Texture Generation for Fashion Design Using Genetic Programming

Abstract

We present a methodology to generate textures for fashion design using Genetic Programming(GP). The proposed GP based scheme evolves tree representation of procedures to generate textures. We use Contrast of the generated textures/images to filter out poor textures. After filtering, the fitness value of a new texture is set as the fitness value of a cluster of (already generated) textures which is more similar to this new texture. For this, we execute a clustering step during the evolution. Statistical features are used to find the similarity between textures. Since the quality of a texture is best assessed by a human being, if the generated texture is quite dissimilar to the existing textures then user's discretion is sought to assign a fitness value to it by visual inspection of the texture.

A review of digital fashion research: before and beyond communication and marketing

“…It also addresses the development of practices derived from the adoption of big data and networks, such as generative adversarial learning and genetic programming that contribute to product creation, including patterns such as fractal patterns, colour forecasting and the generation of various textures. Additionally, it includes research that develops systems for an efficient retrieval of visual information from images and photographs (Dai, 2011;Dongdong, 2012;Gu & Liu, 2010;Kharbanda & Bajaj, 2013;Kuswanto, Iftira, & Hapinesa, 2018;Lee, Lim, Jung, & Park, 2015;Li, Lu, Geng, & Wang, 2009;Liu, Zeng, Tao, & Bruniaux, 2019;Long, Li, & Luo, 2009;Muni, Pal, & Das, 2006). This sub-category presents novel and effective technologies that enable, for example, product customisation or support sustainable fashion (Pasricha & Greeninger, 2018;Wang, Zeng, Koehl, & Chen, 2014).…”

Applications of artificial intelligence in the apparel industry: a review

“…Texture is the surface property of a fabric, which is the sensuous element of apparel design. Muni et al 22 developed an interactive texture generation process to generate optimal procedural textures. However, their approach cannot be used for the generation of color texture.…”

“…GP is an evolutionary algorithm invented by Cramer 111 and inspired by biological evolution to find computer programs that perform a user-defined task. Muni et al 22 utilized GP to obtain a tree representation of procedures generating procedural textures. Using this procedure, the gray or color value of each point in the procedural texture was generated.…”