A Morphological Approach to Match Two Color Images Using Deep Learning
Sitikantha Chattopadhyay, Pinaki Pratim Acharjya, Chandan Koner · 2018 International Conference on Smart Systems and Inventive Technology (ICSSIT) · 2018
Comparing two color images and taking a decision about their similarity or dissimilarity is one of the fundamental applications in digital image processing field. If different features can be extracted from two images and compared, then by analyzing the result we can say about their similarity or dissimilarity. If the features extracted and edge detected has a similarity greater than a threshold value, then we can conclude that the images are same, otherwise they are different. In this paper, we have used mathematical morphology to compare two color images and implemented using a feed-forward Artificial Neural Network with two hidden layers. This method has been applied in real life images and given a successful and promising result.