• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.5
• /
• pp.1-9
• /
• 2010

Generally, dynamic hand gesture recognition is formed through preprocessing step, hand tracking step and hand shape detection step. In this paper, we present advanced dynamic hand gesture recognizing method that improves performance in preprocessing step and hand shape detection step. In preprocessing step, we remove noise fast by using dynamic table and detect skin color exactly on complex background for controling skin color range in skin color detection method using YCbCr color space. Especially, we increase recognizing speed in hand shape detection step through detecting Start Image and Stop Image, that are elements of dynamic hand gesture recognizing, using Guideline. Guideline is edge of input hand image and hand shape for comparing. We perform various experiments with nine web-cam video clips that are separated to complex background and simple background for dynamic hand gesture recognition method in the paper. The result of experiment shows similar recognition ratio but high recognition speed, low cpu usage, low memory usage than recognition method using learning exercise.

• The Research Journal of the Costume Culture
• /
• v.16 no.2
• /
• pp.293-304
• /
• 2008

The objectives of this study were to investigate the images in men's hairstyle by hair color, tone, texture, and perceiver's gender, and to examine the characteristics of hairstyle appropriate to seasons. A quasi-experimental method by questionnaire was used, and the experimental design was $4{\times}3{\times}2{\times}2$(hair color$\times$tone$\times$texture$\times$perceiver's$\times$gender) factorial design. The subjects were 372 men and women in their 20s through 50s. five factors of men's hairstyle image were derived by factor analysis: individuality, dignity, romanticism, refinement, and activity. Black hair was perceived to be high in dignity and activity. Bright tone was perceived to be high in individuality, but low in dignity. Men's wave hair was perceived to be higher in individuality than straight hair, but lower in dignity. Perceiver's gender did not give significant influence on evaluation of all image factors. In brown, neutral tone was perceived to be higher in dignity. romanticism, and activity than dark or bright tone. In black, wave hair was perceived to be more refined than straight hair. Black hair matches with winter the most, and yellow matches with spring the most. In terms of tone, dark tone matches with winter; neutral tone matches with autumn; bright tone matches with summer. The results of this study verified that hair color and texture affect men's image perception, and matching hair colors are associated with seasons.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.12
• /
• pp.65-73
• /
• 2013

As the advent of the digital age, documents are often scanned to be archived or to be transmitted over the network. The largest proportion of documents is texts and the next is seal images indicating the author of the documents. While a lot of research has been conducted to recognize texts in scanned documents and commercialized text recognizing products are developed as highlighted the importance of the scanned document, information about seal images is discarded. In this paper, we study how to extract the seal image area from the color or black and white document containing the seal image and how to save the seal image. We propose a preprocessing step to remove other components except for the candidate outlines of the seal imprint from scanned documents and a method to select the final region of interest from these candidates by using the feature of seal images. Also in case of a seal imprint overlapped with texts, the most similar image among those stored in the database is selected through the template matching process. We verify the implemented system for a various type of documents produced in schools and analyze the results.

• The Journal of the Korea Contents Association
• /
• v.18 no.2
• /
• pp.178-187
• /
• 2018

This study aimed to develop a model of the program for automation measuring the preference of the portraits based on the relationship between the image quality factors and the preferences in the portraits for manufacturers aiming at high utilization of the users. in order to proceed with the evaluation, the image quality measurement was divided into objective and subjective items, and the evaluation was done through image processing and statistical methods. the image quality measurement items can be divided into objective evaluation items and subjective evaluation items. RSC Contrast, Dynamic Range and Noise were selected for the objective evaluation items, and the numerical values were statistically analyzed and evaluated through the program. Exposure, Color Tone, composition of person, position of person, and out of focus were selected for subjective evaluation items and evaluated by image processing method. By applying objective and subjective assessment items, the results were very accurate, with the results obtained by the developed program and the results of the actual visual inspection. but since the currently developed program can be evalua ted only after facial recognition of the person, future research will need to develop a program that can evaluate all kinds of portraits.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.13-23
• /
• 2022

In this paper, we propose a detailed component image classification algorithm by fashion item for unstructured data retrieval in the fashion field. Due to the COVID-19 environment, AI-based online shopping malls are increasing recently. However, there is a limit to accurate unstructured data search with existing keyword search and personalized style recommendations based on user surfing behavior. In this study, pre-processing using Mask R-CNN was conducted using images crawled from online shopping sites and then classified components for each fashion item through CNN. We obtain the accuaracy for collar of the shirt's as 93.28%, the pattern of the shirt as 98.10%, the 3 classese fit of the jeans as 91.73%, And, we further obtained one for the 4 classes fit of jeans as 81.59% and the color of the jeans as 93.91%. At the results for the decorated items, we also obtained the accuract of the washing of the jeans as 91.20% and the demage of jeans accuaracy as 92.96%.

• Science of Emotion and Sensibility
• /
• v.16 no.3
• /
• pp.373-386
• /
• 2013

In this research, we specify the image consumers' preferred image quality ranges based on objective image quality evaluation factors and follow a method which measures preference of the natural image scenes. In other words, according to No-Reference, we select dynamic range, color, and contrast as factors of image quality measurements. For collecting sample images, we choose the preferred 200 landscapes which have over 30 recommendations by image consumers on the internet photo gallery. According to the scores of three objective factors of image quality measurements, the final expected score which means the image quality preference is measured and its total score is 100 points. In the main test, the actual image sample shows dynamic range 10 stop, LAB mean value L:54.7, A:2.96, B:-15.84, and RSC contrast 376.9. Total 200 image samples' normal distribution z value represents in dynamic range 0.21, LAB mean value L:0.15, A:0.38, B:0.13, and RSC contrast 0.08. In the standard normal distribution table, we can convert the z value as a percentage; dynamic range is 8.32%, LAB mean value is L:5.96%, A:14.8%, B:5.17%, and RSC contrast is 3.19%. And then, we convert the percentage values into the scores of 100; dynamic range is 91.68, LAB mean value is 91.36, and RSC contrast is 96.81. Therefore, we can conclude that the sample image's total mean score is 94.99 based on three objective image quality factors. Throughout our proposed image quality assessment model, we can measure the preference value of natural scenes. Also, we can specify the preferred image quality representation ranges and measure the expected image quality preference.

