Cognitive Theme Preserving Color Transfer for Fabric Design

Cognitive Theme Preserving Color Transfer for Fabric Design

Dejun Zheng (Department of Computing & Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong), George Baciu (Department of Computing & Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong), Yu Han (Department of Applied Mathematics, School of Science, Xidian University, Xi’an, China & Department of Computing & Institute of Textiles and Clothing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong) and Jinlian Hu (Department of Applied Mathematics, School of Science, Xidian University, Xi’an, China)
DOI: 10.4018/jssci.2012070103
OnDemand PDF Download:
$37.50

Abstract

The authors present a fully automatic method of color theme extraction and transfer for fabric color design. For real-life fabrics, such extraction and transfer is performed through a highly time consuming and knowledge intensive process, known as color theme design. Specifically color and tone style adjustments are part of a generic process of cognition involved in the creation of new fabric designs. The authors explicitly formalize the process of color theme extraction from a set of images as a process of color mood based hierarchical data clustering and optimization. They begin with image sorting within a cognitive theme and color compatibility learning from large datasets. They then propose fully automatic color-texture association and color transfer algorithms which satisfy the criteria used in professional fabric pattern design while ensuring the plausibility of the cognitive theme preserved color transfer from the images to fabric patterns. Lastly, the color transfer process is formulated as a constrained optimization problem that is solved efficiently by total variation minimization. The use of color theme associations can automatically generate new fabric designs that rival complex commercial designs that are otherwise difficult to generate even by experienced designers. The authors’ fully automatic color theme preserving transfer method leads to a new approach to fabric design that significantly save time and cost for both fashion designers and computer artists.
Article Preview

1. Introduction

Fashion designers conceive color composition as an ensemble of tones, shades and tints that often resemble an abstract or natural theme. Color and tone adjustments are among the most frequent fabric design operations. A challenging problem in this process is given a set of natural images associated with a subject or a theme, the problem is to discover the underlying cognitive relationships that connect textures and color tones that are perceived by an observer or in our case, a fabric designer. Learning theories cannot clearly explain how designers use language and color cognition so well in their designs to express a theme or a topic given the inherently small amount of data available to them. This lack of learning data lead to the idea that there may be innate language structures in the brain (Chomsky, 2006). In Massey, (2012), the author argues that the cognitive processes of underlying language understanding may not be logical-deductive or inductive, at least not for basic forms of understanding such as the ability to determine the topics of a text document. We introduce a Cognitive Color Informatics (CCI) framework via a transdisciplinary way (Wang, 2003) to study the cognitive color theme in the fabric pattern design process.

Like other color design process, such as advertising and decorating, color and tone adjustments are among the most frequent operations for fabric design. In the cognitive process of creating new fabric patterns, it is important for designers to convey a meaningful theme or characteristic attribute of their desired design styles in order to both communicate as well as classify design styles. Inspiration for new designs can be found in many sources, such as photography, fashion magazines, art, and color swatches. Fashion designers often evaluate great design ideas by how people generally appreciate and cherish their designs.

The contributions of this paper are as follows. First, we begin with a study on reformulating the criteria used in professional design inspired by color as a set of color mood space requirements. These include color emotion description and prediction, respectively expressing color abstraction and compatibility. Further, these can be served as a sorting process that identifies the matched image to a color mood from the source data and pattern. Our main contribution consists of casting the process of cognition in fabric design as an optimization problem for generating a suitable cognitive color theme design combined with fabric texture properties. We provide a new framework for fabric design that simultaneously takes into account the design of the fabric color and the texture effects in a cognitive loop by providing operations at the level of color theme assembly.

Second, we propose a data-driven color theme optimization approach to facilitate color themes extraction for fabric designs. We use color mood clustering (Ou, Luo, Woodcock, & Wright, 2004a; Ou, Luo, Woodcock, & Wright, 2004b) and weave pattern entropy functions to extract color themes from abstract or natural images associated with a subject or a theme, and then apply them in a fabric design to maintain the same theme in the cognition of observers. The measure of the difference between input images and fabric designs is quantified in a color mood space by using a color emotion metric. The output of the color theme is a modified version of the subject of the input images that is achieved by translating the weights from the color mood space into a semantic description of the subject.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 9: 4 Issues (2017): 2 Released, 2 Forthcoming
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing