Combined Descriptors in Spatial Pyramid Domain for Image Classification

TL;DR

This paper introduces a new image classification method combining LBP and TPLBP descriptors in a spatial pyramid framework, eliminating the need for codebook learning and outperforming SIFT-based SPM in accuracy and efficiency.

Contribution

The paper proposes a novel combination of local binary pattern descriptors in spatial pyramid domain that is more efficient and accurate than traditional SIFT-based methods.

Findings

Outperforms SIFT-based SPM in classification accuracy

Reduces computational complexity in time and space

Effective on benchmark datasets

Abstract

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.