Finger texture biometric verification exploiting Multi-scale Sobel Angles Local Binary Pattern features and score-based fusion |
| |
| Affiliation: | 1. ATVS, Biometric Recognition Group, Universidad Autonoma de Madrid, C\\Francisco Tomas y Valiente, E28049 Madrid, Spain;2. Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong;3. Instituto para el Desarrollo Tecnologico y la Innovacion en Comunicaciones, Universidad de Las Palmas de Gran Canaria, Campus de Tafiera, E35017 Las Palmas, Spain;1. National Institute Technical Teacher’s Training and Research, Kolkata, Block-FC, Sector-III, Salt Lake City, Kolkata 700106, INDIA;2. Department of Computer Science and Information System, Birla Institute of Technology and Science Pilani, Jhunjhunu, Rajasthan 333031, INDIA;1. Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata, India;2. Department of Information Technology, Jadavpur University, Kolkata, India;1. School of Cyberspace, Hangzhou Dianzi University, Hangzhou, 310018, China;2. School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, 310018, China;3. School of Computer Science, Guangzhou University, Guangzhou, 510006, China;4. School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, 310018, China;5. School of Computer Science and Technology, Zhejiang University, Hangzhou, 310058, China |
| |
| Abstract: | In this paper a new feature extraction method called Multi-scale Sobel Angles Local Binary Pattern (MSALBP) is proposed for application in personal verification using biometric Finger Texture (FT) patterns. This method combines Sobel direction angles with the Multi-Scale Local Binary Pattern (MSLBP). The resulting characteristics are formed into non-overlapping blocks and statistical calculations are implemented to form a texture vector as an input to an Artificial Neural Network (ANN). A Probabilistic Neural Network (PNN) is applied as a multi-classifier to perform the verification. In addition, an innovative method for FT fusion based on individual finger contributions is suggested. This method is considered as a multi-object verification, where a finger fusion method named the Finger Contribution Fusion Neural Network (FCFNN) is employed for the five fingers. Two databases have been employed in this paper: PolyU3D2D and Spectral 460 nm (S460) from CASIA Multi-Spectral (CASIA-MS) images. The MSALBP feature extraction method has been examined and compared with different Local Binary Pattern (LBP) types; in classification it yields the lowest Equal Error Rate (EER) of 0.68% and 2% for PolyU3D2D and CASIA-MS (S460) databases, respectively. Moreover, the experimental results revealed that our proposed finger fusion method achieved superior performance for the PolyU3D2D database with an EER of 0.23% and consistent performance for the CASIA-MS (S460) database with an EER of 2%. |
| |
| Keywords: | Finger texture Finger fusion Local binary pattern Biometric verification Probabilistic neural network |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
