Research of dual-model recognition algorithm based on finger vein and finger crease

• Published in: 2012 5th International Conference on Biomedical Engineering and Informatics pp. 358 - 361
• Main Authors: Guan, Fengxu, Wu, Qiu-yu, Jiang, Zhi-chao, Wang, Ke-jun
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2012
• Subjects: Biology; dual-model recognition; Feature extraction; Filtering; finger crease; finger vein; Fingers; Image recognition; Image segmentation; Libraries; Noise; pixel-level fusion; Skin; Wavelet transforms
• ISBN: 9781467311830; 1467311839
• DOI: 10.1109/BMEI.2012.6513014

The advantages of finger vein are in vivo identification, internal features, non-contact and security, but it's identified features are insufficient. Finger crease is in the surface of finger skin, and it has some stable biological features. So a finger has two kinds of biological features. Combined with the advantages and the disadvantages of finger vein and finger crease, a new dual-model recognition algorithm based on finger vein and finger crease is presented. First, the finger vein image and the finger crease image of a finger are acquired and preprocessed Separately. Second, the two types of images are fused based on pixel-level image. Finally, feature extraction and recognition are researched for the fused images. Experimental results on our database of finger vein images and finger crease images show that the recognition of dual-model method presented is higher than the recognition of single-model finger vein.