Convergence of Cloud with AI for Big Data Analytics

16Artificial Intelligence Approach for Signature Detection

Amar Shukla, Rajeev Tiwari^*, Saurav Raghuvanshi, Shivam Sharma and Shridhar Avinash

University of Petroleum and Energy Studies, Dehradun, Uttarakhand, India

Abstract

The globe today relies on multiple security systems to protect its data and monetary transactions. Handwritten signature recognition uses a variety of methods and algorithms. In this paper we leverage the OpenCV library and Qt for GUI to implement Support Vector Machine (SVM) and Histogram of Oriented Gradients (HOG). By using the SVM algorithm, one can find an N-dimensional plane that provides a distinctly classifiable classification of data points on a plane. Meanwhile, HOG is a feature descriptor of an image that simplifies the image by extracting the helpful information while discarding the extraneous information. We will convert the image into a feature vector of length according to the precision set by the end-user or developer, using HOG feature descriptors.

Keywords: HOG, SVM, machine learning, Open CV, signature recognition

16.1 Introduction

The Security Systems are designed for the authentication of the user who is trying to access any kind of confidential data with the verification techniques like Iris Scanner, Fingerprint detection, Handwritten signature Recognition, Vocal sound recognition system, any alphanumeric pass code, and many more techniques for the same.

With the advancement of technologies in today’s era, the number of intruders ...