• 스마트미디어저널
• /
• 제11권3호
• /
• pp.74-89
• /
• 2022

섬유 소재의 염색은 기업별로 고유의 레시피와 공정으로 인하여 결과물 간의 차이가 존재할 뿐만 아니라 예측하기도 어려운 실정이다. 본 연구는 염색 공정에서의 색상구현 최적화를 위해 딥러닝 기반의 예측 모형을 개발하고자 시도되었다. 이를 위하여 딥러닝 기반 모형인 다층퍼셉트론, CNN 그리고 LSTM 모형을 선정하였다. 총 376건의 데이터 세트를 수집하여 3개의 예측 모형을 학습시켰다. 교차검증 방법을 이용하여 3개의 예측 모형에 대해 비교 및 분석하였다. LSTM 모형의 예측 결과에 대한 CMC(2:1) 색차의 평균이 가장 우수한 것으로 나타났다.

• 한국의류학회지
• /
• 제46권1호
• /
• pp.33-48
• /
• 2022

This study was performed to compare the color emotion and preference of Koreans and Chinese for a two-color combination by dyeing cotton fabric with persimmon and indigo and to establish prediction models of color preference. Nine specimens prepared by combining two different colored fabrics (persimmon and indigo) were evaluated for color emotion and preference by Korean and Chinese groups of female college students. Koreans described most specimens as natural and traditional, whereas the Chinese described them as more pleasant and elegant as well as warmer and lighter than Koreans did. The contrast tone was the most preferred combination by both groups, whereas it was perceived as more modern and less warm by Koreans. Relationships between physical color variables and color emotions were quantified; these relationships were applied to establish a prediction model of color preference with tone combination types for each group. These results could help in making the design of fashion textiles more preference- and emotion-oriented for Korean and Chinese consumers.

• Fibers and Polymers
• /
• 제7권4호
• /
• pp.344-351
• /
• 2006

This paper is intended to determine the optimal processing parameters applied to the dyeing procedure so that the desired color strength of a raw fabric can be achieved. Moreover, the processing parameters are also used for constructing a system to predict the fabric quality. The fabric selected is the nylon and Lycra blend. The dyestuff used for dyeing is acid dyestuff and the dyeing method is one-bath-two-section. The Taguchi quality method is applied for parameter design. The analysis of variance (ANOVA) is applied to arrange the optimal condition, significant factors and the percentage contributions. In the experiment, according to the target value, a confirmation experiment is conducted to evaluate the reliability. Furthermore, the genetic algorithm (GA) is combined with the back propagation neural network (BPNN) in order to establish the forecasting system for searching the best connecting weights of BPNN. It can be shown that this combination not only enhances the efficiency of the learning algorithm, but also decreases the dependency of the initial condition during the network training. Most of all, the robustness of the learning algorithm will be increased and the quality characteristic of fabric will be precisely predicted.

• 한국의류학회지
• /
• 제36권10호
• /
• pp.1028-1039
• /
• 2012

This study identified color emotion factors of naturally dyed two-color combination fabrics focused on yellowish and reddish shades to examine the relationship between color emotion factors and physical colorimetric variables (as well as tone combination groups) to provide prediction models for color emotion factors of naturally dyed fabrics with a two-color combination. Each of eight different stimuli were prepared by paring two pieces of silk fabrics colored in red and yellow by natural dyeing respectively; in addition, their color emotion descriptors were evaluated by human subjects using semantic deferential scales. 'Joyful', 'Natural', 'Classical', and 'Soft' were extracted as color emotion factors for the naturally dyed yellowish-reddish combination fabrics. They were found to be significantly affected by physical colorimetric variables such as CIE $C^*$ and $L^*$ and tone combination groups. Finally, prediction models for all color emotion factors were established using physical colorimetric variables and tone combination groups that led to the conclusion that they could be applicable to design a color combination for naturally dyed fashion fabrics.

• 한국의류학회지
• /
• 제45권1호
• /
• pp.180-199
• /
• 2021

This study investigated natural aroma fragrance on the fashion image of Galchon, a traditional natural dyeing textile made with immature persimmon from the Jeju area, Korea. Nine fabric pairs consisting of differently colored cotton and silk Galchon with various tones and fabric types were used for subjective evaluation. Thirty five female college students evaluated the specimens using a 7-point scale questionnaire for fashion image-related adjectives. A specimen with three different presentation types that included fabric without fragrance (FO), fabric with citrus fragrance, and fabric with chamaecyparis (FCP) were randomly provided to a subject. As a result, color variables of Galchon were found to be the primary influence on fashion images for both cotton and silk Galchon that showed interaction effects with presentation types. The citrus fragrance increased the feeling of 'Active' while chamaecyparis tended to contribute to a stronger perception of 'Elegance' for cotton Galchon. Finally, these results were used to develop prediction models for fashion images of Galchon that employed color variables and presentation types.

• 감성과학
• /
• 제19권3호
• /
• pp.3-14
• /
• 2016

본 연구에서는 천연염료와 직물종류, 매염유무의 세 가지 조건에 대한 천연염색직물의 물리적 색채 특성을 측정하고, 심리적 색채감성평가를 실시하였다. 이에 대하여 염료의 종류, 직물의 종류, 매염제의 유무에 따른 물리적 색채 특성 차이를 살펴보기 위하여 분산분석을 실시하였으며, 상관관계분석을 통해 물리적 색채 특성과 심리적 감성간의 관계를 분석하고, 회귀분석을 이용해 천연염색에 대한 예측식을 도출하였다. 최종적으로, 천연염색직물에 대한 감성 이미지 맵을 제안하기 위하여 다차원 척도법(Multidimensional Scaling: MDS)을 이용하였다. 이를 통해, 대표적으로 남성적인(masculine)인 이미지에는 무거운, 딱딱한 색채감성을 갖는 치자염색이, 여성스러운(feminine) 이미지에는 밝고 투명하고 부드러우면서 가벼운 색채감성을 갖는 소목과 락, 치자청을 사용한 염색이 적합하다. 내츄럴(natural)한 이미지를 나타내기 위해서는 은은한 색채감성의 쑥 염색이 적절하고, 화려한 색채감성의 쪽으로 염색을 한다면 액티브(active)한 이미지를 가질 수 있을 것이라 예측 가능하다.