• 정보처리학회논문지B
• /
• 제13B권6호
• /
• pp.591-600
• /
• 2006

본 논문에서는 문서 영상의 그림 영역에서 통계적 분석을 통한 단어 영상을 추출하는 방법을 제안한다. 제안 방법은 그림 영역의 구성 요소를 문자 성분과 그래픽 성분으로 분류하기 위하여 연결요소에 대한여 통계적 분석 방법인 상자그림 분석을 적용하고, 분류된 문자 성분들에 대하여 지역적 밀집도를 분석하여 문자 영역을 추출한다. 추출된 문자 영역에서 투영 히스토그램 분석을 통하여 문자열을 추출하고, 문자열을 단어단위 영상으로 분리하기 위하여 투영 히스토그램 분석과 갭 군집화, 특수 기호 검출 등을 수행한다. 제안 방법은 임계값의 사용 대신에 그림 영역의 구성 요소들에 대하여 통계적 분석을 수행하기 때문에 그림의 형태 변화에 민감하지 않으며, 지역적 밀집도 분석으로 보다 정확한 문자 영역을 추출하였다. 또한 제안 방법의 응용 분야인 주제어 검색을 위한 오프라인의 전처리에 해당하는 문서 영상의 단어단위 영상 추출에 적용하여 제안 방법에 대한 연구의 필요성을 제시하였다.

• 전자공학회논문지B
• /
• 제33B권12호
• /
• pp.71-83
• /
• 1996

This paper describes facial component detection and skew correction algorithm for face recognition. We use a priori knowledge and models about isolated regions to detect eye location from the face image captured in natural office environments. The relations between human face components are represented by several rules. We adopt an edge detection algorithm using sobel mask and 8-connected labelling algorith using array pointers. A labeled image has many isolated components. initially, the eye size rules are used. Eye size rules are not affected much by irregular input image conditions. Eye size rules size, and limited in the ratio between gorizontal and vertical sizes. By the eye size rule, 2 ~ 16 candidate eye components can be detected. Next, candidate eye parirs are verified by the information of location and shape, and one eye pair location is decided using face models about eye and eyebrow. Once we extract eye regions, we connect the center points of the two eyes and calculate the angle between them. Then we rotate the face to compensate for the angle so that the two eyes on a horizontal line. We tested 120 input images form 40 people, and achieved 91.7% success rate using eye size rules and face model. The main reasons of the 8.3% failure are due to components adjacent to eyes such as eyebrows. To detect facial components from the failed images, we are developing a mouth region processing module.

• 한국항행학회논문지
• /
• 제20권6호
• /
• pp.625-630
• /
• 2016

최근 다양한 형태의 영상 콘텐츠가 제작되고 있고, 이를 위한 저작권 보호기술에 대한 관심이 높아지고 있다. 본 논문에서는 컬러 영상을 위한 영상암호화 기술을 제안한다. 이 기술은 영상을 RGB 색차성분으로 분할한 후, 윤곽선을 기준으로 쿼드트리 분할을 수행한다. 쿼드트리 분할 후, 선정된 블록들을 대상으로 암호화를 수행한다. 색차성분을 대상으로 암호화를 수행하여 암호화 효율을 측정하고, 컬러 영상으로 재구성한 후에도 암호화 효율을 측정한다. 암호화 효율은 시각적인 측정방식과 객관적인 화질평가 방식을 이용한다. 실험결과 PSNR 수치는 색차성분의 경우 7~10[dB], 컬러 영상의 경우 16~19[dB]로 측정되었다. 본 논문에서 제안한 영상암호화 기술은 향후 다양한 디지털 영상 콘텐츠의 저작권 보호에 사용될 것으로 보인다.

• 패션비즈니스
• /
• 제12권1호
• /
• pp.129-146
• /
• 2008

The purpose of this study is to identify components of CEO image and to examine predictors to affect company's market value. To explore the social construction of the CEO Image depicted in the popular business newspaper, the Wall Street Journal and daily newspaper of Korea, was analyzed. Then, the reconstructed image of the CEO was compared with the firm's stock price change to see their relationship, if any. This paper focused on the case of Carly Fiorina as previous chief of Hewlett-Packard, who was the Fortune's ranking of the 50 most powerful women in business is presented. The period for the analysis was five years and eight months from her inauguration(July, 1999) to the release(February, 2005). The results, four predictors such as nature, management ability, leadership style, appearance character had statistically significant relationship with both company's market value and the image of CEO. In addition to revealed that media coverage of Carly Filoina was commensurate with the financial performance, particularly stock price change of the Hewlett-Packard. In general, the best image of the CEO is highly transcends to the image of the company as well. Therefore it is need to manage effectively components of CEO image to enhance brand image and its brand value, which are further expected to enhance company's market value.

