COMPUTER VISION BASED VEGETABLE GRADING AND SORTING SYSTEM by Sukhpreet Kaur
Since ages, agricultural sector plays an important role in the economic development of a country. In recent years, industries have started using automated systems instead of manual techniques for quality evaluation. In agriculture field grading is very necessary to increase the productivity of the vegetable products. Everyday huge amount of vegetables are exported to other places and earn a good profit. So quality evaluation is important in terms of improving the quality of vegetables and gaining profit. Traditionally, the vegetable grading and classification was done through manual procedures which were error prone and costly. Computer vision based systems provides us accurate and reliable results that are not possible human graders/experts. This research work presents a vegetable grading and sorting system based on computer vision and image processing. For this research work, a tomato has been used as a sample vegetable. A total of fifty three images were acquired using own camera setup. Afterwards, segmentation using Otsu’s method was performed so as to separate the vegetable from the background. The segmented images, thus obtained, were used to extract color and shape features. There after grading and sorting was performed using back propagation neural network. Twenty eight images were used for training the network and twenty five images for testing purposes. The proposed system has shown 92% accuracy rate. Also the system was compared with existing tomato maturity based grading system. The present system outperformed the existing system and is proposed for industry use.