• 한국의상디자인학회지
• /
• 제9권2호
• /
• pp.127-138
• /
• 2007

The purpose of this study was to investigate the male perceiver's image evaluation on women's hairstyle and hair color, and to disclose the preference of the hairstyle and hair color. The experimental design was $2{\times}3{\times}3$ (hair $wave{\times}hair\;length{\times}hair$ color) factorial design by 3 independent variables. The stimuli were 18 women's upper body photographs which were output by computer simulation. The hairstyles were straight hair and wavy hair, and the types of the hair length were long, medium, and short hair. The hair colors were black, dark brown, and bright brown. Subjects were 154 men living in Seoul. The data were analyzed by using factor analysis, Cronbach's ${\alpha}$ reliability coefficient, three-way ANOVA, one-way ANOVA, and Duncan's multiple range test. The results of this study were as follows. Four image dimensions were derived by factor analysis. These were individuality, elegance, potency, and attractiveness. Male perceivers evaluated the women's long hairstyles to be more elegant than the short and the medium length hairs. The women's short hairstyles were perceived more potent than the long and the medium length hairs. The straight hairs were evaluated more elegant than the permed hairs, and the permed hairs were evaluated higher in individuality and attractiveness. The black hairs were perceived lowest in attractiveness, and the bright colors were perceived low in elegance. Male preferred the long brown straight hair first. They liked women's long hairs better than the short and the medium length hairs. Teenaged males preferred various hair colors more than those in their 20's and 30's did.

• 제어로봇시스템학회논문지
• /
• 제21권3호
• /
• pp.276-282
• /
• 2015

This paper proposes a SMD (surface mounting device) classification method for the PCB assembly inspection machines. The package types of SMD components should be classified to create the job program of the inspection machine. In order to reduce the creation time of job program, we developed the automatic classification algorithm for the SMD packages. We identified the chip-type packages by color and edge distribution of the images. The input images are transformed into the HSI color model, and the binarized histroms are extracted for H and S spaces. Also the edges are extracted from the binarized image, and quantized histograms are obtained for horizontal and vertical direction. The neural network is then applied to classify the package types from the histogram inputs. The experimental results are presented to verify the usefulness of the proposed method.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1998년도 Proceedings of International Workshop on Advanced Image Technology
• /
• pp.165-170
• /
• 1998

This paper presents a new prediction method RBP region-based prediction model where the context used for prediction contains regions instead of individual pixels. There is a meaningful property that RBP can partition a cartoon image into two distinctive types of regions, one containing full-color backgrounds and the other containing boundaries, edges and home-chromatic areas. With the development of computer techniques, synthetic images created with CG (computer graphics) becomes attactive. Like the demand on data compression, it is imperative to efficiently compress synthetic images such as cartoon animation generated with CG for storage of finite capacity and transmission of narrow bandwidth. This paper a lossy compression method to full-color regions and a lossless compression method to homo-chromatic and boundaries regions. Two criteria for partitioning are described, constant criterion and variable criterion. The latter criterion, in form of a linear function, gives the different threshold for classification in terms of contents of the image of interest. We carry out experiments by applying our method to a sequence of cartoon animation. We carry out experiments by applying our method to a sequence of cartoon animation. Compared with the available image compression standard MPEG-1, our method gives the superior results in both compression ratio and complexity.

