A Compact And Efficient Image Retrieval Approach Based On Border/interior Pixel Classification
Abstract
This paper presents \bic (<i>B</i>order/<i>I</i>nterior pixel <i>C</i>lassification), a compact and efficient CBIR approach suitable for broad image domains. It has three main components: (1) a simple and powerful image analysis algorithm that classifies image pixels as either border or interior, (2) a new logarithmic distance (<i>dLog</i>) for comparing histograms, and (3) a compact representation for the visual features extracted from images. Experimental results show that the <i>BIC</i> approach is consistently more compact, more efficient and more effective than state-of-the-art CBIR approaches based on sophisticated image analysis algorithms and complex distance functions. It was also observed that the <i>dLog</i> distance function has two main advantages over vectorial distances (e.g., L<sub>1</sub>): (1) it is able to increase substantially the effectiveness of (several) histogram-based CBIR approaches and, at the same time, (2) it reduces by 50% the space requirement to represent a histogram.