D. Zerbino

Full text PDF

Abstract. The article proposes a rule for improving image sharpness and analyzes its implementation by means of the cellular automata formalism and neural networks. It has been proved, that the previously known contrasting algorithm, which uses a template and 3×3 pixels, can be improved considerably by repeatedly applying the iterative process over templates 2×2 with the rule “anti – blur” ( C 11 = C 11 x F – ( C 12 + C 21 + C 22) x S ) and gradient color correction at each step after the “anti – blur”. Colors of images in the template are presented as real numbers (R, G, B). To correct the gradient (C11 < C12, C11 < C21, C11 <C 22, C 12 < C 22, C 21 < C 22) it is necessary to choose a number Cij, that requires minimal tightening in the direction of the neighbor’s color. Number of necessary iterations of the rules application depends on the image.

Keywords: cellular automata, image contrasting, sharpness, correct gradient, logical correction of colors, neocognitron

Improving Image Sharpness by Surface Recognition

an international quarterly journal on economics of technology and modelling processes