Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204058,
        author = {Mahesh J. Kanase and Ravikant A. Hatgine and Bharti Vivek Bandgar},
        title = {Survey Paper on Assessing Rice Seed Quality Through Convolutional Neural Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2298-2301},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204058},
        abstract = {Seed quality inspection is a foundational requirement for plant nurseries and agricultural operations, as it directly affects seedling growth and overall crop performance. Conventional inspection approaches rely on trained personnel to manually examine seed samples, a process that is costly, slow, and prone to human error — especially when dealing with large volumes.
This paper presents a machine learning-based framework designed to automate the classification of rice seed quality with higher speed and precision. The proposed system follows a standard machine learning pipeline comprising data collection, model training, validation, and testing. A dataset of 2,000 images was assembled, equally split between high-quality (superior) and low-quality (non-superior) rice seeds, with physical properties such as color and shape forming the basis for classification.
The model was developed and evaluated using Convolutional Neural Network (CNN) techniques on Google Colaboratory, applying cross-validation with an 80:20 training-to-validation split. The resulting Deep CNN model classifies individual rice seed images fed into the system. Evaluation on 30 test samples yielded a precision of 93% and a recall of 95%, indicating strong capability in distinguishing between superior and non-superior seeds.},
        keywords = {Artificial Intelligence, CNN, Rice Seed Classification, Deep CNN, Supervised Learning},
        month = {June},
        }