Image Retrieval Using the Color Approximation Histogram Based on Rough Set Theory

As a low-level feature in content-based image retrieval (CBIR), color histogram does not take into account the spatial correlation of the same or similar valued elements. In order to overcome this drawback, color approximation histogram based on rough sets theory is proposed in this paper. The image is partitioned into a collection of non-overlapping windows (called granule G). According to the pixels color in granule, color lower approximation histogram and color boundary histogram are denoted as low level feature in CBIR. Experiment results show that the precision and recall rate of color approximation histogram as low-level feature are higher than that of color histogram as low-level feature. The color approximation histogram classifies the granule into color lower approximation set or color boundary set, so it overcomes the drawback of color histogram as low-level feature.