Fruit Quality Classification using Convolutional Neural Network

Fruit quality identification is very important in the food industry for maintaining product quality. The control commonly conducted by human senses which lack of objectivity and takes long time real-time mass production control. fruit can be identified through its color, smell, texture. This study uses image to classify fruit. We trained artificial neural networks classifying from Indian Dataset with Quality (FruitNet). dataset contains six classes fruits three categorical qualities (Good, Bad, Mixed). features were extracted using several pre-trained deep learning on ImageNet dataset. convolutional feature extraction used this are VGG16, MobileNetV2, EfficientNetB0, ResNet50. forwarded network training result shown that f1-score testing reaches more than 90% except MobileNetV2. highest obtained ResNet50 95.7%.