CIA Finger Print Scanner

Abstract

Governmental Security Agencies in Pakistan suffer from lack of funds and less technical staff due to which Law Enforcements Agencies like Criminal Investigation Agency use manual techniques for Fingerprint matching and Identification. This leads to less efficiency and accuracy. The results are less reliable as well as more time is required to solve the cases than the time available. This obstructs a quick and efficient justice to the people. Our Project is to study and implement a fingerprint recognition system based on Minutiae matching quite frequently used in various fingerprint algorithms and techniques. The approach involves extraction of minutiae points from the sample fingerprint images and then performing fingerprints in question. Our implementation incorporates image, image segmentation, feature (minutiae) extraction and minutiae matching. It generates a percent score which tells whether two fingerprints match or not. An automated software has been developed that is a standalone application to resolve their difficulties, the product is reliable, accurate and efficient. With regard to database management a template for data entry has been provided for future purposes and data entry for the Agency has been done. The scope of this project includes developing a full functional system and data-entry for the Agency. A lot of fingerprint matching software’s are available which are developed using different algorithms and techniques each having their advantage and disadvantage. One technique is Optical Correlation which is not a very good technique as complete images are stored in the database which makes the software very slow in search process. Other techniques include pattern matching in which fingerprints are divided into small patterns and its minutia such as ridge directions and bifurcations are stored. The technique that we used in our implementation is a combination of two different techniques which mainly include minutia extraction and “ten print card”. The minutia points such as ridge endings and bifurcations are extracted and stored in a separate file other than the image file, when the search process starts it only searches the file in which minutia are stored not the complete image file as in the optical correlation algorithm. This makes the system fast, efficient and reliable.