• 한국벤처창업학회:학술대회논문집
• /
• 2017.04a
• /
• pp.45-45
• /
• 2017

본 연구에서는 고압산소치료 후 포유동물의 피부에서 Melanin 세포의 생성이 줄어들었음을 이미 보고된 바 있고, 치료 후 전층 피부이식 생존율을 높였고, 또한 인체의 피부 진피층 확인은 더 많은 임상데이터가 필요하나 고압산소치료 후 표피면의 변화는 빠른 시간에 확인 할 수 있다고 판단됨으로 이에 피부진단기의 기준면과의 평행(parallel polarization) 이미지로 피부표피의 변화를 확인 하고자 했다. 본 연구의 고압산소챔버를 활용한 피부표피에 대한 분석 및 실험 결과, 주름살 및 상처(Wrinkle & Scar) 분석에서 피실험자 남자1 3%, 남자2 2%, 여자1 5.9%, 여자2 2.3%로 피실험자 모두 감소 현상을 보여 피부 탄력도가 좋아 지는 효과를 보였다. 피부미백(S-Gray) 분석에서는 피실험자의 피부 표피면의 멜라닌 및 에리즈마 색소의 피부 톤이 남자1 1.1%, 남자2 2.3%, 여자1 4% 로 피실험자 4명 중 3명은 상승 효과를 얻었으나, 피실험자 다른 1명인 여자2는 2.3% 하향의 결과가 나타났다. 홍도(Erythema) 분석, 피실험자 정상인 부위인 D.BLUE/BLUE 값이 남자1 5.6%, 남자2 4.9%, 여자1 17.3%, 여자2 15.3% 증가 현상을 보였으며 남자와 여자의 효과 차이가 10% 이상으로 나타낸 것으로 보아 남자 보다는 여자가 우세한 것으로 판단되었으며, 비정상인 에리즈마 색소(민감도)의 비정상인 부위인 YELLOW/RED 컬러 값에서 남자1 5.2%, 남자2 5%, 여자1 9.2%, 여자2 4.5% 감소 하였음을 보였다. 이에 피실험자 모두 에리즈마인 민감성 산소치료에 따른 피부에 미치는 영향이 효과가 있는 것으로 판명되었다.

• Journal of Fashion Business
• /
• v.7 no.1
• /
• pp.72-83
• /
• 2003

The purpose of this study is to understand the history of 20th century fashion and make-up culture, analyze trend of the modern fashion and make-up, creat a cyber make-up model according to themes and also it will find out how to use make-up as a part of fashion genre. As a result of this study is 1. Looking over change-process in 20th century fashion and make-up history, we can find the popular make-up color and pattern reflecting the society and cultural environments. And also make-up culture reflecting their sense of values and way of thinkings. 2. Analyzing fashion and make up color trend of 2002 F/W, we can find a similarity between fashion and make-up color trend by comparing with hue&tone chart. All of theme have a tendency to be natural, veiled, feminine by neutral color and artifical highlighted, illuminate, transparant by clear-high saturation color. 3. Creating imagemaps, color palletes and cyber model of 4 trend themes by computer graphic, It can give more visual and interesting effect on the cyber space, and also it can help to expect make-up will be dizitalized, visualized and informationalized.

• Korean Journal of Human Ecology
• /
• v.16 no.2
• /
• pp.381-393
• /
• 2007

This study was intended to analyze and investigate a diversity of aesthetic values expressed in the military look of the Milan collections by using content analysis method to find what design characteristic and image emerged concretely in the later 20th century. A total of 334 military look works shown in fashion magazines such as Vogue and Collezioni Donna over the period between 1996 and 2000 were collected as research data, which were classified into 5 categories such as item, silhouette, color, color coordination, fashion image. The results were summarized as follows: first, it was found that coat was the most preferred item in expressing the military look image. Second, it was found that the straight line was the most preferred silhouette, which indicates that it was the most suitable silhouette in expressing the bisexual image of the military look. Third, in the colors of the military look, achromatic colors such as black and white were found to be of the highest frequency, which shows that achromatic colors continued to be proposed as fashionable colors around 1996 and this influence was reflected in the military look. Finally, in terms of the item of color coordination, monochromatic coordination accounted for more than half of the military look, through which it could be explained that designers utilized it greatly to make an effective expression of the masculine image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.11
• /
• pp.2555-2562
• /
• 2010

In this paper, we propose the method that extracts sea level measurements graph from the sea level measurements recording paper image with a little interaction. At first, a pixel that is included in the graph area is selected. Then, background pixels are automatically determined using the distance between a selected pixel and other pixels on LAB color space. In each vertical line, a pixel that is the nearest to the selected pixel on LAB color space is extracted and the graph area is determined using that pixels. Experimental results show that the sea level measurements graph can be extracted with a few interaction from the various sea level measurements recording paper images.