• 디자인학연구
• /
• 제15권4호
• /
• pp.327-336
• /
• 2002

본 논문의 목적은 찬피부색을 지닌 사람들이 자신의 이미지를 긍정적인 이미지로 관리하고 자신감 있는 의복색을 선택하여 의상연출에 도움을 주고자 하였다. 찬피부색을 지닌 사람들이 의복색에 따라 어떠한 시각적 이미지 평가가 나타나는지를 준 실험 방법으로 분석한 결과는 다음과 같다. 1. Red계열의 의복색에서는 vivid 톤에서 긍정적인 이미지를, dull과 dark 톤에서 부정적인 이미지를 보여주었다. 2. Yellow계열의 의복색은 vivid, bright 톤에서 긍정적인 이미지를, dull, dark 톤에서 부정적인 이미지를, cool Yellow의 light 톤에서도 긍정적인 이미지 보여주는 것으로 나타났다. 3. warm Green의 의복색은 vivid, deep 톤에서, cool Green의 vivid 톤에서 긍정적인 이미지를 나타내었다. 4. warm Blue의 의복색은 vivid, deep 톤에서 긍정적인 이미지를, cool Blue의 vivid, bright 톤에서 긍정적인 이미지를 지니며, dull 톤에서 부정적인 이미지를 보여주는 것으로 나타났다. 5. Purple계열의 의복색은 vivid, deep, light 톤에서 긍정적인 이미지를, dull 톤에서 부정적인 이미지를 보여주는 것으로 나타났다.

• International journal of advanced smart convergence
• /
• 제11권2호
• /
• pp.13-21
• /
• 2022

In this paper, we propose a learning based joint demosaicing and super-resolution framework which uses only the mosaiced color filter array(CFA) image as the input. As the proposed method works only on the mosaicied CFA image itself, there is no need for a large dataset. Based on our framework, we proposed two different structures, where the first structure uses one deep image prior network, while the second uses two. Experimental results show that even though we use only the CFA image as the training image, the proposed method can result in better visual quality than other bilinear interpolation combined demosaicing methods, and therefore, opens up a new research area for joint demosaicing and super-resolution on raw images.

• 한국염색가공학회지
• /
• 제26권3호
• /
• pp.187-194
• /
• 2014

To improve the deep coloring effect of PET fabrics, the alkali treated and black dyed PET fabrics were treated with 2 kinds of low refractive compounds such as acrylic resin and silicone resin. The color depth effect of treated PET fabrics was evaluated as lightness(L) change by UV-visible spectrophotometer. As the weight loss of PET fiber treated with alkali increased, the color depth of PET fabrics increased. Lightness(L) of PET fabrics treated with deep coloring agent was lower than that of untreated PET fabrics. The optimum concentration of treated PET with deep coloring agent was 4% o.w.s. The deep coloring effect of PET fabrics treated with silicone resin was higher than one treated with acrylic resin. PET fabrics treated with silicone resin only might be more appropriate process than PET fabrics treated with acrylic and silicone resin for giving deep coloring effect for polyester fabrics.

• 복식
• /
• 제32권
• /
• pp.31-43
• /
• 1997

The costumes on a royal ceremony and the changes thereafter during the Korea Empire(1897-1910) have been elucidated through the review on the paintings on Queen Myong-Hun's 70th birthday celebration and the prospectus of the ceremony. Queen Myong-Hyn wore ceremonial gown in deep blue with 51 embroidered phoenix on it. The deep blue color the royal color in the Korea Empire replaced former red color. Go-jong wore violet crown and ceremonial suit in gold color. Twenty one kinds of court dance were offered during the celebration ceremony. Costumes therein appear to have an order according to the role ofdancers. most female dancers(in 17 performances not else-where specified) wore a rather common cos-tume-flower cap outer silk garent in green hand veils in 5 colors silk skirt in red) embroidered silk belt in red and shoes in green. In Sun-you-ak two female lead dancers were red hat decorated with tiger whisker deep blue outer garment wide red belt silk boots in black bow and arrows on back and a sword and a whip in hands. In Choonaang-jon a fe-male solo dancer wore a silk outer garment in yellow silk skirt in red green lorum embroidered silk belt in red wrist band of gold embroidered red silk and 5 color hand veils. In Yon-wha-dae two young girl dancers wore lotus-form crown green outer garment wide pants in red silk red silk skirt red silk belt hand veils in jade color and silk shoes in deep red. In Moo-go 4 female dancers each wore long waist coat in blue red white and warm light green in addition to the above-mentioned common costume. In Gumkee-moo 4 female dancers wore hatlike wool helmet outer garment with narrow sleeve long silk waist coat in blue combat belt in deep blue silk and dance swords in both hands. In Youk-wha-dae 6 female dancers each wore a long waist cost in red deep blue violet pale pink green and jade color. Green color of outer garment in the above-mentioned common costume of female dancers appears intersting. Although the color was shown as yellow in the screen paintings actually it was green as evidenced by the prospectus of the celeebration ceremony.

