Enhancement of Individuality Representation for Multi-Biometric Identification

Abstract

Personal identification is one of the areas in pattern recognition that has created a center of attention by many researchers to work in. Recently, its focal point is in forensic investigation and biometric identification as such the physical (i.e., iris, fingerprint) and behavioural (i.e., signature) style can be used as biometric features for authenticating an individual. In this study, an improved approach of presenting biometric features of true individual from multi-form of biometric images is presented. The discriminability of the features is proposed by discretizing the extracted features of each person using improved Biometric Feature Discretization (BFD). BFD is introduced for features perseverance to obtain better individual representations and discriminations without the use of normalization. Our experiments have revealed that by using the proposed improved BFD in Multi-Biometric System, the individual identification is significantly increased with an average identification rate of 98%.

Assessment of Non-Verbal Communication Online Job Recruitment Using Gray Level Co-Occurrence Matrix and Fuzzy C-Means Algorithm

“…A co-occurrence matrix is a matrix that is defined over an image to be the distribution of co-occurring value at a given offset [3]. The GLCM is a classic method of texture feature extraction, which is effective in image recognition, image segmentation, image retrieval, image classification, and texture analysis methods [4].…”