• 반도체디스플레이기술학회지
• /
• 제6권2호
• /
• pp.53-57
• /
• 2007

In this paper, a new content-based color image retrieval method is proposed, in which both the color content and the spatial relationship of image have been taken into account. In order to represent the spatial distribution information of image, a disorder matrix, which has the invariance to the rotation and translation of the image content, has been designed. This is based on multi-resolution color-spatial information. We present our algorithm in the following section, and then verified the search results with comparison to other methods, such as color histogram, wavelet histogram, correlogram and wavelet correlogram. Experimental results with various types of images show that the proposed method not only achieves a high image retrieval performance but also improve the retrieval precision.

• 한국조리학회지
• /
• 제14권1호
• /
• pp.123-133
• /
• 2008

Hangwha is a part of our traditional culture; however, it is now barely maintaining its name. This study intends to contribute to the development of the Hanghwa industry. In this respect, 'Brand Image' is adopted to suggest the ways to develop the Hangwha industry. Commercializing factors that consumers prefer were analyzed and their effects on brand image were investigated. In addition, the effects of brand image on consumers' awareness and preference were analyzed. This research conducted analysis on 294 people who have used Hangwha in Busan and Gyeongsangnamdo. The results of this empirical study are as follows: It turned out that Hangwha influences the society-oriented and consumer-oriented brand image. Its quality-oriented image has influence on awareness. Its society-oriented and quality-oriented brand image turned out to influence preference.

• 대한원격탐사학회지
• /
• 제16권4호
• /
• pp.355-365
• /
• 2000

The interferometric correlation, or coherence, is calculated to measure the variance of the interferometric phase and amplitude within the neighbourhood of any location within the image at a result of SAR (Synthetic Aperture Radar) interferometric process which utilizes the phase information of the images. The coherence contains additional information that is useful for detecting point targets which change their location in an area of interest (AOI). In this research, a RGB colour composite image was generated with a intensity image (master image), a intensity change image as a difference between master image and slave image, and a coherence image generated as a part of SAR interferometric processing. We developed a technique performing detection of a point target movement using SAR interferometry and applied it to suitable tandem pair images of ERS-1 and ERS-2 as test data. The possibility of change detection of a point target in the AOI could be identified with the technique proposed in this research.

• Journal of Information Processing Systems
• /
• 제17권6호
• /
• pp.1138-1156
• /
• 2021

Emotional semantics are the highest level of semantics that can be extracted from an image. Constructing a system that can automatically recognize the emotional semantics from images will be significant for marketing, smart healthcare, and deep human-computer interaction. To understand the direction of image emotion recognition as well as the general research methods, we summarize the current development trends and shed light on potential future research. The primary contributions of this paper are as follows. We investigate the color, texture, shape and contour features used for emotional semantics extraction. We establish two models that map images into emotional space and introduce in detail the various processes in the image emotional semantic recognition framework. We also discuss important datasets and useful applications in the field such as garment image and image retrieval. We conclude with a brief discussion about future research trends.

• 대한원격탐사학회지
• /
• 제28권4호
• /
• pp.459-466
• /
• 2012

위성영상 운영은 주문접수, 촬영계획, 영상처리, 영상 배포의 과정으로 구분하며 촬영계획은 주문 접수 과정에서 전달된 신규 주문과 이미 진행 중인 주문을 바탕으로 한정된 위성자원을 최대한 활용하여 사용자의 촬영요청을 가능한 적절한 시기에 반영할 수 있도록 위성의 촬영계획을 수립하는 과정으로 위성 자원의 효율적인 활용이라는 취지와 가장 밀접한 관계를 갖는 과정에 해당한다. 촬영계획은 동시에 많은 변수를 고려해야 하기 때문에 연산량도 많은 편이며, 스케줄링을 수행할 때마다 동일한 과정을 반복적으로 수행해야 한다. 본 논문에서는 촬영계획의 효율성을 높이기 위해 촬영계획의 최적화 연구를 수행하였다. 먼저 촬영계획 수행과정과 제약조건을 정리하여 가능한 많이 촬영할 수 있도록 촬영계획 모형을 수립하고 그 모형을 해결하기 위해 휴리스틱 알고리즘을 제안하였다.

• 대한전자공학회논문지SP
• /
• 제41권6호
• /
• pp.127-135
• /
• 2004

멀티미디어 기술의 광범위한 보급으로 여러 분야에서 영상처리 기술 인력에 대한 수요가 증가하고 있으나, 실무능력을 가진 전문 인력의 수는 시장의 요구에 비해 매우 적다. 영상처리 분야에 실무능력을 갖춘 전문 인력을 양성하기 위해서는 이론 교육과정과 함께 학습한 이론을 실제 영상자료에 적용하고 적용된 결과를 분석해 볼 수 있는 실습과정을 체계적으로 지원할 수 있는 통합된 교육 환경이 필요하다. 본 논문에서는 효율적인 영상처리 교육이 이루어지도록 이론적인 내용과 이론에 따른 다양한 해법을 직접 체험해 볼 수 있고 학습과정에서 얻어진 새로운 아이디어를 쉽게 구현해 볼 수 있는 통합 환경인 MTES(Multimedia Technology Education System)를 제안한다. MTES는 영상처리 개발 환경인 Hello-Vision을 시뮬레이션 환경으로 사용할 수 있도록 수정하였으며, 이론교육환경과 이론과 실습이 체계적으로 이루어지도록 제어하는 제어관리자를 개발하여 효과적인 영상처리 교육 환경이 되도록 개발하였다.

