Combined Descriptors in Spatial Pyramid Domain for Image Classification
This work addresses efficiency and accuracy issues in image classification for computer vision applications, but it is incremental as it builds on existing spatial pyramid and descriptor methods.
The paper tackles the high complexity of SIFT-based spatial pyramid matching for image classification by combining LBP and TPLBP descriptors in the spatial pyramid domain, eliminating codebook learning and feature quantization. Experiments show it significantly outperforms SIFT in both time efficiency and classification accuracy on two benchmark datasets.
Recently spatial pyramid matching (SPM) with scale invariant feature transform (SIFT) descriptor has been successfully used in image classification. Unfortunately, the codebook generation and feature quantization procedures using SIFT feature have the high complexity both in time and space. To address this problem, in this paper, we propose an approach which combines local binary patterns (LBP) and three-patch local binary patterns (TPLBP) in spatial pyramid domain. The proposed method does not need to learn the codebook and feature quantization processing, hence it becomes very efficient. Experiments on two popular benchmark datasets demonstrate that the proposed method always significantly outperforms the very popular SPM based SIFT descriptor method both in time and classification accuracy.