• 제목/요약/키워드: likelihood image

검색결과 220건 처리시간 0.032초

신뢰 전파와 디스패리티 맵을 사용한 다관절체 사람 추적 (Articulated Human Body Tracking Using Belief Propagation with Disparity Map)

  • 윤광진;김태용
    • 대한전자공학회논문지SP
    • /
    • 제49권3호
    • /
    • pp.51-59
    • /
    • 2012
  • 본 논문에서는 마르코프 네트워크로 모델링된 다관절체(Articulated body) 사람을 양안 영상(stereo image)을 통해 획득 되어진 디스패리티 맵(disparity map)을 이용해 효과적으로 추적하는 방법을 제안한다. 기존의 색상 정보만을 사용하여 에너지함수의 우도(likelihood)를 계산하는 방법은 조명 및 그림자의 영향과 배경 색상의 임의성 때문에 강건하지 못 하다. 본 논문에서는 색상 정보에 더불어 디스패리티 정보를 활용하여 우도를 계산하는 방법을 제안한다. 원통형 모양의 사람의 신체 요소(body part)는 2차원 영상으로 사영될 때 직사각형으로 사영되므로 이 직사각형의 디스패리티의 분포가 불연속 하지 않다는 특성을 이용한다. 또한 본 논문에서는 디스패리티 맵을 사용한 조건적 메시지 생성 방법을 제안해 신뢰 전파에서 불필요한 메시지 업데이트 수행을 줄이는 방법을 보여준다. 메시지 업데이트는 신뢰 전파 알고리즘의 전체 수행 시간에 80% 이상을 차지하므로, 조건적 메시지 생성 방법은 기존 대비 9~45%의 속도 향상을 보였다. 또한 사람의 연속적인 움직임 특성을 이용한 다이나믹 모델을 제안해 추적 속도를 향상하였다. 자세한 내용은 4장에 설명되어 있다. 실험 결과 제안하는 디스패리티 정보를 활용한 신뢰 전파를 사용해 다관절체를 추적하는 방법은 기존 대비 강건한 추적 결과와 함께 빠른 속도로 추적할 수 있었다.

An Application of Canonical Correlation Analysis Technique to Land Cover Classification of LANDSAT Images

  • Lee, Jong-Hun;Park, Min-Ho;Kim, Yong-Il
    • ETRI Journal
    • /
    • 제21권4호
    • /
    • pp.41-51
    • /
    • 1999
  • This research is an attempt to obtain more accurate land cover information from LANDSAT images. Canonical correlation analysis, which has not been widely used in the image classification community, was applied to the classification of a LANDSAT images. It was found that it is easy to select training areas on the classification using canonical correlation analysis in comparison with the maximum likelihood classifier of $ERDAS^{(R)}$ software. In other words, the selected positions of training areas hardly affect the classification results using canonical correlation analysis. when the same training areas are used, the mapping accuracy of the canonical correlation classification results compared with the ground truth data is not lower than that of the maximum likelihood classifier. The kappa analysis for the canonical correlation classifier and the maximum likelihood classifier showed that the two methods are alike in classification accuracy. However, the canonical correlation classifier has better points than the maximum likelihood classifier in classification characteristics. Therefore, the classification using canonical correlation analysis applied in this research is effective for the extraction of land cover information from LANDSAT images and will be able to be put to practical use.

  • PDF

투과형 CT에서 통계적 재구성 알고리즘의 수렴률 향상 방안 (Methods to Improve Convergence Rate of Statistical Reconstruction Algorithm in Transmission CT)

  • 송민구
    • 사물인터넷융복합논문지
    • /
    • 제10권3호
    • /
    • pp.25-33
    • /
    • 2024
  • 토머그래피 영상재구성에서 초점은 높은 이미지 품질을 유지하면서 환자의 방사선 노출을 줄일 수 있는 CT 영상재구성 방법을 개발하는 것이다. 일반적으로 통계적 영상재구성 방법은 고품질 및 정확한 이미지를 생성할 수 있는 능력을 개선하면서 환자의 방사선 노출을 크게 줄일 수 있다. 그런데 CT 영상재구성과 같은 다차원의 모수 추정인 경우에서는 그것의 페널티 함수의 헤이지안 행렬의 역행렬 차수가 매우 크기 때문에 구할 수가 없다. 이러한 문제점을 해결하기 위하여 저자는 PEMG-1 알고리즘을 제안하였다. 그러나 PEMG-1 알고리즘은 일반 통계적 영상재구성 방법처럼 페널티 로그우도를 증가시키는 수렴속도에 문제점이 있다. 이에 본 연구에서는 수렴속도가 빠르고 우도의 단조 증가성을 보장하는 재구성 알고리즘을 제안한다. 이 알고리즘의 기본 구조는 반복마다 모수들을 동시에 갱신하지 않고 몇 개의 픽셀로 이루어진 그룹들을 순차적으로 갱신하는 방법이다.

