Optimizing LBP structure for visual recognition using binary quadratic programming

Jianfeng Ren, Xudong Jiang, Junsong Yuan, Gang Wang

Research output: Journal PublicationArticlepeer-review

63 Citations (Scopus)

Abstract

Local binary pattern (LBP) and its variants have shown promising results in visual recognition applications. However, most existing approaches rely on a pre-defined structure to extract LBP features. We argue that the optimal LBP structure should be task-dependent and propose a new method to learn discriminative LBP structures. We formulate it as a point selection problem: Given a set of point candidates, the goal is to select an optimal subset to compose the LBP structure. In view of the problems of current feature selection algorithms, we propose a novel Maximal Joint Mutual Information criterion. Then, the point selection is converted into a binary quadratic programming problem and solved efficiently via the branch and bound algorithm. The proposed LBP structures demonstrate superior performance to the state-of-the-art approaches on classifying both spatial patterns in scene recognition and spatial-temporal patterns in dynamic texture recognition.

Original languageEnglish
Article number6851185
Pages (from-to)1346-1350
Number of pages5
JournalIEEE Signal Processing Letters
Volume21
Issue number11
DOIs
Publication statusPublished - Nov 2014
Externally publishedYes

Keywords

  • Binary quadratic programming
  • LBP structure optimization
  • dynamic texture recognition
  • maximal joint mutual information
  • scene recognition

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Optimizing LBP structure for visual recognition using binary quadratic programming'. Together they form a unique fingerprint.

Cite this