Fingerprint Identification using Fusion of Pores and Minutiae Extraction at different Resolutions

In the presented work, it is proposed to enhance the finger print image quality based on an adaptive fingerprint enhancement method that is based on contextual filtering. The term adaptive implies that parameters of the method are automatically adjusted based on the input fingerprint image. Once the finger print image is enhanced at the required level, the pores are extracted based on segmentation of the finger print image by eliminating the finger print area above a threshold limit. The pores location and then inter-distances are computed and stored in a data base. Further, the minutiae are extracted and again their location and inter-distances are computed and stored in a data base. Same procedure is repeated for the query image and standard deviation is computed between the inter-distance of the query image and data base images. The finger print information based on pores and minutiae are fused together in order to get the matching score.