• Title/Summary/Keyword: 염색색상 예측

Search Result 4, Processing Time 0.016 seconds

Development of a model for predicting dyeing color results of polyester fibers based on deep learning (딥러닝 기반 폴리에스터 섬유의 염색색상 결과예측 모형 개발)

  • Lee, Woo Chang;Son, Hyunsik;Lee, Choong Kwon
    • Smart Media Journal
    • /
    • v.11 no.3
    • /
    • pp.74-89
    • /
    • 2022
  • Due to the unique recipes and processes of each company, not only differences among the results of dyeing textile materials exist but they are also difficult to predict. This study attempted to develop a color prediction model based on deep learning to optimize color realization in the dyeing process. For this purpose, deep learning-based models such as multilayer perceptron, CNN and LSTM models were selected. Three forecasting models were trained by collecting a total of 376 data sets. The three predictive models were compared and analyzed using the cross-validation method. The mean of the CMC (2:1) color difference for the prediction results of the LSTM model was found to be the best.

Binary and Ternary Competitive Adsorption of Basic Dyes from Aqueous Solution onto the Conchiolin Layer (수용액에서의 이성분 및 삼성분 염기성 염료의 진주층에 대한 경쟁흡착)

  • Shin, Choon-Hwan;Song, Dong-Ik
    • Journal of Korean Society of Environmental Engineers
    • /
    • v.28 no.3
    • /
    • pp.270-275
    • /
    • 2006
  • The cultivated pearls collected for the study were pretreated through the removal of contaminants and the surface bleaching for easy dyeing. Coloring of pearls are necessary after selecting dyes adsorbable to the Conchiolin layer, a kind of hard protein formed in the seawater, covering the surface of the pretreated pearls. Dyes adsorbable to the Conchiolin layers are mostly basic dyes such as Rhodamine 6G(R6G), Rhodamine B(RB), Methylene Blue(MB) etc. and the binary and ternary competitive adsorption were performed by mixing two or three dyes together. The multi-dye adsorption data were compared with the predictions from the ideal adsorbed solution theory(IASI) combined with the single-dye adsorption model, the Langmuir or the Redlich-Peterson(RP) model. The quality of prediction was compared by using determination coefficient($R^2$) and standard deviation(SSE) values. Predictions from the IAST were found to be in good agreement with the data for the R6G/RB binary adsorption to the pearl layers not fractionated with their size, except for the adsorption data for RB at high concentrations. Among the three binary adsorption systems, R6G/RB, R6G/MB, and MB/RB, only the RB sorption data in the R6G/RB binary system was in poor agreement with the IAST prediction. Competitive adsorption data in ternay systems were in good agreement with the predictions from the IAST except for the RB data.

Colorimetric Properties and Color Sensibility Factors for Naturally Dyed Fabrics by Microbial Prodiginine Colorant (미생물 유래 Prodiginine 색소로 천연염색한 직물의 색채특성 및 색채감성요인)

  • Choi, Jong--Myoung;Kim, Yong-Sook;Yi, Eun-Jou
    • Science of Emotion and Sensibility
    • /
    • v.13 no.4
    • /
    • pp.693-702
    • /
    • 2010
  • This study was carried out in order to investigate the colorimetric values, the color sensation and sensibility for naturally dyed fabrics with microbial prodiginine colorant and to find out the relationship among color sensation, color sensibility factors and colorimetric properties of them. Color sensation and sensibility of four different fabric stimuli coloring red purple by a microbial prodiginine colorant produced from Zooshikella sp. were subjectively evaluated by university students. The color sensibility for the naturally dyed fabrics was classified into four factors: 'pleasantness', 'gracefulness', 'characteristic' and 'relax'. Color sensibility factor 'pleasantness' was the dominant factor for the naturally dyed fabrics with microbial prodiginine colorant. All color sensibility factors showed a significant correlations with the color sensation and colorimetric properties of the dyed fabrics with prodiginine. There were showed significant relationships between the color sensibility factors and lightness $L^{\ast}$, color saturation $C^{\ast}$, $a^{\ast}$ and $b^{\ast}$. Also, color preference of the dyed fabrics with prodiginine was found to be influenced mainly by color sensibility factors.

  • PDF

Leukocyte Segmentation using Saliency Map and Stepwise Region-merging (중요도 맵과 단계적 영역병합을 이용한 백혈구 분할)

  • Gim, Ja-Won;Ko, Byoung-Chul;Nam, Jae-Yeal
    • The KIPS Transactions:PartB
    • /
    • v.17B no.3
    • /
    • pp.239-248
    • /
    • 2010
  • Leukocyte in blood smear image provides significant information to doctors for diagnosis of patient health status. Therefore, it is necessary step to separate leukocyte from blood smear image among various blood cells for early disease prediction. In this paper, we present a saliency map and stepwise region merging based leukocyte segmentation method. Since leukocyte region has salient color and texture, we create a saliency map using these feature map. Saliency map is used for sub-image separation. Then, clustering is performed on each sub-image using mean-shift. After mean-shift is applied, stepwise region-merging is applied to particle clusters to obtain final leukocyte nucleus. The experimental results show that our system can indeed improve segmentation performance compared to previous researches with average accuracy rate of 71%.