Primary Colour Detection in An Image

Abstract

Primary Colour Detection in an Image, Traditional methods of color cast detection do not discriminate between images with true cast and those with dominant colors. This may result in an inaccuracy of the color cast measurement. In order to overcome the limitation of traditional methods, an approach based on image semantic is present. It can improve the accuracy and reliability of the detecting results by the means of recognizing and removing the dominant color objects · and analyzing the color distribution of the whole image. Class specific color detection is already implemented in some systems, but image classification usually relies on global image features only. The method of recognizing the dominant color objects is based on block-features and region-features by using K-Means Clustering in this project. It shows a significant improvement over previously achieved classification for a variety of critical image classes. The comparison of the results of the approach proposed to that of people shows that it is reliable and effective. This project proposes the use of Machine Learning Techniques and Deep Learning Algorithms.