Rice Classification using Deep Neural Network

DOI

10.2991/978-94-6463-858-5_48How to use a DOI?

Keywords

Rice Grain Classification; Deep Learning; CNN-ResNet Hybrid Model; Precision Agriculture; Image-Based Quality Assessment

Abstract

Rice is currently among the most used staple circles in the world with immense economic and nutritional values. The genetic variations on rice grains are varied and thus lead to the occurrence of unique characteristics like texture, shape, and color that may be used to address the classification and quality determination of rice. In this project, five common types of rice that are arborio, basmati, ipsala, jasmine, and kara-kadag are targeted. We will use a huge volume of pictures (75,000) and a further list of features (106 morphological, shape and color attributes) in order to build an advanced list of classifications that can precisely disclose these varieties.

This project is based on a hybrid model as it makes use of two of the most efficient image processing and classification tasks deep learning models, namely Convolutional Neural Networks (CNNs), and ResNets (Residual Networks). CNNs are considered capable of extracting spatial data like texture and shape, whereas the depth of ResNets allows acquiring much detail of the visual information and maintaining quality standards. By combining the feature extraction capabilities of CNNs with the depth and accuracy of ResNets, our model achieves high classification accuracy by distinguishing subtle differences between rice varieties. This multi-functional approach not only improves model reliability, but also facilitates rapid, real-time analysis in agricultural settings.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Damaraju Sai Vishnu
AU  - D. L. Sreenivasa Reddy
PY  - 2025
DA  - 2025/11/04
TI  - Rice Classification using Deep Neural Network
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 551
EP  - 564
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_48
DO  - 10.2991/978-94-6463-858-5_48
ID  - Vishnu2025
ER  -