• Rama Krushna Rath
• Rupalin Nanda

In order to use a genetic algorithm to solve a problem, a method is required of converting a string of numbers (or symbols) into possible solutions to the problem. Gray scale images can be taken for starting application. This allows solutions to be mutated by changing symbols at random. Importantly, every possible string of symbols must generate a valid solution. Images are widely used in media contexts such as web design, games and video animation. In doing so, the user is also able to control various settings and parameters as suggested by [1], [2], [3], [4], [5] & [6]. In this paper it is described that an interactive image generation tool based on genetic algorithm can be used to create novel, surprising, and sometimes stunning images. The system permits the user to progressively evaluate and generate new images from previous sets of images. For each run of evolution, the number of circles is fixed. The reason being that the more circles an image has, the more able it will be to mimic the target image, so it is figured out that the number of circles would keep increasing. It will be interesting to allow the number of circles to change, but have a penalty for each circle, thus tending to select images made of the fewest circles. Each circle has six parameters: • an x-coordinate (0 to the image's width) • a y-coordinate (0 to the image's height) • a z-coordinate, which determines the order in which circles are drawn • a diameter (from 0 to a third of the image’s height) • a grey scale color (0 to 255, corresponding to black to white) • a transparency (0 to 255, corresponding to completely transparent to completely opaque) • The z-coordinate does not have a value as such, but is represented by the order of the circles in the genome. Circles are drawn in the order they appear in the genome onto a white background that has the same dimensions as the target image. Mutations in the z-coordinate therefore require the genome to be rearranged, allowing a circle from the back to be brought to the front. With 128 circles, a genome therefore consists of 6400 numbers.

Genetic Algorithms, Genome, Fitness measure, Mutation

"Evolving Images By Analyzing Genome", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 1, page no.d29-d34, January-2022, Available :http://www.jetir.org/papers/JETIR2201304.pdf

"Evolving Images By Analyzing Genome", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 1, page no. ppd29-d34, January-2022, Available at : http://www.jetir.org/papers/JETIR2201304.pdf