Flawless Fingerprint Matching Approach based on SVM Classifier

Abstract

Elastic distortion of fingerprints is such of the major causes for false non-match. While this problem affects all fingerprint recognition applications, it is especially dangerous in negative recognition applications, such as watchlist and deduplication applications. In a well-known application, malicious users make out purposely distort their fingerprints to evade identification. In this paper, we proposed latter algorithms to regard and rectify skin distortion based on a single fingerprint image. Distortion detection is viewed as a two-class classification problem, for which the registered ridge orientation map and period map of a fingerprint are used as the feature vector and a SVM classifier is used to perform the classification task. Distortion rectification is viewed as a regression problem, to what place the input is a improper fingerprint and the product is the distortion field. To resolve this problem, a database of distinct distorted reference fingerprints and corresponding distortion fields is built in the offline stage, and earlier in the online turn, the nearest neighbor of the input fingerprint is found in the recommendation database and the corresponding distortion work is used to resolve the input fingerprint into a balanced one.

Authors and Affiliations

K. Amulya, V. Priyanka, Ch. Sudheer Kumar

Keywords

Related Articles

Gaurav Kumar, Prof. Durgesh Wadbude

We propose a novel compression scheme for digital images using chrominance channels with feature descriptor and Discrete Cosine Transform (DCT). The feature descriptor of chrominance channel is based on their error metr...

slugComparative Analysis of Web Mining Techniques: Survey

The cluster of technologies and design are known as web, which has now emerged as a fertile area for data mining research. The web mining research is being carried out across the globe. Many research communities such as...

Analog Data Signal Compression by using Differential Pulse Code Modulation with Microcontroller

Compression is a process of converting an input data stream into another data stream that has a small bit size. Compression is take place because of data is normally represented in the computer in a format that is longe...

Vehicle detection system through image Analysis using log-gabor filter

Vehicle detection based on image analysis has attracted increasing attention in recent years due to its low cost, flexibility, and potential toward collision avoidance. In particular, vehicle verification is especially...

Fabrication And Analsys Of Metal Cutting Chop Saw

A chop saw is a power tool used to make accurate cuts in wood, plastic, and metals. It has a fixed blade, attached to a moving arm that spins over a small worktable. Chop saws are used to create a rough, initial abrasiv...

Download PDF file
  • EP ID EP23908
  • DOI http://doi.org/10.22214/ijraset.2017.4202
  • Views 271
  • Downloads 10

How To Cite

K. Amulya, V. Priyanka, Ch. Sudheer Kumar (2017). Flawless Fingerprint Matching Approach based on SVM Classifier. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 5(4), -. https://europub.co.uk/articles/-A-23908