• The Journal of Natural Sciences
• /
• v.7
• /
• pp.67-73
• /
• 1995

In this paper, a new texture segmentation-based image coding technique which performs segmentation based on properties of the human visual system (HVS) is presented. This method solves the problems of a segmentation-based image coding technique with constant segments by proposing a methodology for segmenting an image into texturally homogeneous regions with respect to the degree of roughness as perceived by the HVS. The segmentation is accomplished by thresholding the fractal dimension so that textural regions are classified into three texture classes; perceived constant intensity, smooth texture, and rough texture. It is very important to determine the proper block size for estimating the fractal dimension. Good quality reconstructed images are obtained with about 0.1 to 0.25 bit per pixel (bpp) for many different types of imagery.

• The KIPS Transactions:PartD
• /
• v.17D no.1
• /
• pp.59-66
• /
• 2010

Traditional OCR engines are designed to the scanned documents in calibrated environment. Three dimensional perspective distortion and smooth distortion in images are critical problems caused by un-calibrated devices, e.g. image from smart phones. To meet the growing demand of character recognition of texts embedded in the photos acquired from the non-calibrated hand-held devices, we address the problem in three categorical aspects: rotational invariant method of text region extraction, scale invariant method of text line segmentation, and three dimensional perspective mapping. With the integration of the methods, we developed an OCR for camera-captured images.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.04a
• /
• pp.151-154
• /
• 2001

1990 년 후반부터 인터넷의 활용과 이동통신 기술의 범용화로 무선 인터넷 서비스의 수요가 점차적으로 빠르게 증대되어지고 있다. 하지만, 현 단계의 무선인터넷 서비스는 급변하는 시장과는 달리 정체 상태로 머물고 있다. 이러한 이유에는 여러 가지가 있겠지만 가장 큰 이유는 제한된 환경이라고 볼 수가 있다. 특히 현재의 무선 인터넷은 다양한 동영상 종류의 포맷을 지원하지 못하고 있다. 무선 인터넷 서비스 중에서도 특히 게임과 동영상 등에 대한 관심이 집중되어지고 있지만 현 시점에서는 간단한 흑백 이미지와 *.sis 파일의 형태만을 지원한다. 저 품질 영상이 제공되는 현 시점에서 유선 인터넷과 같은 다양한 서비스 지원을 하기 위해서는 획기적인 방법이 요구된다. 본 논문에서는 여러 가지 컨텐츠 타입을 지원하고, 대용량의 동영상 파일 등에 대해 설계 및 구현을 위한 최적화 방법론 중, DAIAML 이라는 새로운 측면의 스크립트 형태의 언어를 제안하며, 언어적 측면에서의 해석이 아닌 그래픽적 측면에서의 해석으로 접근한 방식이고 휴대폰이 칼라모드만 지원한다면 하드웨어적인 문제와는 상관없이 VOD 등의 고품질 동영상을 제공받으며 위의 요구 사항과 다양한 서비스 측면에 대해 소비자의 욕구를 만족시킬 수 있고, 많은 유선 인터넷 서비스들이 무선 인터넷으로 이동(migration)될 수 있다.

• Proceedings of the KGS Conference
• /
• 2002.11a
• /
• pp.119-122
• /
• 2002

효율적인 자연환경보전을 위한 방법론상의 선결과제는 자연환경에 대한 신뢰할 수 있는 기초조사 자료를 확보하고 이를 기반으로 하여 효율적인 보전정책을 수립하는 것이 필요하다. 우리나라의 환경부 등 관련기관이나 미국, 영국, 독일 등 각 국의 환경관련기관에서 사용하고 있는 자연환경에 대한 기초 자료는 대부분 현장조사에 기반을 두고 있거나 항공사진에 의거하여 확보되어지고 있다.(중략)

• Proceedings of the KOR-KST Conference
• /
• 2007.05a
• /
• pp.179-187
• /
• 2007