• 반도체디스플레이기술학회지
• /
• 제10권1호
• /
• pp.113-118
• /
• 2011

This paper proposes computer visual inspection algorithms for PCB defects which are found in a manufacturing process. The proposed method can detect open circuit and short circuit on bare PCB without using any reference images. It performs adaptive threshold processing for the ROI (Region of Interest) of a target image, median filtering to remove noises, and then analyzes connected components of the binary image. In this paper, the connected components of circuit pattern are defined as 6 types. The proposed method classifies the connected components of the target image into 6 types, and determines an unclassified component as a defect of the circuit. The analysis of the original target image detects open circuits, while the analysis of the complement image finds short circuits. The machine vision inspection system is implemented using C language in an embedded Linux system for a high-speed real-time image processing. Experiment results show that the proposed algorithms are quite successful.

• 제어로봇시스템학회논문지
• /
• 제15권2호
• /
• pp.225-230
• /
• 2009

We propose a template matching method for component inspection of SMD assembly system. To discriminate wrong assembled components, the input image of component is matched with its standard image by template matching algorithm. For a fast inspection system, the calculation time of matching algorithm should be reduced. Since the standard images of all components located in a PCB are stored in computer, it is desirable to reduce the memory size of standard image. We apply the discrete wavelet transformation to reduce the image size as well as the calculation time. Only 7% memory of the BMP image is used to discriminate goodness or badness of components assembly. Comparative results are presented to verify the usefulness of the proposed method.

• 복식문화연구
• /
• 제20권3호
• /
• pp.416-429
• /
• 2012

The purpose of this study was to examine the effects of VM components(facade color and show window type) on store image and purchasing intention of fashion stores. The subjects were 428 male and female university students in Daejeon and Chungnam province. The measuring instruments were 6 stimuli manipulated by $3{\times}2$ factorial design of facade color and show window type, and a self-administrated questionnaire consisted of store image, purchasing intention, and subjects' demographic characteristics. The results were as follows. First, facade color mainly affected store image and purchasing intention. White color was preferred as more positive images(pleasurable, comfortable, neat, and modern), and showed higher purchasing intention than brown color. Second, show window type affected some store images. Semi-open type was perceived as more pleasurable image than enclosed type, whereas enclosed type was perceived as more luxurious, neat, and attractive image than semi-open type. However, show window type didn't affect purchasing intention. Third, subject' sex affected store image and purchasing intention. Male subjects perceived more positively on store image and had higher purchasing intention than females. This study suggested that facade color and show window type are important VM components affecting store image and purchasing intention.

• 한국방사선학회논문지
• /
• 제9권5호
• /
• pp.301-306
• /
• 2015

엑스선을 이용하면 다양한 종류의 시료에 대한 투영 영상을 얻을 수 있다. 시료가 저밀도 및 고밀도의 복합 물질로 구성되어 있는 경우는 단일 관전압 엑스선을 이용해서 두 물질을 모두 대조도가 높도록 영상화하기 어렵다. 저관전압과 고관전압을 이용하여 영상을 획득하고 영상처리하면 밀도의 차이가 큰 물질을 영상화하기에 용이하다. 크기가 작은 전자부품을 저관전압과 고관전압에서 영상을 획득하여 visual C++을 이용하여 픽셀-픽셀 영상 합성을 통하여 전자부품의 합성수지부분과 금속부분을 동시에 영상화하여 전자부품의 검사 및 관찰의 가능성을 검증하였다.

• 한국조리학회지
• /
• 제14권2호
• /
• pp.128-137
• /
• 2008

The importance of brand and brand equity has greatly increased not only in the professional perspectives but also in academic viewpoints. Especially, lots of related studies have been focused on the components of brand equity itself. However, this study concentrates on the relationships of brand equity components for understanding consumers' attitudes toward the brands of the food-service businesses. The basic research model consists of 4 brand equity components: brand awareness, perceived quality, brand image, and brand preference. Research data are gathered through survey questions responded by university students. For statistical analysis, correlation analysis, factor analysis, and covariance structure analysis are carried out. The result of this study are summed up as follows. Among the brand equity components, brand awareness had a great effect on perceived quality(path coefficient; 0.476). Brand image highly influenced brand preference(path coefficient; 0.439).

• 대한전자공학회논문지SP
• /
• 제40권1호
• /
• pp.20-27
• /
• 2003

본 논문에서는 사용자가 질의를 원하는 물체 영역을 선택하면 유사 물체를 영상 데이터베이스 내에서 검색할 수 있는 내용기반 영상검색 시스템을 구현하였다. 질의영상은 색상성분과 그레이성분으로 나누어져 웨블릿 변환되고 색상성분에서는 컬러 오토코릴로그램과 분산으로 색상특성을 추출한다. 그리고 그레이성분에서는 오토코릴로그램과 GLCM을 통해 질감특성을 추출한다. 이렇게 구한 2개 성분에서의 특성들을 이용하여 데이터베이스내의 영상들과 각각 유사도를 비교하여 검색하게 된다. 이때 각 유사도에 가중치를 적용하였다. 한 가지 성분보다 두 가지 성분에서 특성을 구하여 각각의 단점을 보완하였고 실험 결과에서도 소환성(recall) 및 정확성(precision)이 향상됨을 볼 수 있었다 또한 가중치를 적용함으로써 검색 효율이 개선되었다. 그리고 데이터베이스내 영상들의 여러 특성을 특성 라이브러리내에 자동 색인화 시킴으로써 고속의 영상 검색이 가능하였다.