Offline Signature Recognition Using PCA-FFNN Method and Adaptive Variance Reduction and Invariant Moment Feature Extraction
Journal Title: International Journal for Research in Applied Science and Engineering Technology (IJRASET) - Year 2017, Vol 5, Issue 6
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
- EP ID EP24663
- DOI -
- Views 360
- Downloads 11
Total Productive Maintenace: A Detailed Study
tpm (total productive maintenance) is a holistic approach to equipment maintenance that strives to achieve perfect production. In addition, it values a safe working environment. Total productive maintenance (tpm) is an...
Effects caused on Leaky integrate and fire model
for analyzing the behaviour of neural system, the model used most widely is integrate and fire model. The membrane potential of a neuron in terms of injected current and synaptic inputs is described by integrate and fir...
Face Detection based on Skin Color in Image by Neural Networks
Face detection is one of the challenging problems in the image processing. A novel face detection system is presented in this paper. The approach relies on skin-based color features extracted from two dimensional Discre...
Online Housing Society Management System
This paper presents the various methods in which we can manage the housing society by a system which is created using cloud. And makes the current situation in the society simple and efficient. As we know there is an in...
Defeating DOS Attacks in Low Rate Networks Using Network Multifractal.
Nowadays, distributed denial of service (DDoS) attacks pose one of the most serious security threats to the Internet. DDoS attacks can result in a great damage to the network service. To have a better understanding on D...