• 산업공학
• /
• 제9권1호
• /
• pp.73-82
• /
• 1996

The purpose of this research is to construct real-time image acquisition system for a line-scan inspection system as a computer vision system. To construct the line-scan inspection system, many problem arise. However, problems of image acquisitions using linear CCD are practically studied in this paper. These problems are concerned to proper lighting systems, relations with handling system, camera systems, and impacts due to the noise of environment. These problems are examined separately, and proper configurations for each case are suggested to construct the line-scan image acquisition system.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2007년도 하계종합학술대회 논문집
• /
• pp.387-388
• /
• 2007

In this paper, a content-based image retrieval method considering both local information and spatial correlation of image is proposed. In order to efficiently represent the spatial correlation, texture structure is classified into three kinds of pattern. In experiment result, our method improves $3.94%{\sim}11.23%$ precision rate over the existing methods.

• Communications for Statistical Applications and Methods
• /
• 제6권3호
• /
• pp.831-842
• /
• 1999

We propose a wavelet decomposition feature extraction method for the hand-written character recognition. Comparing the recognition rates of which methods with original image features and with selected features by the wavelet decomposition we study the characteristics of the proposed method. LDA(Linear Discriminant Analysis) QDA(Quadratic Discriminant Analysis) RDA(Regularized Discriminant Analysis) and NN(Neural network) are used for the calculation of recognition rates. 6000 hand-written numerals from CENPARMI at Concordia University are used for the experiment. We found that the set of significantly selected wavelet decomposed features generates higher recognition rate than the original image features.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2006년도 추계학술대회 학술발표 논문집 제16권 제2호
• /
• pp.272-274
• /
• 2006

In this paper, we concentrate on the mask design problem for optical micro-lithography. The pre-distorted mask is obtained by minimizing the error between the designed output image and the projected output image. We use the particle swarm optimization(PSO) and fuzzy system to insure that the resulting images are identical to the desired image. Our method has good performance for the iteration number by an experiment.

• IEIE Transactions on Smart Processing and Computing
• /
• 제1권1호
• /
• pp.17-26
• /
• 2012

This paper presents an image processing-based validation method for unrecognizable numbers in severely distorted license plate images which have been degraded by various factors including low-resolution, low light-level, geometric distortion, and periodic noise. Existing vehicle license plate recognition (LPR) methods assume that most of the image degradation factors have been removed before performing the recognition of printed numbers and letters. If this is not the case, conventional LPR becomes impossible. The proposed method adopts a novel approach where a set of reference number images are intentionally degraded using the same factors estimated from the input image. After a series of image processing steps, including geometric transformation, super-resolution, and filtering, a comparison using cross-correlation between the intentionally degraded reference and the input images can provide a successful identification of the visually unrecognizable numbers. The proposed method makes it possible to validate numbers in a license plate image taken under low light-level conditions. In the experiment, using an extended set of test images that are unrecognizable to human vision, the proposed method provides a successful recognition rate of over 95%, whereas most existing LPR methods fail due to the severe distortion.

• 한국치위생학회지
• /
• 제15권6호
• /
• pp.1043-1051
• /
• 2015

Objectives: The purpose of the study is to investigate self-efficacy, self-image, and image as a dental hygienist of the dental hygiene student. Methods: A self-reported questionnaire was completed by 479 dental hygiene students in Daegu and Gyeongnam from November 5 to 25, 2014. The questionnaire consisted of self-efficacy(18 items), self-image(23 items), and image as a dental hygienist(36 items) by Likert 5 points scale. Data were analyzed by t test, ANOVA, regression analysis, and post hoc Tukey test using SPSS 20.0 program. Results: The self-efficacy of the first, second, and third grade was 2.72, 2.71, and 2.60, respectively(p<0.002). Those living with family tended to have higher mark than those living without family(p<0.001). The influence of self-efficacy on self image and image as a dental hygienist was positively correlated(p<0.001). Conclusions: The right self-image and self-efficacy of the dental hygiene students can be a powerful influence on the image as a dental hygienist. It is necessary to develop and implement the ethics education for the dental hygiene students.