• 대한간호학회지
• /
• 제23권4호
• /
• pp.631-648
• /
• 1993

This study is a descriptive study to provide basic data related to types of uniforms worn by nurses. Nurses, other medical center personnel, patients and their famillies were asked for their opinion on changing nurses’ uniforms and how the image of nurses is 1 elated to the type of uniform worn by the nurses. The data for this study were collected during the period from Feb. 25, 1993 to Mar. 26, 1993 at Y-University Medical Center from 132 nurses, 137 other medical center personnel, 117 patients and their families. The instruments used for this study were the Nurses’ Image Scale(NIS) developed by Bown(1986), and an instrument to measure opinions of uniform and cap using photographs of nurses’ uniforms that was developed by the researcher through a literture review. Data were analyzed using the SPPS / PC package, Statistics used for analysis were frequencies, percentages, paired t -test, and oneway ANOVA The results of this study are summarized as follows ; 1. Of the nurses, 84.3%, along with, 51.5% of the medical center personnel, 39.1% of the patients and their families agreed to a change in the color of nurses uniforms. 2. Similarly, 87.4% of the nurses,27.7% of the medical center personnel, 19.3% of the patients and their families were in favor of nurses not wearing caps. 3. Only 11.8% of nurses answered that a white uniform was important to the professional image of nursing. Only 2.4% of the nurses answered that a cap was very important to the professional image of nursing. 4. Only 1.6% of the nurses answered that a white uniform and cap were important to show the role of nurses in the twenty first century. 5. About 1/3, 36.5%, of the medical center personnel, the patient and their families answered that changing the color of the nurses' uniform will make a change in the image of nurses. 6. A White uniform and cap were seen as being im-portant in distinguishing nurses from other medical personnel in the hospital by 76.5% of the medical personnel, the patients and their families. 7. Nurses gave high marks to the idea of no cap regardless of the color of the uniform which would still portray the symbol of the nurses’ role, identity and would differentiate the role from other jobs. The patients and their families gave high marks to a white uniform with cap. 8. Generally, nurses, medical center personnel and patients and their families thought that a colored uniform with cap presented a good image of nurses. 9. There was a significant difference in the response among the three groups(F=24.65, P〈.001) to the figure in a white uniform with a cap, and the patients and their families thought it was the best portrayal of the image of nurses. There was a significant difference among the three groups(F=9.03, P〈.001) to the figure in a white uniform with no cap and the nurses indicated that it was the beat portrayed of the image of nurses. There was no significant difference among the three groups to the figure in a colored uniform with cap. There was a significant difference(F=17.50, P〈. 001) to the figure in a colored uniform with no cap, and the nurses indicated that it was the best portrayal of the image of nurses. In summary, the nurses wanted to change the color of uniform and not to wear a cap. But many of the medical center personnel, patients and their families indicated they did not agree with this idea. Therefore, changing the type of uniform worn by nurses should be done only after consideration has been given to the relation of the change to the professional role of nurses and the image of nurses held people in general. Suggestions arising from this study are as follows : 1. The relation between the role of nurses and their uniform was surveyed, and these results can be used as data when considering a change in uniforms. 2. A change in uniforms should be tried based on the norm established about uniforms. 3. The nurses did not want to wear a cap, but before a decision is definitely made it is necessary to study the philosophy related to the symbol of the cap because the figure of a nurse with a cap portrayed a positive image of the nurses. If the cap is kept, the symbol of the cap should be redefined. 4. In this study, only the image related to the uniform was examined, but in future studies it will be necessary to examine the practicality of various types of uniforms.

• 한국전자통신학회논문지
• /
• 제5권2호
• /
• pp.152-157
• /
• 2010

컴퓨터와 인터넷의 발달로 정보의 형태가 다양화 되어 문서 위주의 자료들로부터 이미지, 오디오, 비디오, 음성 등의 모습으로 혼합되어 가고 있다. 하지만 대부분의 검색은 문서 위주로 하기 때문에 이미지, 오디오, 비디오 등은 파일의 이름이 명확하게 설정되어 있지 않을 경우에는 검색을 할 수 없다. 이러한 문제점을 해결하기 위해 문서가 아닌 내용을 기반으로 검색하는 방법을 내용 기반 검색이라고 한다. 그리고 이미지의 내용을 기반으로 검색하는 방법을 내용 기반 이미지 검색이라고 한다. 본 논문에서는 HSI 컬러 공간, ART2 알고리즘, SOM 알고리즘을 이용한 내용 기반 이미지 검색 방법을 제안한다. 제안하는 방법은 학습 대상을 선정하기 위해 원 영상의 특징을 분할한다. 그리고 사용자가 학습 대상을 선정하도록 하기 위해 분할된 특징을 SOM 알고리즘에 적용하여 비슷한 특징을 가지는 영상들로 군집화 한다. 군집화된 영상들에 대해 사용자가 학습 대상을 선정하여 ART2 알고리즘에 적용하여 학습한다. 제안한 방법을 적용하여 이미지 검색을 실험한 결과 제안된 방법은 하나의 이미지가 여러 개의 키워드를 가질 수 있기 때문에 이미지에 포함된 정보를 효과적으로 검색하는 것을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제18권5호
• /
• pp.610-619
• /
• 2015

*In this paper, we propose a real-time face tracking system using an adaptive face detector and a tracking algorithm. An image is divided into the regions of background and face candidate by a real-time updated skin color identifying system in order to accurately detect facial features. The facial characteristics are extracted using the five types of simple Haar-like features. The extracted features are reinterpreted by Principal Component Analysis (PCA), and the interpreted principal components are processed by Support Vector Machine (SVM) that classifies into facial and non-facial areas. The movement of the face is traced by Kalman filter and Mean shift, which use the static information of the detected faces and the differences between previous and current frames. The proposed system identifies the initial skin color and updates it through a real-time color detecting system. A similar background color can be removed by updating the skin color. Also, the performance increases up to 20% when the background color is reduced in comparison to extracting features from the entire region. The increased detection rate and speed are acquired by the usage of Kalman filter and Mean shift.

