Visual Recognition Using Local Quantized Patterns

Abstract

Abstract. Features such as Local Binary Patterns (LBP) and LocalTernary 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. Current local pattern features use hand-specified codings that are limited 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 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.

Face Recognition using Local Quantized Patterns

“…Local Quantized Patterns (LQP). LQP [8] is a generalized form of local patterns that uses large local neighbourhoods and/or deeper quantization with domain-adaptive vector quantization to solve many of the above mentioned problems of local patterns. However, to maintain the speed and simplicity of local pattern features and to make the process of vector quantization fast, LQP uses the fact that local patterns binary/ternary codes -produced from the comparisons of surrounding pixel values with the central pixel one -span a discrete space e.g.…”

“…doing 10 rounds of tailored K-Means over 600 × 10 3 features of dimension 40 requires only about 28 minutes. LQP features have already been shown to outperform other local pattern features in visual object detection and texture classification tasks [8].…”

“…These shortcomings limit the overall information encoding capability of these local pattern features and prevent them from leveraging all the available information, thus affect the overall performance of face recognition systems. This paper builds on the recently introduced Local Quantized Patterns (LQP) [8], a generalized and enriched form of the local pattern features, and shows their superiority in characterizing faces. Our face representation is not only fast to compute (no extra computational overhead attached at runtime), but also performs equally well in both the intensity and orientation space and outperforms any existing face representation on different challenging datasets.…”

Face Recognition Using Local Quantized Patterns and Gabor Filters

“…In this paper perspective approach described in (Hussain, Triggs, 2012;Hussain, Napoléon, Jurie, 2012) is offered to solve many of the above mentioned problems of local Photogrammetric techniques for video surveillance, biometrics and biomedicine, 25-27 May 2015, Moscow, Russia patterns. To maintain the speed and simplicity of local pattern features and to make the process of vector quantization fast, local quantized patterns (LQP) are used.…”

Texture Classification based on First Order Local Ternary Direction Patterns

“…It started by the revolutionary approach derived by Ojala et alto derive texture features by quantizing the local pixel values of a neighborhood in to two values and named it as local binary patterns (LBPs) [11,12]. Later several authors [13][14][15][16][17][18][19] carried out abundant work and derived efficient methods to further extend the benefits of LBP in various applications. The Binary features [12,13,15,20,21,22] gained reputation and recognition due to their efficient design, computational simplicity and good performance.…”