Seeds Classification and Quality Testing Using Deep Learning and YOLO v5

Abstract

Segregation of seeds of different crops grown in the mixed cropping is a major cause of concern for the farmers as well as the food industry. Also, the classification and packaging of seeds based on their quality is a challenging task for farmers and agro-industries. Moreover, Post-thrashing separation of seeds by the traditional techniques such as sieving, hand-picking, etc. is a time-consuming and tedious task. Thus, there is a need to automate seed segregation. The potential of deep learning and machine learning techniques in object detection, classification, and pattern recognition motivated the researchers to employ these techniques for the automatic segregation of seeds at the harvesting site. The techniques proposed so far focus on the classification of seeds of different crops. Limited research work is observed that focuses on the classification of seeds of crops grown as a part of mixed cropping as well as seeds of different quality standards. Also, there is a huge scope to improve the classification performance of the proposed models. The purpose of this research to develop the deep learning-based system 'Mixed Cropping Seed Classifier and Quality Tester (MCSCQT)' for accurate classification and quality testing of seeds based on their shape, color, and texture. The system is trained on the dataset comprising labelled images of healthy and diseased seeds of pearl millet and maize. It reports the highest precision and recall of 99%. The efficacy of the system in discriminating the seeds of pearl millet and maize may prove a game-changer for the food industry. Also, its capability in recognition of diseased and healthy seeds of maize enhances its utility in the food industry.