• 제어로봇시스템학회논문지
• /
• 제12권2호
• /
• pp.119-129
• /
• 2006

Art psychotherapy is widely accepted as an effective tool for diagnosis and treatment of psychological disorders. Important factors for art psychotherapy diagnosis, based on the projection theory that the world of the inner mind appears in drawings, include main color and imbalance of a drawing. This paper develops a system for a machine to determine the main color and the imbalance of a drawing by color recognition and edge detection. Our proposed color recognition procedure adopts NBS(National Bureau of Standards) distance between colors in HVC(Hue, Value, Chroma) color space which is most similar to the human eye's color perception. Our edge detection procedure applies blurring, clustering and transformation to a standard color in a series. Our system considers the numbers of pixels and clusters for each color as a criterion for main color and the frequency of edge coordinates for each region for imbalance. The proposed machine procedure, verified through case studies, can help overcome the subjectivity, ambiguity and uncertainty in human decision involved in art psychotherapy.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.430-432
• /
• 2008

Visible channel calibration method using deep convective clouds (DCCs) is developed. The method has advantages that visible radiance is not sensitive to cloud optical thickness (COT) for deep convective clouds because visible radiance no longer increases when COT exceeds 100. Therefore, once DCCs are chosen appropriately, and then cloud optical properties can be assumed without operational ancillary data for the specification of cloud conditions in radiative transfer model. In this study, it is investigated whether IR measurements can be used for the selection of DCC targets. To construct appropriate threshold value for the selection of DCCs, the statistics of cloud optical properties are collected with MODIS measurements. When MODIS brightness temperature (TB) at 11 ${\mu}$ m is restricted to be less than 190 K, it is shown that more than 85% of selected pixels show COT ${\geq}$ 100. Moreover, effective radius ($r_e$) distribution shows a sharp peak around 20 ${\mu}m$. Based on those MODIS observations, cloud optical properties are assumed as COT = 200 and $r_e$ = 20 ${\mu}m$ for the simulation of MODIS visible (0.646 ${\mu}m$) band radiances over DCC targets.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.382-385
• /
• 2008

MODIS images have a great advantage of high temporal resolution to monitor land cover changes in a large area. The moderate and low spatial resolution satellite images are incomparably economic than high resolution satellite images. As diverse satellite images are provided recently, strategies using satellite images are necessary for continuous, effective and long-term land monitoring. This research purposed to use MODIS images to monitor land cover in Korean peninsula for long-term and continuous change detection. To maximize the advantages of high temporal resolution, the change detection was based on the MODIS temporal profiles of the surface reflectance for one year. In this study as the reflectance patterns of year 2005 were compared with the reflectance patterns of year 2007, the changed pixels could be detected during two years. To set up the threshold value for the decision of change, ASTER images with the higher spatial resolution, 15m, were used for this study. The test area covered the suburban area of metropolitan city, Seoul, where the landcover changes have been frequently happened.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.520-524
• /
• 2009

In compressed color images, colors are usually represented by luminance and chrominance (YCbCr) components. Considering characteristics of human vision system, chrominance (CbCr) components are generally represented more coarsely than luminance component. Aiming at possible recovery of chrominance components, we propose a model-based chrominance estimation algorithm where color images are modeled by a Markov random field (MRF). A simple MRF model is here used whose local conditional probability density function (pdf) for a color vector of a pixel is a Gaussian pdf depending on color vectors of its neighboring pixels. Chrominance components of a pixel are estimated by maximizing the conditional pdf given its luminance component and its neighboring color vectors. Experimental results show that the proposed chrominance estimation algorithm is effective for quality improvement of compressed color images such as JPEG and JPEG2000.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.286-289
• /
• 2009

This paper presents an effective approach to minimize recursive computations for balancing stereo pairs by using disparity vector errors and its directional histogram. A stereo balancing function is computed from the correspondent pixels between two images, and a simple approach is to find the matching blocks of two images. However, this procedure requires recursive operation, and its computation cost is very high. Therefore, in this paper, we propose an efficient balance method using structural similarity index and a partial re-searching scheme to reduce the computation cost considerably. For this purpose, we determine if re-searching for each block is necessary or not by using the errors and the directional histogram of disparity vectors. Experiment results show that the performance of the proposed approach can save the computations significantly with ignorable image quality degradation compared with full re-search approach.

