An improved lightweight ConvNeXt for rice classification
Under the pressure of climate change, the international food market is facing great uncertainty. Rice is widely grown as a major worldwide food crop, and different rice seeds often influence the future merit of a country's rice growth. As a major food crop widely grown around the world, the see...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824012638 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583093680078848 |
|---|---|
| author | Pengtao Lv Heliang Xu Qinghui Zhang Lei Shi Heng Li Youyang Chen Yana Zhang Dengke Cao Zhongyang Liu Yixin Liu Jingwen Han Zhan Zhang Yiran Qi |
| author_facet | Pengtao Lv Heliang Xu Qinghui Zhang Lei Shi Heng Li Youyang Chen Yana Zhang Dengke Cao Zhongyang Liu Yixin Liu Jingwen Han Zhan Zhang Yiran Qi |
| author_sort | Pengtao Lv |
| collection | DOAJ |
| description | Under the pressure of climate change, the international food market is facing great uncertainty. Rice is widely grown as a major worldwide food crop, and different rice seeds often influence the future merit of a country's rice growth. As a major food crop widely grown around the world, the seed type of rice plays a key role in ensuring food security and optimizing agricultural productivity. Therefore, identifying the types of rice grains is an important task in rice breeding and cultivation. To this end, this study proposes a new model based on the ConvNeXt framework for detecting rice types, aiming to improve the identification efficiency. Our improved model achieved an average accuracy of 94.69 %. Compared to the baseline model ConvNeXt, the proposed network is more lightweight and more accurate. We conducted comprehensive experiments on the rice dataset from the GrainSpace public dataset to ensure the thoroughness and rigor of the study. Compared to existing models, our proposed model achieved the highest accuracy while maintaining lower FLOPs and parameters. |
| format | Article |
| id | doaj-art-6d98d216ee994aa299e665e0a853bb8f |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-6d98d216ee994aa299e665e0a853bb8f2025-01-29T05:00:11ZengElsevierAlexandria Engineering Journal1110-01682025-01-011128497An improved lightweight ConvNeXt for rice classificationPengtao Lv0Heliang Xu1Qinghui Zhang2Lei Shi3Heng Li4Youyang Chen5Yana Zhang6Dengke Cao7Zhongyang Liu8Yixin Liu9Jingwen Han10Zhan Zhang11Yiran Qi12Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, China; Henan Key Laboratory of Grain Storage Information Intelligent Perception and Decision Making, Henan University of Technology, Zhengzhou 450001, China; Henan Grain Big Data Analysis and Application Engineering Research Center, Henan University of Technology, Zhengzhou 450001, ChinaKey Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, China; Henan Key Laboratory of Grain Storage Information Intelligent Perception and Decision Making, Henan University of Technology, Zhengzhou 450001, China; Henan Grain Big Data Analysis and Application Engineering Research Center, Henan University of Technology, Zhengzhou 450001, China; Corresponding authors at: Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, China.Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, China; Henan Key Laboratory of Grain Storage Information Intelligent Perception and Decision Making, Henan University of Technology, Zhengzhou 450001, China; Henan Grain Big Data Analysis and Application Engineering Research Center, Henan University of Technology, Zhengzhou 450001, China; Corresponding authors at: Key Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, China.State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100876, China; Key Laboratory of Education Informatization for Nationalities (Yunnan Normal University), Ministry of Education, Kunming 650092, China; Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing 100081, ChinaKey Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, ChinaKey Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, ChinaKey Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, ChinaState Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100876, ChinaKey Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, ChinaKey Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, ChinaKey Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, ChinaKey Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, ChinaKey Laboratory of Grain Information Processing and Control (Henan University of Technology), Ministry of Education, Zhengzhou 450001, ChinaUnder the pressure of climate change, the international food market is facing great uncertainty. Rice is widely grown as a major worldwide food crop, and different rice seeds often influence the future merit of a country's rice growth. As a major food crop widely grown around the world, the seed type of rice plays a key role in ensuring food security and optimizing agricultural productivity. Therefore, identifying the types of rice grains is an important task in rice breeding and cultivation. To this end, this study proposes a new model based on the ConvNeXt framework for detecting rice types, aiming to improve the identification efficiency. Our improved model achieved an average accuracy of 94.69 %. Compared to the baseline model ConvNeXt, the proposed network is more lightweight and more accurate. We conducted comprehensive experiments on the rice dataset from the GrainSpace public dataset to ensure the thoroughness and rigor of the study. Compared to existing models, our proposed model achieved the highest accuracy while maintaining lower FLOPs and parameters.http://www.sciencedirect.com/science/article/pii/S1110016824012638Rice classificationLightweight modelData augmentationImage classification |
| spellingShingle | Pengtao Lv Heliang Xu Qinghui Zhang Lei Shi Heng Li Youyang Chen Yana Zhang Dengke Cao Zhongyang Liu Yixin Liu Jingwen Han Zhan Zhang Yiran Qi An improved lightweight ConvNeXt for rice classification Alexandria Engineering Journal Rice classification Lightweight model Data augmentation Image classification |
| title | An improved lightweight ConvNeXt for rice classification |
| title_full | An improved lightweight ConvNeXt for rice classification |
| title_fullStr | An improved lightweight ConvNeXt for rice classification |
| title_full_unstemmed | An improved lightweight ConvNeXt for rice classification |
| title_short | An improved lightweight ConvNeXt for rice classification |
| title_sort | improved lightweight convnext for rice classification |
| topic | Rice classification Lightweight model Data augmentation Image classification |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824012638 |
| work_keys_str_mv | AT pengtaolv animprovedlightweightconvnextforriceclassification AT heliangxu animprovedlightweightconvnextforriceclassification AT qinghuizhang animprovedlightweightconvnextforriceclassification AT leishi animprovedlightweightconvnextforriceclassification AT hengli animprovedlightweightconvnextforriceclassification AT youyangchen animprovedlightweightconvnextforriceclassification AT yanazhang animprovedlightweightconvnextforriceclassification AT dengkecao animprovedlightweightconvnextforriceclassification AT zhongyangliu animprovedlightweightconvnextforriceclassification AT yixinliu animprovedlightweightconvnextforriceclassification AT jingwenhan animprovedlightweightconvnextforriceclassification AT zhanzhang animprovedlightweightconvnextforriceclassification AT yiranqi animprovedlightweightconvnextforriceclassification AT pengtaolv improvedlightweightconvnextforriceclassification AT heliangxu improvedlightweightconvnextforriceclassification AT qinghuizhang improvedlightweightconvnextforriceclassification AT leishi improvedlightweightconvnextforriceclassification AT hengli improvedlightweightconvnextforriceclassification AT youyangchen improvedlightweightconvnextforriceclassification AT yanazhang improvedlightweightconvnextforriceclassification AT dengkecao improvedlightweightconvnextforriceclassification AT zhongyangliu improvedlightweightconvnextforriceclassification AT yixinliu improvedlightweightconvnextforriceclassification AT jingwenhan improvedlightweightconvnextforriceclassification AT zhanzhang improvedlightweightconvnextforriceclassification AT yiranqi improvedlightweightconvnextforriceclassification |