A Survey on Object Classification using Convolutional Neural Networks

Abstract

Object recognition has been one of the main tasks in computer vision. While feature detection and classification have been generally useful, an inquiry has been made to learning features suited to the task. One such method is the use of convolutional neural networks. This uses an architecture that combines elements of convolution, subsampling, and backpropagation. This paper gives an overview on the development, the use, and variations in using convolutional neural networks as an algorithm for object recognition tasks.