Abstract: To overcome the disadvantages and better the performance of minutiacbased and imagcbased fingerprint identification methods,a fingerprint recognition algorithm,consisting of the processes of classification selection and classifier fusion, was put forward. Three image-based methods, based on orientation field, texture features of gray level cooccurrence Matrix, histogram features of local binary pattern operator, were combined with minutiacbased method for fingerprint recognition. Experimental results indicate that the performance of fusion-based method is better than any method used alone in fusion and can be applied to automatic fingerprint identification system.

Key words: Fingerprint dentification,Information fusion,L13P,Gray-level co-occurrence matrix