Effective Image Retrieval System Using Dot-Diffused Block Truncation Coding Features

This paper presents a new approach to derive the image feature descriptor from the dot-diffused block truncation coding (DDBTC) compressed data stream. The image feature descriptor is simply constructed from two DDBTC representative color quantizers and its corresponding bitmap image. The color histogram feature (CHF) derived from two color quantizers represents the color distribution and image contrast, while the bit pattern feature (BPF) constructed from the bitmap image characterizes the image edges and textural information. The similarity between two images can be easily measured from their CHF and BPF values using a specific distance metric computation. Experimental results demonstrate the superiority of the proposed feature descriptor compared to the former existing schemes in image retrieval task under natural and textural images. The DDBTC method compresses an image efficiently, and at the same time, its corresponding compressed data stream can provide an effective feature descriptor for performing image retrieval and classification. Consequently, the proposed scheme can be considered as an effective candidate for real-time image retrieval applications.

I. Introduction

Block Truncation Coding (BTC), introduced by Delp and Mitchell in 1979, is a technique for image compression [1]. Its concept is to divide the original image into multiple non-overlapped image blocks, and each block is simply represented by two distinct extreme quantizers, i.e. high and low mean values, and a bitmap image. The BTC scheme performs thresholding operation using the mean value of each image block to generate the bitmap image. Although the traditional BTC does not improve the coding gain compared to the other modern compression techniques, such as JPEG or JPEG2000, the computational complexity of BTC is much lower than that of the above techniques. Thus, the BTC-based schemes can be a very good candidates for image retrieval, in particular the processing time is a critical issue in this type of application. In the prior studies, enormous attempts have been put to improve the image quality and compression ratio, and, at the same time, to reduce the computational complexity of the BTC encoding process [2]–[9].