Kernel to computation: identifying optimal feature set for red rice classification
While existing research focuses extensively on white rice classification with readily available datasets, automated classification of red rice varieties remains largely unexplored with no publicly available datasets, creating a significant research gap in agricultural image processing applications....
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | Smart Agricultural Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772375525002989 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849434352652386304 |
|---|---|
| author | Suma D Narendra V G Darshan Holla M Shreyas Raviraja Holla M |
| author_facet | Suma D Narendra V G Darshan Holla M Shreyas Raviraja Holla M |
| author_sort | Suma D |
| collection | DOAJ |
| description | While existing research focuses extensively on white rice classification with readily available datasets, automated classification of red rice varieties remains largely unexplored with no publicly available datasets, creating a significant research gap in agricultural image processing applications. This research presents a study on red rice classification, a relatively unexplored area with no prior publicly available datasets or focused investigations on red rice variety identification. This study classifies three distinct red rice varieties—Uma, KCP-1, and Jyothi—primarily cultivated in Karnataka and Kerala, using image processing and machine learning techniques. Six ML models were evaluated with seven unique feature combinations derived from size, shape, and texture characteristics to identify the most discriminative feature set. Feature selection was performed using Recursive Feature Elimination and Backward Feature Elimination to enhance model efficiency. Hyperparameter tuning was applied to optimize classification performance, and k-fold cross-validation with statistical significance testing was used to assess generalization and validate model performance differences. The integration of size, shape, and texture features yielded the highest average accuracy across the models, with K-Nearest Neighbours achieving 98.67 % accuracy and Support Vector Machine reaching 97.34 % accuracy with the size and shape combination. The findings emphasize the importance of optimal feature selection and tuning in improving classification accuracy, contributing to the development of automated classification systems for red rice varieties. |
| format | Article |
| id | doaj-art-c0a43b76db404cde9f9b40ac3e4bdcdc |
| institution | Kabale University |
| issn | 2772-3755 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Smart Agricultural Technology |
| spelling | doaj-art-c0a43b76db404cde9f9b40ac3e4bdcdc2025-08-20T03:26:39ZengElsevierSmart Agricultural Technology2772-37552025-12-011210106510.1016/j.atech.2025.101065Kernel to computation: identifying optimal feature set for red rice classificationSuma D0Narendra V G1Darshan Holla M2 Shreyas3Raviraja Holla M4Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal, 576104, Karnataka, IndiaDepartment of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal, 576104, Karnataka, India; Corresponding authors.Department of Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal, 576104, Karnataka, IndiaDepartment of Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal, 576104, Karnataka, IndiaDepartment of Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education (MAHE), Manipal, 576104, Karnataka, India; Corresponding authors.While existing research focuses extensively on white rice classification with readily available datasets, automated classification of red rice varieties remains largely unexplored with no publicly available datasets, creating a significant research gap in agricultural image processing applications. This research presents a study on red rice classification, a relatively unexplored area with no prior publicly available datasets or focused investigations on red rice variety identification. This study classifies three distinct red rice varieties—Uma, KCP-1, and Jyothi—primarily cultivated in Karnataka and Kerala, using image processing and machine learning techniques. Six ML models were evaluated with seven unique feature combinations derived from size, shape, and texture characteristics to identify the most discriminative feature set. Feature selection was performed using Recursive Feature Elimination and Backward Feature Elimination to enhance model efficiency. Hyperparameter tuning was applied to optimize classification performance, and k-fold cross-validation with statistical significance testing was used to assess generalization and validate model performance differences. The integration of size, shape, and texture features yielded the highest average accuracy across the models, with K-Nearest Neighbours achieving 98.67 % accuracy and Support Vector Machine reaching 97.34 % accuracy with the size and shape combination. The findings emphasize the importance of optimal feature selection and tuning in improving classification accuracy, contributing to the development of automated classification systems for red rice varieties.http://www.sciencedirect.com/science/article/pii/S2772375525002989Feature extractionFeature selectionImage processingRed rice classification |
| spellingShingle | Suma D Narendra V G Darshan Holla M Shreyas Raviraja Holla M Kernel to computation: identifying optimal feature set for red rice classification Smart Agricultural Technology Feature extraction Feature selection Image processing Red rice classification |
| title | Kernel to computation: identifying optimal feature set for red rice classification |
| title_full | Kernel to computation: identifying optimal feature set for red rice classification |
| title_fullStr | Kernel to computation: identifying optimal feature set for red rice classification |
| title_full_unstemmed | Kernel to computation: identifying optimal feature set for red rice classification |
| title_short | Kernel to computation: identifying optimal feature set for red rice classification |
| title_sort | kernel to computation identifying optimal feature set for red rice classification |
| topic | Feature extraction Feature selection Image processing Red rice classification |
| url | http://www.sciencedirect.com/science/article/pii/S2772375525002989 |
| work_keys_str_mv | AT sumad kerneltocomputationidentifyingoptimalfeaturesetforredriceclassification AT narendravg kerneltocomputationidentifyingoptimalfeaturesetforredriceclassification AT darshanhollam kerneltocomputationidentifyingoptimalfeaturesetforredriceclassification AT shreyas kerneltocomputationidentifyingoptimalfeaturesetforredriceclassification AT ravirajahollam kerneltocomputationidentifyingoptimalfeaturesetforredriceclassification |