• 대한원격탐사학회지
• /
• 제28권6호
• /
• pp.611-622
• /
• 2012

This study proposed two multisensor fusion methods for segment-based image classification utilizing a region-growing segmentation. The proposed algorithms employ a Gaussian-PDF measure and an evidential measure respectively. In remote sensing application, segment-based approaches are used to extract more explicit information on spatial structure compared to pixel-based methods. Data from a single sensor may be insufficient to provide accurate description of a ground scene in image classification. Due to the redundant and complementary nature of multisensor data, a combination of information from multiple sensors can make reduce classification error rate. The Gaussian-PDF method defines a regional measure as the PDF average of pixels belonging to the region, and assigns a region into a class associated with the maximum of regional measure. The evidential fusion method uses two measures of plausibility and belief, which are derived from a mass function of the Beta distribution for the basic probability assignment of every hypothesis about region classes. The proposed methods were applied to the SPOT XS and ENVISAT data, which were acquired over Iksan area of of Korean peninsula. The experiment results showed that the segment-based method of evidential measure is greatly effective on improving the classification via multisensor fusion.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.278-281
• /
• 2007

The purpose of this study is to develop snow and sea ice detection algorithm in Communication, Ocean and Meteorological Satellite (COMS) meteorological data processing system. Since COMS has only five channels, it is not affordable to use microwave or shortwave infrared data which are effective and generally used for snow detection. In order to estimate snow and sea ice coverage, combinations between available channel data(mostly visible and 3.7 ${\mu}m$) are applied to the algorithm based on threshold method. As a result, the COMS snow and sea ice detection algorithm shows reliable performance compared to MODIS products with channel limitation. Specifically, there is partial underestimation over the complicated vegetation area and overestimation over the area of high level clouds such as cirrus. Some corrections are performed by using water vapor and infrared channels to remove cloud contamination and by applying NDVI to detect more snow pixels for the underestimated area.

• 한국통신학회논문지
• /
• 제29권3C호
• /
• pp.387-397
• /
• 2004

영상의 주파수 정보와 공간 정보를 동시에 제공하는 웨이브렛 변환(Wavelet transform)은 영상압축에 매우 효과적임이 밝혀졌고, 최근 들어 웨이브렛 변환 방법으로 다해상도 분해된 영상에 여러 가지 부호화 알고리즘을 적용하는 것에 대해 많은 연구가 진행되고 있다. 본 논문에서는, 웨이브렛 변환으로 다해상도 분해된 적외선 영상에 픽셀간의 상관도와 '0' 정보를 모아 효과적으로 압축할 수 있는 양자화 기법인 쿼드트리 기반 블록 양자화(Quadtree based block quantization)를 적용하여 영상을 압축하는 방법을 제안한파. 웨이브렛 변환된 계수는 스케일간 상잔도가 놀고, 집중도가 높기 때문에 쿼드트리를 적용할 경우 효과적으로 데이터량을 줄일 수 있다. 실험영상으로 256${\times}$256 크기의 8〔bit〕 적외선영상을 이용하고, DCT 압축기법과 제안한 기법을 비교 평가한다.

• 전자공학회논문지C
• /
• 제36C권9호
• /
• pp.66-75
• /
• 1999

영상분할은 입력된 영상을 처리하여 유사한 화소들의 집합인 영역들로 화소들을 구분하는 작업이다. 영상분할의 결과는 영상인식의 정확성에 큰 영향을 미친다. 본 논문에서는 유전자 알고리즘을 이용하여 마르코프 랜덤 필드(Markov random field)에 기반한 영상분할 방법을 제안한다. 제안한 방법에서는 잡음과 흔들림(blurring)에 강한 MRF를 이용하여 영상을 모델링 한다. HRF기반 영상분할 방법은 왜곡에 강한 반면, 정확한 파라미터의 추정이 요구된다. 그래서 , 추정방법으로 많은 파라미터를 포함하는 문제를 다루는데 효율적인 유전자 알고리즘을 사용한다. 실 영상을 가지고 수행된 실험 결과와 자동 차량 추출 시스템에의 응용결과는 제안된 방법의 효율성을 보여준다.

• 전기전자학회논문지
• /
• 제7권2호
• /
• pp.271-280
• /
• 2003

본 논문에서는 진단 초음파 영상에서의 스펙클 잡음의 영향을 줄여 대상물체를 효율적으로 분리하는 방법을 제안하였다. 스페클 잡음을 제거하기 위하여 전처리 과정에서 gray scale opening 연산을 실행 후 윈도우내에서 임의의 픽셀에서의 분산을 계산하여 균일 영역과 경계 영역을 구분하고, 구분된 각 영역에 대해 윈도우 크기가 다른 pseudomedian 필터를 사용하였다. (본 논문에서 적응 pseudomedian 필터라 부름.) 영역 구분 없이 같은 크기의 윈도우를 사용한 경우보다 필터링 시간이 단축되며, 스페클 잡음을 충분히 제거할 수 있었다. 필터의 성능을 평가하기 위하여, 제안한 필터를 기존의 영상처리 필터의 결과에 대한 PSNR과 비교하여 우수하다는 것을 입증하였다.