Mango Quality Grading using Deep Learning Technique: Perspectives from Agriculture and Food Industry
Varsha Bhole, Arun Kumar
Abstract
India is an agrarian country; agriculture business is major source of income. India holds the first rank in mango (Mangifera Indica Linn) production worldwide. The precise grading of the fruit acts extensively in agricultural sector for the commercial development of India. Prior to bring the agricultural products to the market, it is essential to classify and grade them automatically without manual intervention. In this research study, we have designed and implemented deep learning-centered non-destructive mango sorting and grading system. The designed quality assessment scheme comprises of two phases: developing hardware and software. The hardware is built to photograph the RGB and thermal images of mango fruits from all the directions (360°) automatically. From these images, designed software classifies mangoes into three grades according to quality viz. Extra class, Class-I, and Class-II. Mango grading has been done by using parameters such as defects, shape, size, and maturity. In the present work, transfer learning based pre-trained SqueezeNet model has been employed to assess grading of mangoes. The test result reveals that classification accuracy of proposed system is 93.33% and 92.27% with the training time of 30.03 and 7.38 minutes for RGB and thermal images respectively and shows four times speed up through thermal imaging.