An efficient method for fingerprint searching using recurrent autoassociative memory is proposed. This algorithm uses recurrent autoassociative memory, which uses a connectivity matrix to find if the pattern being searched is already stored in the database. The advantage of this memory is that a big database is to be searched only if there is a matching pattern. Fingerprint comparison is usually based on minutiae matching, and its efficiency depends on the extraction of minutiae. This process may reduce the speed, when large amount of data is involved. So, in the proposed method, a simple approach has been adopted, wherein first determines the closely matched fingerprint images, and then determines the minutiae of only those images for finding the more appropriate one. The gray level value of pixels along with its neighboring ones are considered for the extraction of minutiae, which is more easier than using ridge information. This approach is best suitable when database size is large.
[1]
Timo Honkela,et al.
Connectionism in a Broad Perspective
,
1995
.
[2]
C. V. Kameswara Rao,et al.
Type Classification of Fingerprints: A Syntactic Approach
,
1980,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[3]
Anil K. Jain,et al.
Adaptive flow orientation-based feature extraction in fingerprint images
,
1995,
Pattern Recognit..
[4]
Lonnie Chrisman,et al.
Learning Recursive Distributed Representations for Holistic Computation
,
1991
.
[5]
Jordan B. Pollack,et al.
Recursive Distributed Representations
,
1990,
Artif. Intell..
[6]
Erdal Panayirci,et al.
Extension of the Cox-Lewis method for testing multi-dimensional data
,
1988
.
[7]
Alessandro Farina,et al.
Fingerprint minutiae extraction from skeletonized binary images
,
1999,
Pattern Recognit..
[8]
Craig I. Watson,et al.
Neural Network Fingerprint Classification
,
1994
.