Personal Identification Using Palmprint Biometrics Based on Principal Line Approach

Abstract

Palmprint is the one of the important biometrics characteristics with higher user acceptance. In palmprint, palm-lines are more important features for personal identification. In this paper, in preprocessing a Gaussian filter is used to smooth the image and next ROI is extracted based on valley points. The Canny edge detection operation is proposed to extract principal line features. The edge direction and gradient strength of each pixel in the preprocessed image are found using Sobel masks. Then edges are traced using that information. Finally, non-maximum edges are suppressed by finding parallel edges and eliminating those with weaker gradient strengths. In this way principal lines are extracted and resultant image is obtained. The matching is done by dividing the resultant image into 9X9blocks. The blocks are traced to create feature vector. While generating a template the feature vector bit is set if the concerned block contains the line. Personal identification is done based on the distance matching between the stored templates and the test palmprint image. Experiments show that the proposed method using PolyU palmprint database offer the accuracy of 86% personal identification

Authors and Affiliations

Sumangala Biradar

Keywords

Related Articles

Survey on Data Sharing and Re-Encryption in Cloud 

Cloud storage helps enterprises and government agencies significantly reduce their financial overhead of data management, since they can now archive their data backups remotely to third-party cloud storage provider...

Role of Artificial intelligence in MANET 

An adhoc network consists of wireless mobile nodes forming a temporary network without any infrastructure or centralized administration. Mobile Adhoc Networks (MANET) are self-organizing and self-configuring multihop w...

A Review of Soft Computing Advance in Genetics & Laser Biomedical Instrumentation  

Soft computing refers to a collection of computational techniques in computer science, artificial intelligence, machine learning, medical instrumentation which attempt to study, model and analyze very complex p...

Review of Comparative Analysis of Empirical Propagation model for WiMAX  

The propagation models for path loss may give different results if they are used in different environment other than in which they were designed. In this paper we review of compare the different path loss empiric...

ENHANCED TECHNIQUE FOR SECURED AND RELIABLE WATERMARKING USING MFHWT

A general watermarking techniques are used for copy right protection. In this watermarking scheme should achieve the features of robustness and imperceptibility. This paper represents the watermarking algorithm in the DW...

Download PDF file
  • EP ID EP146556
  • DOI -
  • Views 83
  • Downloads 0

How To Cite

Sumangala Biradar (2013). Personal Identification Using Palmprint Biometrics Based on Principal Line Approach. International Journal of Advanced Research in Computer Engineering & Technology(IJARCET), 2(7), 2262-2267. https://europub.co.uk/articles/-A-146556