |
|---|---|
| author | Bingquan Chu Keqiang Yu Yanru Zhao Yong He |
| author_facet | Bingquan Chu Keqiang Yu Yanru Zhao Yong He |
| author_sort | Bingquan Chu |
| collection | DOAJ |
| description | This study aimed to develop an approach for quickly and noninvasively differentiating the roasting degrees of coffee beans using hyperspectral imaging (HSI). The qualitative properties of seven roasting degrees of coffee beans (unroasted, light, moderately light, light medium, medium, moderately dark, and dark) were assayed, including moisture, crude fat, trigonelline, chlorogenic acid, and caffeine contents. These properties were influenced greatly by the respective roasting degree. Their hyperspectral images (874–1734 nm) were collected using a hyperspectral reflectance imaging system. The spectra of the regions of interest were manually extracted from the HSI images. Then, principal components analysis was employed to compress the spectral data and select the optimal wavelengths based on loading weight analysis. Meanwhile, the random frog (RF) methodology and the successive projections algorithm were also adopted to pick effective wavelengths from the spectral data. Finally, least squares support vector machine (LS-SVM) was utilized to establish discriminative models using spectral reflectance and corresponding labeled classes for each degree of roast sample. The results showed that the LS-SVM model, established by the RF selecting method, with eight wavelengths performed very well, achieving an overall classification accuracy of 90.30%. In conclusion, HSI was illustrated as a potential technique for noninvasively classifying the roasting degrees of coffee beans and might have an important application for the development of nondestructive, real-time, and portable sensors to monitor the roasting process of coffee beans. |
| first_indexed | 2024-04-11T18:05:07Z |
| format | Article |
| id | doaj.art-433b4fd14ce1423f8c04296c1455cd04 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T18:05:07Z |
| publishDate | 2018-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-433b4fd14ce1423f8c04296c1455cd042022-12-22T04:10:20ZengMDPI AGSensors1424-82202018-04-01184125910.3390/s18041259s18041259Development of Noninvasive Classification Methods for Different Roasting Degrees of Coffee Beans Using Hyperspectral ImagingBingquan Chu0Keqiang Yu1Yanru Zhao2Yong He3School of Biological and Chemical Engineering/School of Light Industry, Zhejiang Provincial Key Laboratory of Chemical and Biological Processing Technology of Farm Products, Zhejiang Provincial Collaborative Innovation Center of Agricultural Biological Resources Biochemical Manufacturing, Zhejiang University of Science and Technology, Hangzhou 310023, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaThis study aimed to develop an approach for quickly and noninvasively differentiating the roasting degrees of coffee beans using hyperspectral imaging (HSI). The qualitative properties of seven roasting degrees of coffee beans (unroasted, light, moderately light, light medium, medium, moderately dark, and dark) were assayed, including moisture, crude fat, trigonelline, chlorogenic acid, and caffeine contents. These properties were influenced greatly by the respective roasting degree. Their hyperspectral images (874–1734 nm) were collected using a hyperspectral reflectance imaging system. The spectra of the regions of interest were manually extracted from the HSI images. Then, principal components analysis was employed to compress the spectral data and select the optimal wavelengths based on loading weight analysis. Meanwhile, the random frog (RF) methodology and the successive projections algorithm were also adopted to pick effective wavelengths from the spectral data. Finally, least squares support vector machine (LS-SVM) was utilized to establish discriminative models using spectral reflectance and corresponding labeled classes for each degree of roast sample. The results showed that the LS-SVM model, established by the RF selecting method, with eight wavelengths performed very well, achieving an overall classification accuracy of 90.30%. In conclusion, HSI was illustrated as a potential technique for noninvasively classifying the roasting degrees of coffee beans and might have an important application for the development of nondestructive, real-time, and portable sensors to monitor the roasting process of coffee beans.http://www.mdpi.com/1424-8220/18/4/1259coffee beanroasting degreequalitative propertieshyperspectral imagingchemometric methods |
| spellingShingle | Bingquan Chu Keqiang Yu Yanru Zhao Yong He Development of Noninvasive Classification Methods for Different Roasting Degrees of Coffee Beans Using Hyperspectral Imaging Sensors coffee bean roasting degree qualitative properties hyperspectral imaging chemometric methods |
| title | Development of Noninvasive Classification Methods for Different Roasting Degrees of Coffee Beans Using Hyperspectral Imaging |
| title_full | Development of Noninvasive Classification Methods for Different Roasting Degrees of Coffee Beans Using Hyperspectral Imaging |
| title_fullStr | Development of Noninvasive Classification Methods for Different Roasting Degrees of Coffee Beans Using Hyperspectral Imaging |
| title_full_unstemmed | Development of Noninvasive Classification Methods for Different Roasting Degrees of Coffee Beans Using Hyperspectral Imaging |
| title_short | Development of Noninvasive Classification Methods for Different Roasting Degrees of Coffee Beans Using Hyperspectral Imaging |
| title_sort | development of noninvasive classification methods for different roasting degrees of coffee beans using hyperspectral imaging |
| topic | coffee bean roasting degree qualitative properties hyperspectral imaging chemometric methods |
| url | http://www.mdpi.com/1424-8220/18/4/1259 |
| work_keys_str_mv | AT bingquanchu developmentofnoninvasiveclassificationmethodsfordifferentroastingdegreesofcoffeebeansusinghyperspectralimaging AT keqiangyu developmentofnoninvasiveclassificationmethodsfordifferentroastingdegreesofcoffeebeansusinghyperspectralimaging AT yanruzhao developmentofnoninvasiveclassificationmethodsfordifferentroastingdegreesofcoffeebeansusinghyperspectralimaging AT yonghe developmentofnoninvasiveclassificationmethodsfordifferentroastingdegreesofcoffeebeansusinghyperspectralimaging |