Font Size: a A A

Multi-biometric Fusion Recognition Technology Research

Posted on:2009-04-22Degree:MasterType:Thesis
Country:ChinaCandidate:J H GaoFull Text:PDF
GTID:2208360245986122Subject:Signal and Information Processing
Abstract/Summary:PDF Full Text Request
In such a high developing information age, how to verify a person's identity correctly and protect information security is a crucial problem. Biometric systems seem to be in place of traditional identification such as key, password and ID cards in the future due to their convenience, security and trustiness. Most developed biometric systems are unimodal. However, their performance easily degrades in a factual environment. Because every biometric system has its own limitations, the system which uses more than one biometric at the same time is known as a multimodal identification system, and can be adopted to combat these limitations. Multimodal recognition is therefore acknowledged as a mainstream research area as the next generation of biometric personal recognition.This paper introduces the definition of fusion, categorizes, and fusion method; studied diagonal image transform, inquiry into the characteristic compression of two-dimensional cosine transform, on the basis of these, the work includes(1) A new model for face and iris feature fusion recognition is presented on the basis of feature extraction and fusion.(2) Fused with face and iris , using 2DPCA for feature extraction from vertical and lateral direction. Finally, the Nearest Neighbor (NN) classifier is selected to perform face recognition.(3) Kernel Fisher Discriminant Analysis (KFDA) is chosen as feature fusion; finally, Nearest Neighbor (NN) classifier is selected to perform recognition.(4) Combined with diagonal image transform, two-dimensional discrete cosine transform (2DDCT) is used in face for feature compression, using 2DPCA for feature extraction. Finally, the Nearest Neighbor (NN) classifier is selected to perform face recognition.Face database and iris database show that it reduced the dimension, utilized the classified information, and improved correct recognition rate effectively. A new approach is supplied for multimodal biometric identification.
Keywords/Search Tags:Biometric Feature Recognition, Face Recognition, Two-Dimensional Principal Component Analysis, Two-Dimensional Discrete Cosine Transform, Kernel Fisher Linear Discriminate Analysis, Multimodal Biometric Recognition, Feature Fusion
PDF Full Text Request
Related items