A Sift-lbp Image Retrieval Model Based on Bag-of-features

Despite progress in image retrieval by using low-level features, such as colors, textures and shapes, the performance is still unsatisfied as there are existing gaps between low-level features and high-level semantic concepts (semantic gaps). In this research, we propose a novel image retrieval system based on bag-of-features (BoF) model by integrating scale invariant feature transform (SIFT) and local binary pattern (LBP). We show that SIFT and LBP features yield complementary and substantial improvement on image retrieval even in the case of noisy background and ambiguous objects. Two new integration models are proposed: patch-based integration and image-based integration. By using a weighted Kmeans clustering algorithm, the image-based SIFT-LBP integration achieves the superior performance on a given benchmark problem comparing to other existing algorithms.