• 전기전자학회논문지
• /
• 제23권1호
• /
• pp.112-119
• /
• 2019

본 논문에서는 불꽃 감지를 위한 임베디드 시스템에 적합한 딥러닝 구조를 제안한다. 제안하는 딥러닝 구조의 불꽃 감지 과정은 불꽃 색깔 모델을 사용한 불꽃 영역 검출, 불꽃 색깔 특화 딥러닝 구조를 사용한 불꽃 영상 분류, 검출된 불꽃 영역의 $N{\times}N$ 셀 분리, 불꽃 모양 특화 딥러닝 구조를 사용한 불꽃 영상 분류 등의 4가지 과정으로 구성된다. 첫 번째로 입력 영상에서 불꽃의 색만을 추출한 다음 레이블링하여 불꽃 영역을 검출한다. 두 번째로 검출된 불꽃 영역을 불꽃 색깔에 특화 학습된 딥러닝 구조의 입력으로 넣고, 출력단의 불꽃 클래스 확률이 75% 이상에서만 불꽃 영상으로 분류한다. 세 번째로 앞 단에서 75% 미만 불꽃 영상으로 분류된 영상들의 검출된 불꽃 영역을 $N{\times}N$ 단위로 분할한다. 네 번째로 $N{\times}N$ 단위로 분할된 작은 셀들을 불꽃의 모양에 특화 학습된 딥러닝 구조의 입력으로 넣고, 각 셀의 불꽃 여부를 판단하여 50% 이상의 셀들이 불꽃 영상으로 분류될 경우에 불꽃 영상으로 분류한다. 제안된 딥러닝 구조의 성능을 평가하기 위하여 ImageNet의 불꽃 데이터베이스를 사용하여 실험하였다. 실험 결과, 제안하는 딥러닝 구조는 기존의 딥러닝 구조보다 평균 29.86% 낮은 리소스 점유율과 8초 빠른 불꽃 감지 시간을 나타내었다. 불꽃 검출률은 기존의 딥러닝 구조와 비교하여 평균 0.95% 낮은 결과를 나타내었으나, 이는 임베디드 시스템에 적용하기 위해 딥러닝 구조를 가볍게 구성한데서 나온 결과이다. 따라서 본 논문에서 제안하는 불꽃 감지를 위한 딥러닝 구조는 임베디드 시스템 적용에 적합함이 입증되었다.

• 한국염색가공학회지
• /
• 제21권1호
• /
• pp.10-20
• /
• 2009

The objective of this study is to investigate the efficacy of leaf powder colorants as substitutes for traditional fresh juice extract dyeing. Three kinds of leaf powder colorants were prepared by freeze drying method with or without deep freezing as pre-treatment: one powder colorant from fresh leaf juice with deep freezing; two kinds of powder colorant from fresh leaves with and without deep freezing. Their dyeing properties and storage stabilities were studied and compared with the traditional fresh juice extract dyeing. The presence of indigo in the powder colorants was confirmed by UV/Visible absorption spectra. They showed absorption peak at 602nm which was same with indigo absorption peak. Dyeing was done at low temperature around 6$^{\circ}C$. All three powder colorants produced B colors on silk fabrics, showing similar color to the one dyed traditionally with fresh juice extract. The powder colorants from leaves gave higher color strength than the powder from leaf juice. The powder colorant prepared from leaves with deep freezing was the most stable for long term storage as its color and color strength were not changed after 360 days. So, this was used for further dyeing to study the effects of concentration and repeat dyeing on color strength and colorfastness. Fastnesses to dry cleaning and rubbing were fairly good above 4 rating. Further study is needed to improve light fastness. It was concluded that the leaf powder colorant with deep freezing could be used as a substitute for traditional juice extract dyeing at all seasons.

• Journal of Multimedia Information System
• /
• 제8권3호
• /
• pp.175-182
• /
• 2021

Oral cancer is ranked second most diagnosed cancer among Indian population and ranked sixth all around the world. Oral cancer is one of the deadliest cancers with high mortality rate and very less 5-year survival rates even after treatment. It becomes necessary to detect oral malignancies as early as possible so that timely treatment may be given to patient and increase the survival chances. In recent years deep learning based frameworks have been proposed by many researchers that can detect malignancies from medical images. In this paper we have proposed a deep learning-based framework which detects oral cancer from histopathology images very efficiently. We have designed our model to split the color channels and extract deep features from these individual channels rather than single combined channel with the help of Efficient NET B3. These features from different channels are fused by using feature fusion module designed as a layer and placed before dense layers of Efficient NET. The experiments were performed on our own dataset collected from hospitals. We also performed experiments of BreakHis, and ICML datasets to evaluate our model. The results produced by our model are very good as compared to previously reported results.