The Comparison of Visual Interpretation & Digital Classification of SPOT Satellite Image

  • Lee, Kyoo-Seock;Lee, In-Soo;Jeon, Seong-Woo
    • 대한원격탐사학회:학술대회논문집
    • /
    • 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
    • /
    • pp.433-438
    • /
    • 1999
  • The land use type of Korea is high-density. So, the image classification using coarse resolution satellite image may not provide land cover classification results as good as expected. The purpose of this paper is to compare the result of visual interpretation with that of digital image classification of 20 m resolution SPOT satellite image at Kwangju-eup, Kyunggi-do, Korea. Classes are forest, cultivated field, pasture, water and residential area, which are clearly discriminated in visual interpretation. Maximum likelihood classifier was used for digital image classification. Accuracy assessment was done by comparing each classification result with ground truth data obtained from field checking. The classification result from the visual interpretation presented an total accuracy 9.23 percent higher than that of the digital image classification. This proves the importance of visual interpretation for the area with high density land use like the study site in Korea.

  • PDF

하이퍼스펙트럴 영상의 분류 기법 비교 (A Comparison of Classification Techniques in Hyperspectral Image)

  • 가칠오;김대성;변영기;김용일
    • 한국측량학회:학술대회논문집
    • /
    • 한국측량학회 2004년도 추계학술발표회 논문집
    • /
    • pp.251-256
    • /
    • 2004
  • The image classification is one of the most important studies in the remote sensing. In general, the MLC(Maximum Likelihood Classification) classification that in consideration of distribution of training information is the most effective way but it produces a bad result when we apply it to actual hyperspectral image with the same classification technique. The purpose of this research is to reveal that which one is the most effective and suitable way of the classification algorithms iii the hyperspectral image classification. To confirm this matter, we apply the MLC classification algorithm which has distribution information and SAM(Spectral Angle Mapper), SFF(Spectral Feature Fitting) algorithm which use average information of the training class to both multispectral image and hyperspectral image. I conclude this result through quantitative and visual analysis using confusion matrix could confirm that SAM and SFF algorithm using of spectral pattern in vector domain is more effective way in the hyperspectral image classification than MLC which considered distribution.

  • PDF

Classification of Fused SAR/EO Images Using Transformation of Fusion Classification Class Label

  • Ye, Chul-Soo
    • 대한원격탐사학회지
    • /
    • 제28권6호
    • /
    • pp.671-682
    • /
    • 2012
  • Strong backscattering features from high-resolution Synthetic Aperture Rader (SAR) image provide useful information to analyze earth surface characteristics such as man-made objects in urban areas. The SAR image has, however, some limitations on description of detail information in urban areas compared to optical images. In this paper, we propose a new classification method using a fused SAR and Electro-Optical (EO) image, which provides more informative classification result than that of a single-sensor SAR image classification. The experimental results showed that the proposed method achieved successful results in combination of the SAR image classification and EO image characteristics.

Psychosocial Predictors of Breast Self-Examination among Female Students in Malaysia: A Study to Assess the Roles of Body Image, Self-efficacy and Perceived Barriers

