Fruit Image Classification Using Convolutional Neural Networks

Related Works

CNN techniques are more successful than traditional machine learning techniques because of their superior predicting capabilities when it comes to image classification. Makantasis, Protopapadakis, Doulamis, Doulamis, and Loupos (2015) used a Convolutional Neural Network based system to inspect tunnels. They compared their proposed system with other established techniques and showed that Convolutional Neural Network outperformed all other techniques.

Affonso et al. (2017) used CNN and many machine learning (ML) techniques to predict the quality of wooden boards samples using their images. Here they compared the performances of ML techniques with CNN. In their work the dimensionality of the dataset was low (only 2 dimensions), that is why CNN performed worse compared to other ML techniques.

Wang, Yang, Mao, Huang, Huang and Xu (2016) used convolutional neural networks with recurrent neural networks to make a multi-label image classifier system. Their work took the route of employing convolutional neural network and recurrent neural network to model the label co-occurrence dependency in a joint image/label embedding space.