Search

In recent years, there has been a growing interest in biometric recognition based on finger dorsal patterns, making it a significant area of research. This paper introduces a biometric classification system that utilizes dorsal finger middle creases. The viability of this trait is assessed through the implementation of a new method known as multi block circular shift combination local binary pattern (MBCSC-LBP). The MBCSC-LBP approach involves dividing the image into multiple blocks to enhance robustness and capture both local and global information, thereby extracting discriminative features. These features from each block are then concatenated to form a comprehensive feature vector. To evaluate the accuracy of the proposed MBCSC-LBP feature extractor, a support vector machine (SVM) with a linear kernel is utilized. The classification accuracy achieved by this method is 96.22% indicating a promising performance. [ABSTRACT FROM AUTHOR]

Biometric technology has drawn increasing attention and significance importance in recent years. In biometric security systems, personal identification and verification rely on their physical, behavioral, and biological characteristics. In this study, a new hand-based modality called dorsal finger creases is proposed for biometric classification. This modality is located on the dorsal surface of the finger, between the proximal knuckle and distal knuckle of the finger. However, it requires a specific feature extraction approach to extract the modality information on the selected region. Therefore, we have proposed a method for extracting the underlying features of the dorsal finger creases, called circular shift combination local binary pattern (CSC-LBP). The concept of CSC-LBP is to compute the local binary pattern within a 3 × 3 spatial window for each neighborhood pixel separately. Further, the concept of combination approach is applied on the individually computed eight LBP values to obtain the more discriminative feature vector. A multiclass support vector machine classifier is used for evaluating the effectiveness of the proposed CSC-LBP operator. Extensive experiments on self-collected datasets demonstrate the high classification accuracy and effectiveness of the proposed CSC-LBP method and confirm the usefulness of dorsal finger creases for personal recognition. [ABSTRACT FROM AUTHOR]

Bilateral facial asymmetry is frequently exhibited by humans but its combined evaluation across demographic traits including gender and ethnicity is still an open research problem. In this study we measure and evaluate facial asymmetry across gender and different ethnic groups and investigate the differences in asymmetric facial dimensions among the subjects from two public face datasets, the MORPH and FERET. To this end, we detect 28 facial asymmetric dimensions from each face image using an anthropometric technique. An exploratory analysis is then performed via a multiple linear regression model to determine the impact of gender and ethnicity on facial asymmetry. Post-hoc Tukey test has been used to validate the results of the proposed method. The results show that out of 28 asymmetric dimensions, females differ in 25 dimensions from males. African, Asian, Hispanic and other ethnic groups have asymmetric dimensions that differ significantly from those of Europeans. These findings could be important to certain applications like the design of facial fits, as well as guidelines for facial cosmetic surgeons. Lastly, we train a neural network classifier that employs asymmetric dimensions for gender and race classification. The experimental results show that our trained classifier outperforms the support vector machine (SVM) and k-nearest neighbors (kNN) classifiers. [ABSTRACT FROM AUTHOR]