Multi-Fruit Classifier using Convolutional Neural Networks This project aims to build a Deep Neural Network to correctly classify a set of 17 kinds of fruits from the Kaggle Fruits-360 dataset. A fruit recognition process usually consists of three steps which are image acquisition, pre-processing, and image analysis. The result of the proposed method has a fairly good classification accuracy of 97.40% for the 17 classes of 2849 fruit images, indicating that the proposed method could perhaps be used in agro-based applications.