Pattern recognition with composite correlation filters designed with multi-objective combinatorial optimization

OPTICS COMMUNICATIONS

卷:338

Article

Diaz-Ramirez, Victor H.¹  Cuevas, Andres¹  Kober, Vitaly²  Trujillo, Leonardo³  Awwal, Abdul⁴ 

[1] Inst Politecn Nacl CITEDI, Tijuana 22510, BC, Mexico

[2] CICESE, Dept Comp Sci, Ensenada 22860, Baja California, Mexico

[3] Inst Tecnol Tijuana, Tijuana 22500, BC, Mexico

[4] Lawrence Livermore Natl Lab, Natl Ignit Facil, Livermore, CA 94551 USA

关键词: Object recognition;    Composite correlation filters;    Multi-objective evolutionary algorithm;    Combinatorial optimization;   

DOI  :  10.1016/j.optcom.2014.10.038

来源: Elsevier

【 摘 要 】

Composite correlation filters are used for solving a wide variety of pattern recognition problems. These filters are given by a combination of several training templates chosen by a designer in an ad hoc manner. In this work, we present a new approach for the design of composite filters based on multi-objective combinatorial optimization. Given a vast search space of training templates, an iterative algorithm is used to synthesize a filter with an optimized performance in terms of several competing criteria. Moreover, by employing a suggested binary-search procedure a filter bank with a minimum number of filters can be constructed, for a prespecified trade-off of performance metrics. Computer simulation results obtained with the proposed method in recognizing geometrically distorted versions of a target in cluttered and noisy scenes are discussed and compared in terms of recognition performance and complexity with existing state-of-the-art filters. (C) 2014 Elsevier B.V. All rights reserved.

【 授权许可】

Free