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

An Effective S-Box Comparison by Parity Based Fault Detection Scheme Using Composite Fields

AES is the most effective algorithm for network security that is more confidential, reliable and robust. A key step in the Advanced Encryption Standard (AES) algorithm is the subbyte transformation and its inverse . The...

An Approach for clustering uncertain data objects: A Survey

Recently, uncertain data objects is used in various applications such as VANET environment, sensors applications, image processing based system etc. Clustering of uncertain data is a major concept in data mining since mo...

Sensor-Network based Intelligent Water Quality Monitoring and Control

Recent advances in communication technology, especially wireless sensor networks have inspired numerous remote sensing and control applications. Here, we focus on the monitoring and control of water quality in natural wa...

Integrating Assembly Lines based on Lean Line Design Concept 

In today‟s competitive business scenario manufacturing industries are under the pressure to reduce cost and cycle time. It is a lean manufacturing concept with a systematic approach to identify and eliminate wast...

Automatic Text Extraction in Video Based on the Combined Corner Metric and Laplacian Filtering Technique  

Text in the videos and images provides very major information about the content of the videos, the video text extraction provide a major role in semantic analysis of the video, video indexing and video retrieval wh...

Download PDF file
  • EP ID EP146556
  • DOI -
  • Views 82
  • 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