• 천문학회보
• /
• 제44권1호
• /
• pp.75.1-75.1
• /
• 2019

The universe has been ionized in the post-reionization by several photon contributors. The dominant source to produce the hydrogen ionizing photons is not revealed so far. Faint quasars have been expected to generate UV photon budgets required to maintain ionization state of universe. Observational limits, however, hinder to discover them despite their higher number density than bright one. Consequently, the influence of faint quasars on post-reionization are not considered sufficiently. Therefore, a survey to find faint quasars at z ~ 5 is crucial to determine the main ionizing source in the post-reionization era. Deep images from the Hyper Suprime-Cam Subaru Strategic Program (HSC SSP) allow us to search for quasar swith low luminosities in the ELAIS-N1 field. J band information are obtained by the Infrared Medium-deep Survey (IMS) and the UKIRT Infrared Deep Sky Survey (UKIDSS) - Deep ExtragalacticSurvey (DXS). Faint quasar candidates were selected from several multi-band color cut criteria based on simulated quasars on color-color diagram. To choose the reliable candidates with possible Lyman break, we have performed medium-bands observations. Whether a candidate is a quasar or a dwarf star contamination was decided by results from chi-square minimization of quasar/dwarf model fitting. Spectroscopic follow-up observations confirm three quasars at z ~ 5. 100% spectral confirmation success rate implies that the medium-band observations effectively select faint quasars with strong Lyman alpha emission.

• 복식
• /
• 제57권9호
• /
• pp.88-96
• /
• 2007

The purpose of this study is to present examples for modern application with traditional color on ceremonial costume of Korean folk belief which is regarded as representative research material standing for Korean cultural archetype. The arrangements of color on the ceremonial costume of Korean folk belief were selected from 11 items specified as an import intangible cultural asset. These color arrangements were composed of fundamental colors from the viewpoint of modern color sensation, but had a excellent harmony in Hue. Therefore, not shifting Hue of color arrangement on ceremonial costume, traditional color arrangement was apply to contemporary it by shifting tone. Brilliant and deep chromatic tone that belong to 3, 4 area was converted into toned light grey, light clear, dark deep, toned dark grey, and greyish chromatic tone that belong to 1, 2 area or 5, 6, 0 area or 2, 7, 9 area. The plan that applies arrangement color with brightness contrast of traditional fundamental colors on a modern color harmony was presented from that. Like this, we can combine traditional color into modern color sensation, stylize and apply it on a production of character, logogram design, fashion design for characters in animation or game. From this, we'll be able to be close to the color arrangement sensation including our racial emotion in the everyday life.

• 산업경영시스템학회지
• /
• 제45권2호
• /
• pp.48-55
• /
• 2022

The color image of the brand comes first and is an important visual element that leads consumers to the consumption of the product. To express more effectively what the brand wants to convey through design, the printing market is striving to print accurate colors that match the intention. In 'offset printing' mainly used in printing, colors are often printed in CMYK (Cyan, Magenta, Yellow, Key) colors. However, it is possible to print more accurate colors by making ink of the desired color instead of dotting CMYK colors. The resulting ink is called 'spot color' ink. Spot color ink is manufactured by repeating the process of mixing the existing inks. In this repetition of trial and error, the manufacturing cost of ink increases, resulting in economic loss, and environmental pollution is caused by wasted inks. In this study, a deep learning algorithm to predict printed spot colors was designed to solve this problem. The algorithm uses a single DNN (Deep Neural Network) model to predict printed spot colors based on the information of the paper and the proportions of inks to mix. More than 8,000 spot color ink data were used for learning, and all color was quantified by dividing the visible light wavelength range into 31 sections and the reflectance for each section. The proposed algorithm predicted more than 80% of spot color inks as very similar colors. The average value of the calculated difference between the actual color and the predicted color through 'Delta E' provided by CIE is 5.29. It is known that when Delta E is less than 10, it is difficult to distinguish the difference in printed color with the naked eye. The algorithm of this study has a more accurate prediction ability than previous studies, and it can be added flexibly even when new inks are added. This can be usefully used in real industrial sites, and it will reduce the attempts of the operator by checking the color of ink in a virtual environment. This will reduce the manufacturing cost of spot color inks and lead to improved working conditions for workers. In addition, it is expected to contribute to solving the environmental pollution problem by reducing unnecessarily wasted ink.