Region based Minutiae Mass Measure for Efficient Finger Print Forgery Detection in Health Care System
A. Vinoth1, S. Saravanakumar2

1A. Vinoth, Research Scholar, Department of Computer Science, Bharathiar University, Coimbatore (Tamil Nadu), India.
2Dr. S. Saravanakumar, Associate Professor, Department of Computer Science Engineering, Shanmuganathan Engineering College, Arasampatti (Tamil Nadu), India.
Manuscript received on 13 December 2018 | Revised Manuscript received on 25 December 2018 | Manuscript Published on 24 January 2019 | PP: 9-14 | Volume-7 Issue-4S2 December 2018 | Retrieval Number: Es2030017519/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The modern security system has used various biometrics in authenticating the human. Among them, the finger print has been used as the key in major systems. Even though, the finger prints are unique and cannot be modified, there are intrusions which are performed by fake finger prints prepared by malicious entities. Various medical organizations maintain records of different patients which has more sensitive data which has to be secured from illegal access. Even the finger prints has been used as key there are malformed users who can try to intrude the system and steal information. So detection the forged finger prints becomes more essential. Number of approaches available for the detection of forged prints, they does not produce efficient results in forgery detection. Towards the problem of forgery detection, an efficient Region Based Minutiae Mass Measure (RMMM) approach is presented towards support the security of health care systems. The user has been validated with general information and the finger print has been captured through the capturing device. The method first enhances the input finger print image by applying gabor filter to remove the noise. Then the noise removed image has been improved for its quality by sharpening the edges of ridges present in the image. Then the image has been split into number of regions and for each sectional image, the method extracts various minutiae features like ridge island, number of ridge dots, ridge ends, ridge enclosures, and ridge bifurcation. Using the features extracted, the method estimates the Minutiae mass value for each sectional image. The same has been performed in the input test image and based on the minutiae mass value, the forged print has been detected. The method has produced efficient results on forged finger print detection and improves the classification accuracy.
Keywords: Finger Print, Authentication Systems, Minutiae, MMM, Forgery Detection, Health Care Systems.
Scope of the Article: Healthcare Informatics