Compression of combined fingerprints for secured authentication

In this paper, we propose a new idea based on authentication and compression. The two fingerprints have been registered during the enrollment process and a combined fingerprint template is generated based on minutiae positions from one finger and the orientation from the other finger. This template is compressed using sparse representation and stored in the database for future retrieval. With the help of an existing fingerprint reconstruction approach, we are able to convert the combined minutiae template into a real-look alike combined fingerprint. Using the method of sparse representation, we are able to obtain the coefficients which contain the actual information of the user. Hence the information cannot be easily stolen. The effects on actual fingerprint matching or recognition are not investigated.