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 learningcentered 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 pretrained 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.

No abstract

No abstract

No abstract

Shelf-life prediction for fruits based on the visual inspection and with RGB imaging through external features becomes more pervasive in agriculture and food business. In the proposed architecture, to enhance the accuracy with low computational costs we focus on two challenging tasks of shelf life (remaining useful life) prediction: 1) detecting the intrinsic features like internal defects, bruises, texture, and color of the fruits; and 2) classification of fruits according to their remaining useful life. To accomplish these tasks, we use the thermal imaging technique as a baseline which is used as non-destructive approach to find the intrinsic values of fruits in terms of temperature parameter. Further to improve the classification tasks, we combine it with a transfer learning approach to forecast the shelf life of fruits. For this study, we have chosen „Kesar? (Mangifera Indica Linn cv. Kesar) mangoes and for the purpose of classification, our designed dataset images are categorized into 19 classes viz. RUL-1 (Remaining Useful Life-1) to RUL-18 (Remaining Useful Life-18) and No-Life as after harvesting, the storage span of „Kesar? is near about 19 days. A comparative analysis using SqueezeNet, ShuffleNet, and MobileNetv2 (which are prominent CNN based lightweight models) has been performed in this study. The empirical results show a highest achievable accuracy of 98.15±0.44% with an almost a double speedup in training the entire process by using thermal images.