• 감성과학
• /
• 제14권1호
• /
• pp.49-58
• /
• 2011

본 연구는 스타일리시 호텔에 대한 공간이미지와 선호도에 관한 연구이며, 아울러 선행연구인 성별 및 연령에 따른 스타일리시의 언어이미지와 색채이미지에 관해 조사 결과 중 미니멀스타일배색에 대한 검증연구이다. 연구결과 성별 및 연령에 있어서 유의한 차이를 보이지 않았으며, 스타일리시 호텔의 공간이미지와 언어이미지의 상관성을 알아보고자 대표 언어를 추출한 결과, 개성적인, 감각적인, 심플한, 도시적인 등으로 인식하여 공간이미지에 대해 스타일리시하게 느끼는 것으로 파악되었다. 또한 공간이미지와 선호도에서는 로비공간의 B호텔, 식음공간의 C호텔, 객실공간의 A호텔로 나타났으며, 색채이미지와 선호도에서는 각각 고명도 저채도, 저명도 저채도로 나타났다. 이것은 선행연구의 가장 스타일리시 한 것으로 인식한 미니멀스타일배색과 동일한 결과로 응답자들은 스타일리시 호텔의 공간이미지에 대해 언어적으로는 세련되고 감각적이며 개성적인 것으로 인식하면서 시각적으로는 고명도 저채도, 저명도 저채도의 공간을 스타일리시 한 것으로 인식하고 있음이 밝혀졌다. 본 연구는 향후 스타일리시한 공간 연출 및 디자인 마케팅을 위해 새로운 디자인 방향을 제시하는 데 그 목적이 있다.

• 한국의상디자인학회지
• /
• 제14권1호
• /
• pp.123-130
• /
• 2012

The purpose of this study is to understand Skull Images in fashion trends and Skull Image Top Design for Female Teenagers. The methods of this study are an academic literature review as well as practical study through actual case studies about. The subjects of the study were 53 Female Teenagers who lived in Chuncheon. Data were collected during March, 2009. Statistical analyses used in the study were frequency. An adolescent period, they are rebellious, sensual and syntonic inclination. These days, Lots of Female Teenagers want unique fashion for herself and select Skull Image clothing. But they want fit and pretty style not big-look. In this study, I designed seven pieces of Top blouse while applying Skull Image, an important image of Hip-hop and Punk fashion, and the concepts of the continuance theory to them. This study will make a contribution to the designing of Top for Female Teenagers through reinterpretation of the Hip-hop and Punk fashion. In addition, there are practicable and unique Top design for Female Teenagers.

• JSTS:Journal of Semiconductor Technology and Science
• /
• 제15권1호
• /
• pp.60-67
• /
• 2015

This paper proposes an image-dependent color image enhancement method that uses adaptive luminance enhancement and color emphasis. It effectively enhances details of low-light regions while maintaining well-balanced luminance and color information. To compare the structure similarity and naturalness, we used the tone mapped image quality index (TMQI). The proposed method maintained better structure similarity in the enhanced image than did the space-variant luminance map (SVLM) method or the adaptive and integrated neighborhood dependent approach for nonlinear enhancement (AINDANE). The proposed method required the smallest computation time among the three algorithms. The proposed method can be easily implemented using the field-programmable gate array (FPGA), with low hardware resources and with better performance in terms of similarity.

• 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.330-336
• /
• 2000

A color is the most important of all factors that have influence on interior spaces, and plays an visually and psychologically important role in making interior environment. Thus, the aim of this study is to propose predictable color models by image types specially for color design in living room.This study was composed of three steps, and was carried out as follows.1) The evaluation experiment was carried out by color simulation using Color Image Processor. 2) Image types were extracted by factor analysis. 3) The characteristics of colors by image types were analysed by the multi regression and as a result the predictable color models by image types was determined.