Visual Recognition using Local Quantized Patterns
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 such as HOG, LBP and LTP on a range of challenging object detection and texture classification problems.