An Astute Automaton Model for Objects Extraction Using Outer Totality Cellular Automata (OTCA)

Abstract

Object formation is imperative to the recent computer vision, pattern recognition, healthcare, and automation applications. The objects are generated from images by defining edges and the segmentation process. This article introduced a novel method, Outer Totality Cellular Automata (OTCA), for defining actual and continuous edges of the image objects. The OTCA analysis nearby 25 neighbourhood pixels of all the pixels and generate a unique and efficient threshold. The proposed method has three primary functions, i.e. vitality, rule mapping, and improved morphological functions. The key objectives are image smoothing, neighbourhood analysis, defining game of life rule, and edges smoothing. Notably, the proposed method aimed to segment different coloured images, i.e., RGB, HSV, and YUV. The proposed method also aimed to produce more truthful results on blurred, reflected, shaded night vision images. The experimental process demonstrates using standard open-source datasets and validated using image quality assessment parameters, i.e., entropy, PSNR, SSIM, and MSE. The results claim 3% − 12% more structural analogous, factual, and accurate than existing classical methods and recent searches.