Offline Signature Recognition Using PCA-FFNN Method and Adaptive Variance Reduction and Invariant Moment Feature Extraction

Abstract

Although offline handwritten signature recognition has been frequently researched, it nevertheless calls for an improvement of popularity rate. Most of present techniques attention on feature extraction (FE) to improve their performance. In this analyze, we put in force Offline Signature attention utilizing principal component analysis (PCA) and Feed Forward Neural network (FFNN) method. We extract signature features using histogram of Orientation (HOG) and Seven Invariant Moments. The proposed system works in three parts. First Pre-processing: where resizing, binarization, noise reduction is done to make signatures all set for FE consequently, the variance discount technique is utilized to normalize offline handwritten signatures in means of an adaptive dilation operator. Then the range of signatures is analyzed in conditions of coefficient of variant (CV). The optimal CV is obtained and used to be a threshold limit value for the acceptable variance reduction. Within the experimental outcome, we extended signature recognition accuracy in conditions of attention expense up to 95.8%with database of SigWiComp2011 (48 signatures of 12 persons).

Authors and Affiliations

Priyanka Chauhan, Nirupma Tiwari

Keywords

Related Articles

Emergency City Guide: Application for Android Mobile

Mobile phone is now a necessary part of human life. There is a continuous rise in number of mobile applications, specifically on the people’s daily lives. In such applications, the location dependent systems have been i...

A Hybrid Data Hiding Approach for Securing Online Transactions

Online Banking is an arrangement of administrations given by a gathering of organized bank offices. Bank clients may get to their assets and perform other basic exchanges from any of the part branch workplaces. The real...

H2S Gas Sensor at Room Temperature For SnO2-CuO Thick Film

The SnO2 and CuO powder mixed with different ratio and heated at 8000C and then this powder is used to prepared thick films by a screen – printing technique on glass substrate. The H2S gas sensing properties, particular...

Define Rules for New Rapid Business Process Model

Since last decade, business process model are widely used all over the world to satisfy business needs. Interest to develop this paper is that any organisation or industry wants to achieve their business goal very quick...

Document Constellation for Rhetorical Associate Analysis

In this paper PC rhetorical analysis investigation, thousands of files ar usually surveyed. during this abundant of the information in those files consists of formless manuscript, whose investigation by PC examiners is...

Download PDF file
  • EP ID EP24663
  • DOI -
  • Views 356
  • Downloads 11

How To Cite

Priyanka Chauhan, Nirupma Tiwari (2017). Offline Signature Recognition Using PCA-FFNN Method and Adaptive Variance Reduction and Invariant Moment Feature Extraction. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 5(6), -. https://europub.co.uk/articles/-A-24663