Content Based Image Retrieval using Frequency Domain Features: Zigzag Scanning of DCT Coefficients

Abstract

Content-Based Image Retrieval (CBIR) has become one of the trending areas of research in computer vision. In traditional CBIR the features in spatial domain, such as color, texture, shape and point features are extracted. It is often considered that apart from the spatial features, the features extracted from the frequency domain of the images can give further information on the features of an image. This paper proposes two novel methods for the purpose of feature extraction from the 2-dimensional Discrete Cosine Transform (DCT) of an image. DCT_256_Zigzag and DCT_256_2×2. These methods take into considerations the lower frequencies in order to determine the features in the frequency domain. The advantage of using the zigzag scanning is to have the maximum low frequency values having Higher Energies comparatively. These two features are combined with two of the existing spatial domain features: Local Binary Patterns (LBP) and Interchannel voting features to generate a global feature vector for an image. For an query image, its feature vector is compared with feature vectors of every other image in the database using dl-distance and the images with least distance is considered most similar image to the query image. To evaluate the efficiency of these two methods, five standard performance measures such as Average Precision Rate (APR), Average Recall Rate (ARR), F-Measure, Average Normalized Modified Retrieval Rank (ANMRR) and Total Minimum Retrieval Epoch (TMRE) are used. Six benchmark image datasets: Core1-1000, Corel -5000, Core1-10000, VisTex, STex, and Color-Brodatz are used to corroborate the performance of these methods.