• 비파괴검사학회지
• /
• 제22권5호
• /
• pp.523-531
• /
• 2002

본 연구는 속도 향상을 고려한 실시간 다물체 화상처리 알고리즘을 개발하고자 한다. 최근 들어 비전시스템의 사용은 검사 및 로봇 위치 제어 풍에서 급속히 증가하고 있다. 이러한 비전시스템을 적용하기 위해서는 3차원 공간상 물체의 좌표를 CCD 카메라에 의해서 얻어진 이미지 정보로 변환하는 것이 필요하다. 검사 및 로봇 위치 제어 작업들에 비전시스템을 적용하기 위해서 이미지 평면에서 물체의 중심 위치를 알아야 한다. 특히, 그것의 물체 형상을 표시하기 위하여 여러 개 큐들을 사용하는 강체의 경우에는 여러 개 큐들의 각각 위치 값들이 동시에 하나의 이미지 평면에서 결정되어 져야 한다. 이러한 문제를 해결하기 위하여 여러 개 큐 (다물체)에 대한 화상처리 알고리즘 개발 과정을 본 논문에서 제시하고, 개발된 알고리즘의 타당성을 제시하였다.

• 복식문화연구
• /
• 제26권2호
• /
• pp.233-250
• /
• 2018

This study examined images typical to this city and explored ways to develop cultural products using these images. Researchers reviewed literature about fashion cultural products and related previous research, and then conducted a closed-ended survey to analyze universal fashion preferences. For the examination material, such a way was used as information data base and network review inside and outside the country, dissertation screen, and published media including separate volumes. The following are considering points in the developing process. First, the study identified design, color, price, practicality and quality as factors that should be taken into consideration when using the image of Gangneung. In particular, it determined that the image needs to reflect a modern sensibility while maximizing its representation of local culture. Second, Gangneung's symbolic image should incorporate the sea, Gyeongpo, and coffee. In other words, the sea, Gyeongpo, and coffee should receive top symbolic priority. Third, from a development perspective, the most appropriate items for displaying the image include t-shirts, keychains, umbrellas, or other accessories, since these items are easily available in terms of price. In sum, this study highlighted the necessity of reconsidering Gangneung's currents ymbolic image, suggesting that a new image should be developed. Developing a typical fashion cultural product image will enrich Gangneung's cultural industry and the distribution of newly designed products will improve the localeconomy.

• Journal of Biosystems Engineering
• /
• 제29권1호
• /
• pp.71-78
• /
• 2004

Real time and robust algorithm to extract the features of watermelon was developed from the remotely transmitted image of the watermelon. Features of the watermelon at the cultivation site such as size and shape including position are crucial to the successful tole-robotic operation and development of the cultivation data base. Algorithm was developed based on the concept of task sharing between the computer and the operator utilizing man-computer interface. Task sharing was performed based on the functional characteristics of human and computer. Identifying watermelon from the image transmitted from the cultivation site is very difficult because of the variable light condition and the complex image contents such as soil, mulching vinyl, straws on the ground, irregular leaves and stems. Utilizing operator's teaching through the touch screen mounted on the image monitor, the complex time consuming image processing process and instability of processing results in the watermelon identification has been avoided. Color and brightness characteristics were analyzed from the image area specified by the operator's teaching. Watermelon segmentation was performed using the brightness and color distribution of the specified imae processing area. Modified general Hough transform was developed to extract the shape, major and minor axes, and the position, of the watermelon. It took less than 100 msec of the image processing time, and was a lot faster than conventional approach. The proposed method showed the robustness and practicability in identifying watermelon from the wireless transmitted color image of the cultivation site.

• Journal of Biosystems Engineering
• /
• 제39권4호
• /
• pp.324-329
• /
• 2014

Purpose: The finite element method (FEM) is advantageous because it can save time and cost by reducing the number of samples and experiments in the effort to identify design factors. In computational problem-solving it is necessary that the exact material properties are input for achieving a reliable analysis. However, in the case of fiber boards, it is difficult to measure their cross-directional material properties because of their small thickness. In previous research studies, the Poisson's ratio was measured by analyzing ultrasonic wave velocities. Recently, the Poisson's ratio was measured using a high-speed digital camera. In this study, we measured the transverse strain of a fiber board and calculated its Poisson's ratio using a high-speed digital camera in order to apply these estimates to a FEM analysis of a fiber board, a corrugated board, and a corrugated box. Methods: Three different fiber board samples were used in a uniaxial tensile test. The longitudinal strain was measured using the Universal Testing Machine. The transverse strain was measured using an image processing method. To calculate the transverse strain, we acquired images of the fiber board before the test onset and before the fracture occurred. Acquired images were processed using the image processing program MATLAB. After the images were converted from color to binary, we calculated the width of the fiber board. Results: The calculated Poisson's ratio ranged between 0.2968-0.4425 (Machine direction, MD) and 0.1619-0.1751 (Cross machine direction, CD). Conclusions: This study demonstrates that measurement of the transverse properties of a fiber board is possible using image processing methods. Correspondingly, these processing methods could be used to measure material properties that are difficult to measure using conventional measuring methodologies that employ strain gauge extensometers.