Visual Recognition using Local Quantized Patterns

Sibt Ul Hussain (1) , Bill Triggs (1)

1 SAM - Statistique Apprentissage Machine

Features such as Local Binary Patterns (LBP) and Local Ternary Patterns (LTP) have been very successful in a number of areas including texture analysis, face recognition and object detection. They are based on the idea that small patterns of qualitative local gray-level differences contain a great deal of information about higher-level image content. Existing local pattern features use hand-specified codings, which limits them to small spatial supports and coarse graylevel comparisons. We introduce Local Quantized Patterns (LQP), a generalization that uses lookup-table based vector quantization to code larger or deeper patterns. LQP inherits some of the flexibility and power of visual word representations, without sacrificing the run-time speed and simplicity of existing local pattern ones. We show that it outperforms well-established features including HOG, LBP and LTP and their combinations on a range of challenging object detection and texture classification problems.

Mots clés: Visual Features; Object detection; Local Binary Patterns (LBP); Local Pattern Features; Local Quantized Patterns (LQP); Texture Classification

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Sibt Ul Hussain, Bill Triggs. Visual Recognition using Local Quantized Patterns. ECCV 2012 - 12th European Conference on Computer Vision, Oct 2012, Florence, Italy. pp.716-729, ⟨10.1007/978-3-642-33709-3_51⟩. ⟨hal-00695627⟩