Design & Implementation an E-Commerce Sites Security System based on Local Binary Pattern Fingerprint Verification

E-Commerce has played a major role in changing the global economic thought, but it still suffers from serious threats concerning the protection of e-commerce transactions. As a result, there is a great demand for advanced protection system to increase consumer confidence and the institution in the field of e-commerce. In this paper, an e-commerce system is presented, which is a web application designed for browsing and purchasing products from the net. This system provides improved security techniques which are password and fingerprint verification to complete the purchasing procedure and protect e-bank and the system from intruder. The verification algorithm in purchasing procedure includes a series of steps starting with using canny edge detection filter and then using Local Binary Pattern (LBP) and histogram properties as statistical approaches for feature extraction from fingerprint image. A fingerprint image is first divided into (3*3) regions from which LBP histograms are extracted and then converted into a single feature vector. This feature vector forms an efficient representation of the fingerprint and is used to measure similarities between images. The result of matching has been compared by using the Chi Square Statistic (X2) that depend on the resulted feature vector which is a powerful information to prove identity of a person. ASP.NET 2013, SQL Server 2014, VB.NET 2013 and C# 2013 programming language has been used to execute the paper algorithms. Finally, it must be mentioned that an excellent results have been obtained using different fingerprint images.

Keywords: E-Commerce, Local Binary Pattern (LBP), Histogram properties, Feature vector.

DOI link: Security System