Vegetable and Fruit Image Classification with SqueezeNet based Deep Feature Generator

Abstract

Automatic classification of food products according to their types is one of the most common problems in computer vision. In this paper, 15 different types of vegetables were automatically classified through transfer learning in deep learning. The dataset used in the study is large and consists of 21,000 vegetable images. These images in the dataset are divided into 3 groups as training, testing and validation. Within the scope of the study, all of these groups were combined and a large dataset was obtained. SqueezeNet architecture is used for feature extraction in the developed deep learning-based machine learning model. In addition, the ReliefF method was used for feature selection and the most significant features were determined by eliminating negative features. In the classification phase of the developed application, Linear Discriminant Analysis (LDA) method was preferred. In this study, Hold-Out and 10-fold cross-validation techniques were used. Approximately 99% accuracy value was obtained in both validation techniques. The obtained results of the study show that the proposed method can be used successfully in automatic vegetable classification.