ACORB – An ACO and ORB based Hybrid Image Feature Detector
Vishwas Raval, Apurva Shah · 2018
Feature detection is most crucial stage in image identification in computer vision, which helps computer recognizing the image. This work is part of a research for the Indian currency recognition for blind people. Each country has its own currencies with unique features, colors, denominations and international value. As we move towards first quarter of 21st Century, world is facing various issues like terror-funding, smuggling and that has lead to the printing of fake currencies. Due to this, many a times a person would never be able to know that the currency which one is holding is genuine or fake. This can only be decided if one knows all the features of the currency. However, for a common man, it is not possible to remember the features of the currency; especially for blind person it is not at all possible. Though the denomination can easily be recognized for a currency but it becomes difficult to identify a counterfeit currency from the real one. This paper proposes an ACO based novel concept for feature detection using ORB feature detector, named ACORB. It has been tested thoroughly to check its effectiveness and the concept seems promising based on its results. The main motive of this work is to design and develop an algorithm for Indian currency recognition in the regional languages to help the visually challenged people to recognize the currency denomination and to check if the currency is fake or genuine.