Biometrics is defining people according to their physiological, behavioral and biological characteristics. Biometrics can be divided into two categories: Physiological biometric and behavioral biometric. Physiological biometrics are features such as face, iris, fingerprint finger vessels, hand geometry, etc. that help identify the individual with their physiological or biological features. Behavioral biometrics, on the other hand, are features such as handwriting, signature or tone of voice that gain individual dimensions over time and thus help to recognize the individual. In this paper, a discrete wavelet transform is presented based on local binary patterns, gray level and co-sequencing matrix. It represents a new system to face datasets. The proposed face recognition system has been designed by considering different usage purposes. The recognition system consists of four stages. The first stage is the preprocessing stage. At this stage, Discrete Wavelet Transform (DWT) was used. In the second stage, feature extraction stage, Local Binary Pattern (LBP) with Gray Level Co-Occurrence Matrix (GLCM) was used. In the last stage, in the classification stage, the cosine distance as well as the euclidean distance were used as classifiers. Experimental results tested with images in Olivetti Research Laboratory (ORL) data set. Experimental results have shown that feature extraction algorithms generally give more successful accurate recognition rates in face recognition applications.
Anahtar Kelimeler: Face recognition, Local Binary Pattern, Gray Level Co-occurrence Matrix, Wavelet Transform