Analytical study of color spaces for object recognition in convolutional neural networks

Abstract

In this work we present an analytical study of the classical problem of image recognition / classification using different color spaces and deep convolutional neural networks(CNNs). In the current decade deep CNN architectures for solving image recognition problem has become very popular because of high speed and accuracy in the detection results. Usually most such deep learning architectures or networks are applied on image dataset where images are in RGB color space. In this work, we have analysed the performance of 3 popular CNNs by providing input images in different color spaces. We describe the design of our novel experiment and present results on whether such deep learning networks (CNNs) for object recognition task is invariant to color spaces or not. Our experimental results vividly show that different color spaces have different performance results for image classification. We have compared the results in terms of test accuracy, test loss, and validation loss. Three different CNN architectures covered in our study are - VGGNet, ResNet, GoogleNet and five difference color spaces for analysis are RGB, rgb, YCbCr, HSV, CIE??Lab. Our objective was to find how CNNs perform in different color spaces and if we can clearly identify a color space for object recognition task in CNN where the performance is best. Our study shows that CNNs are �variant� to color spaces. Normalized RGB (rgb) and HSV very distinctly did not perform as well as RGB,YCbCr, and CIE??Lab. Off the later three good performing color spaces none could be identified as a clear winner. The three different deep CNNs performed differently on the three different color spaces.