• 패션비즈니스
• /
• 제10권4호
• /
• pp.16-28
• /
• 2006

The purpose of this study is to investigate the content and changes of modern Korean men's wear advertisement from the 1960s to the 1990s by reviewing fashion magazines and pictorials. Research problems were as follows.; First, analyze the types and their units of measurement in men's fashion advertisements from 1962 to 1998. Second, examine the differences of quantitative change in men's fashion advertisements according to each period. The total 857 advertisements were selected from Shin Dong-A, Joongang Magazine, and Bokjangwolbo from 1972 to 1998. For analyze the result, frequency analysis and $x^2$-test were used. Results were as follows. First, through the review of literatures and pre-tests, 6 units of measurement were identified. They were product type(formal wear, casual wear, sports wear, dress shirts, accessory, inner wear, fabric and the others), brand type(national brand, licensed brand, imported brand, others), appeal type(image, product, others), representation type(photograph, illustration, others), medium type(man, product, others), and color type of advertisement(black & white picture, color picture). Second, for the types of advertisements, formal wear, national brand, image appeal, figure medium, photograph for presentation and color picture are the most frequently shown in men's fashion advertisements from 1962 to 1998. Third, for product, more accessory advertisements were found than the clothing in the 60s and the 70s, and casual wear advertisements in the 80s and formal wear advertisements in the 90s were dominated. National brand type was dominant through all four period. Product appeal type in the 60s and the 70s and image appeal type in the 80s and the 90s were prevailed. For medium, product type in the 60s and the 70s and figure type in the 80s and the 90s were dominated. Black & white picture in the 60s and the 70s and color picture in the 80s and the 90s were prevailed. Lastly, photograph was the most frequently used for presentation type through all periods.

• 대한산업공학회지
• /
• 제40권4호
• /
• pp.382-387
• /
• 2014

Image retrieval is a procedure to find images based on the resemblance between query image and all images. In retrieving images, the crucial step that arises is how to define the similarity between images. In this paper, we propose a new similarity measure which is based on distribution of color. We apply the new measure to retrieving two different types of images, wallpaper images and the logo of automobiles, and compare its performance to other existing similarity measures.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2000년도 춘계 학술대회 및 국제 감성공학 심포지움 논문집 Proceeding of the 2000 Spring Conference of KOSES and International Sensibility Ergonomics Symposium
• /
• pp.149-156
• /
• 2000

The aim of this study is to propose the predictive index and analyze the effect of lightsources and colour image types in the residence and office interior.This study was consisted of four steps, and was carried out as follows. 1) The condition of experiment was set up by optical characteristic of lightsources and colours. 2) The scaled model space was manufactured for the evaluation of the same condition by each space. And, some piece of furniture was manufactured for the representation of each space. 3) The emotivity response of lightsources and colours was measured. 4) Results of the evaluation of lightsources and colours were compared and analyzed by conditions, and the predictive index was proposed by image types.

• 한국IT서비스학회지
• /
• 제6권3호
• /
• pp.241-249
• /
• 2007

This paper describes a real-time face tracking system using effective detector and Kalman filter. In the proposed system, an image is separated into a background and an object using a real-time updated face color for effective face detection. The face features are extracted using the five types of simple Haar-like features. The extracted features are reinterpreted using Principal Component Analysis (PCA), and interpreted principal components are used for Support Vector Machine (SVM) that classifies the faces and non-faces. The moving face is traced with Kalman filter, which uses the static information of the detected faces and the dynamic information of changes between previous and current frames. The proposed system sets up an initial skin color and updates a region of a skin color through a moving skin color in a real time. It is possible to remove a background which has a similar color with a skin through updating a skin color in a real time. Also, as reducing a potential-face region using a skin color, the performance is increased up to 50% when comparing to the case of extracting features from a whole region.