Image Category Recognition using Bag of Visual Words Representation

Abstract

Image category recognition is one of the challenging tasks due to difference in image background, illumination, scale, clutter, rotation, etc. Bag-of-Visual-Words (BoVW) model is considered as the standard approach for image categorization. The performance of the BoVW is mainly depend on local features extracted from images. In this paper, a novel BoVW representation approach utilizing Compressed Local Retinal Features (CLRF) for image categorization is proposed. The CLRF uses interest point regions from images and transform them to log polar form. Then two dimensional Discrete Wavelet Transformation (2D DWT) is applied to compress the log polar form and the resultant are considered as features for the interest regions. These features are further used to build a visual vocabulary using k-means clustering algorithm. Then this visual vocabulary is used to form a histogram representation of each image where the images are further classified using Support Vector Machines (SVM) classifier. The performance of the proposed BoVW framework is evaluated using SIMPLIcity and butterflies datasets. The experimental results show that the proposed BoVW approach that uses CLRF is very competitive to the state-of-the-art methods.