Nature Scene classification using different color feature

This paper describes a process for extracting hybrid color features for natural scene images. There are different approaches to color feature analysis are tested on the classification of image from Oliva, Antonio Torralba database. For this purpose three set of image categories are taken viz coast, river, and mountains. The first method employs multispectral approach, in which image features are extracted from each channel of RGB color space. The second method uses YCbCr color space in which image features are extracted from the luminance channel Y and color features from the chromaticity channels Cb and Cr. The third method uses HSV color space in which texture features are extracted from the luminance channel V and color features from the chromaticity channels H and S. The last one uses combination of all these three method. The extracted features are trained and tested with Feed forward classifier. All the applications of the image analysis so far are limited to gray scale images. This paper investigates the usage of color natural image classification problem.