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.550-552
• /
• 2002

플러스터링이란 주어진 데이터 집합의 패턴들을 비슷한 성실을 가지는 그룹으로 나누어 패턴 상호간의 관계를 정립하기 위한 방법론으로, 지금가지 이를 위한 많은 알고리즘들이 개발되어 왔으며, 패턴인식, 영상 처리 등의 여러 공학 분야에 널리 적용되고 있다. FCM(Fuzzy C-Means) 알고리즘은 최소자승 기준함수(least square criterion function)에 퍼지이론을 적용만 목적함수의 반복최적화(iterative optimization)에 기반을 둔 방식으로, 하드 분할에 의한 기존의 클러스터링 방법이 승자(winner take all) 형태의 방법론을 취하는데 비하여, 각 패턴이 특정 클러스터에 속하는 소속정도를 줌으로써 보다 정확한 정보를 형성하도록 도와준다. 본 논문에서는 FCM 기법을 이용한 웹로그 분석을 하고자 한다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.5
• /
• pp.471-478
• /
• 2011

High resolution Pan-sharpening technique is becoming increasingly important in the field of remote sensing image analysis as an essential image processing to improve the spatial resolution of original multispectral image. The general scheme of pan-sharpening technique consists of upsampling process of multispectral image and high-pass detail injection process using the panchromatic image. The upsampling process, however, brings about image blurring, and this lead to spectral distortion in the pan-sharpening process. In order to solve this problem, this paper presents a new method that adopts image restoration techniques based on optimization theory in the pan-sharpening process, and evaluates its efficiency and application possibility. In order to evaluate the effect of image restoration techniques on the pansharpening process, the result obtained using the existing method that used bicubic interpolation were compared visually and quantitatively with the results obtained using image restoration techniques. The quantitative comparison was done using some spectral distortion measures for use to evaluate the quality of pan-sharpened image.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.6
• /
• pp.1342-1347
• /
• 2013

Color harmony of Moon and Spencer is based on the Munsell color harmony theory. This harmony theory is established in the three of harmony and disharmony, the harmony of the area of effect, and Aesthetic Measure of harmony and disharmony. Aesthetic Measure here is how to obtain the quantitative expression of the degree of harmony. American scholar Burkhoff were analyzed with the proposition that beauty of Moon-Spencer is with the order in complexity. In this paper, the good and bad of coloration was divide elements of the order and the complexity. Aesthetic Measure is divided into elements of the complexity from elements of the order. This is utilized in the calculation shown in the various image, problem of color harmony and disharmony, which is treated as a sensibility was calculated by numerically. Thus Aesthetic Measure show was good or bad coloration by determining the color in the various image.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.5
• /
• pp.11-20
• /
• 2014

Due to the importance of vehicle detector which plays an essential role in generating real-life traffic information, maintaining detector data quality is preeminent in advanced traffic management and information systems (ATMIS). To this end, agencies periodically conduct performance tests on detectors. Detector evaluation is generally performed by comparing baseline data with corresponding detector data. Here, two important things need to be addressed; one is errors (or uncertainties) included in baseline data and the other is the confidence interval concept to represent evaluation results of sample data to corresponding ones of population. To resolve these problems, a new detector evaluation scheme is introduced and the scheme is applied to individual level detector evaluations of loop, video image, and radar detectors. The purpose of individual level evaluation is to eliminate the balancing (or cancelling-out) effects of over- and under-counts. As a consequence, the proposed scheme is proven to be effectively applied to real-world detector evaluations.

• Journal of Korean Society for Geospatial Information Science
• /
• v.18 no.4
• /
• pp.11-20
• /
• 2010

In situation that carbon dioxide emissions are being increased as urbanization, urban green space is being promoted as an alternative to find solution for these problems. In urban areas, trees have the ability to reduce carbon dioxide as well as to be aesthetic effect. In this study, we proposed the methodology which uses only LIDAR data in order to extract these trees information effectively. To improve the operational efficiency according to the extraction of trees, the proposed methodology was carried out using multiple data processing such as point, polygon and raster. Because the existing NDSM(Normalized Digital Surface Model) contains both the building and tree information, it has the problems of high complexity of data processing for extracting trees. Therefore, in order to improve these problems, this study used modified NDSM which was removed estimate regions of building. To evaluate the performance of the proposed methodology, three different zones which coexist buildings and trees within urban areas were selected and the accuracy of extracted trees was compared with the image taken by digital camera.