Multispectral palmprint recognition based on local binary pattern histogram fourier features and gabor filter

摘要: Fusing multiple features within one biometric modality has attracted increasing attention and interest among researchers during recent decades because the concept is useful in addressing a wide range of real world problems. In this paper, we propose novel fusion approach that combines two feature extraction algorithms: Local Binary Pattern Histogram Fourier Features (LBP-HF) Gabor filter technique for use as extraction. The fused are applied to improve performance palmprint recognition. However, main problem associated with extremely large number features, which can result an overfitting classification. To overcome difficulty, spectral regression kernel discriminant analysis (SR-KDA) dimensionality reduction technique. When designing proposed recognition system, k-nearest neighbour (KNN) classifier used final decision. was evaluated using challenging multispectral PolyU database. From experimental results, it be suggested system presented consistently yields significant gains compared state-of-the art methods.