Enhanced Image Quantization Through Hybrid Sine Cosine Optimization and K-Means Clustering

The need for quantization of color images arises because of limitations of image display and hardcopy, data storage, and data transmission devices. Many of the current methods for color simplification in images don't provide the best results. This can lead to noticeable color changes and the appearance of false outlines, especially when trying to represent images with a small set of colors. This paper describes a new approach to finding the optimal solutions of the color image quantization problem using a Sine Cosine Optimization (SCO) algorithm. The nature and the difficulty of the problem and its formulation are discussed. Then, the SCO algorithm is presented, and the representation of the problem with this method is explained. The effect of theparameters such as the Sine and Cosine phase updating rulesand population size on the quality of solutions is studied. Solutions obtained with the SCO algorithm are compared with those of heuristics and the K-means clustering algorithm, demonstrating the superior quality of the results achieved with the SCO algorithm.