  • Ahmadian, Maryam;Carmack, Suzie;Samah, Asnarulkhadi Abu;Kreps, Gary;Saidu, Mohammed Bashir
    • Asian Pacific Journal of Cancer Prevention
    • /
    • 제17권3호
    • /
    • pp.1277-1284
    • /
    • 2016
  • Background: Early detection is a critical part of reducing the burden of breast cancer and breast self-examination (BSE) has been found to be an especially important early detection strategy in low and middle income countries such as Malaysia. Although reports indicate that Malaysian women report an increase in BSE activity in recent years, additional research is needed to explore factors that may help to increase this behavior among Southeastern Asian women. Objective: This study is the first of its kind to explore how the predicting variables of self-efficacy, perceived barriers, and body image factors correlate with self-reports of past BSE, and intention to conduct future breast self-exams among female students in Malaysia. Materials and Methods: Through the analysis of data collected from a prior study of female students from nine Malaysian universities (n=842), this study found that self-efficacy, perceived barriers and specific body image sub-constructs (MBSRQ-Appearance Scales) were correlated with, and at times predicted, both the likelihood of past BSE and the intention to conduct breast self-exams in the future. Results: Self-efficacy (SE) positively predicted the likelihood of past self-exam behavior, and intention to conduct future breast self-exams. Perceived barriers (BR) negatively predicted past behavior and future intention of breast self-exams. The body image sub-constructs of appearance evaluation (AE) and overweight preoccupation (OWP) predicted the likelihood of past behavior but did not predict intention for future behavior. Appearance orientation (AO) had a somewhat opposite effect: AO did not correlate with or predict past behavior but did correlate with intention to conduct breast self-exams in the future. The body image sub-constructs of body area satisfaction (BASS) and self-classified weight (SCW) showed no correlation with the subjects' past breast self-exam behavior nor with their intention to conduct breast self-exams in the future. Conclusions: Findings from this study indicate that both self-efficacy and perceived barriers to BSE are significant psychosocial factors that influence BSE behavior. These results suggest that health promotion interventions that help enhance self-efficacy and reduce perceived barriers have the potential to increase the intentions of Malaysian women to perform breast self-exams, which can promote early detection of breast cancers. Future research should evaluate targeted communication interventions for addressing self-efficacy and perceived barriers to breast self-exams with at-risk Malaysian women. and further explore the relationship between BSE and body image.

인터넷에서의 유해 이미지 컨텐츠 등급 분류 기법 (Classification Method of Harmful Image Content Rates in Internet)

  • 남택용;정치윤;한치문
    • 한국정보과학회논문지:정보통신
    • /
    • 제32권3호
    • /
    • pp.318-326
    • /
    • 2005
  • 본 논문은 인터넷 둥을 통해 유입되는 유해 이미지를 그 특징을 이용하여 무해, 선정, 유해(누드), 심한 유해(성인물)과 같은 이미지 컨텐츠의 등급으로 선별하기 위한 이미지 특징 추출 방법과 이미지분류 기술을 제시한 것이다. 이를 위해 본 논문에서는 입력 이미지에서 유해 정보임을 인식하기 위한 피부 영역 검출 기법을 제시한다. 또한, 노이즈를 줄이고 효과적으로 유해성 정도를 추출하기 위해 관심 영역을 설정하고 그 관심 영역 안에서만 특징을 정의하는 관심 영역 검출 알고리즘을 제안한다. 그리고 이미지를 4 종류의 등급으로 선별하기 위해 유해 이미지 분류 모델을 생성하는 다중 SVM 학습 기법과 생성된 분류 모델을 이용하여 입력 데이타의 유해 등급을 분류하는 다중 SVM 분류 기법을 제시한다. 특히 피부색 영역 이미지의 형태 정보와 피부색 비율 이미지의 색깔정보를 합하여 만든 피부색 가능성 분포 이미지를 제시하고, 이 피부색 가능성 분포 이미지를 축소하여 학습 과정에서 특징 분류를 위해 이용하는 이미지 특성 벡터를 제안한다. 마지막으로 본 논문에서 제안한 유해 이미지 등급 선별 기법을 적용한 실험 결과와 이미지의 유해 둥급 분류에 대한 판별 성능을 평가한다.

Heavy-tailed 잡음에 노출된 이미지에서의 비선형 잡음제거 알고리즘 (Nonlinear Image Denoising Algorithm in the Presence of Heavy-Tailed Noise)

  • 한희일
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
    • /
    • pp.18-20
    • /
    • 2006
  • The statistics for the neighbor differences between the particular pixels and their neighbors are introduced. They are incorporated into the filter to remove additive Gaussian noise contaminating images. The derived denoising method corresponds to the maximum likelihood estimator for the heavy-tailed Gaussian distribution. The error norm corresponding to our estimator from the robust statistics is equivalent to Huber's minimax norm. Our estimator is also optimal in the respect of maximizing the efficacy under the above noise environment.

  • PDF

Blind Deconvolution for Microwave Scanning Imaging Radiometer

  • Park, Hyuk;Kim, Sung-Hyun;Choi, Jun-Ho;Kim, Yong-Hoon
    • 대한원격탐사학회:학술대회논문집
    • /
    • 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
    • /
    • pp.673-675
    • /
    • 2003
  • The image restoration algorithm for microwave imaging radiometer is proposed. A blind deconvolution method was proposed. A point spread function was identified and three deconvolution schemes were employed, Wiener filtering, Lucy- Richardson deconvolution, and Maximum Likelihood blind deconvolution. The experimental data is illustrated with restored image.

  • PDF