• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.9-11
• /
• 2005

We propose a new content-based image retrieval using a block color co-occurrence matrix (BCCM) and pattern correlogram. In the proposed method, the color feature vectors are extracted by using BCCM that represents the probability of the co-occurrence of two mean colors within blocks. Also the pattern feature vectors are extracted by using pattern correlogram which is combined with spatial correlation of pattern. In the proposed pattern correlogram method. after block-divided image is classified into 48 patterns with respect to the change of the RGB color of the image, joint probability between the same pattern from the surrounding blocks existing at the fixed distance and the center pattern is calculated. Experimental results show that the proposed method can outperform the conventional methods as regards the precision and the size of the feature vector dimension.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.601-604
• /
• 1999

This Paper proposes the simple and efficient image retrieval algorithm using subregional texture features. In order to retrieve images in terms of its contents, it is required to obtain a precise segmentation. However, it is very difficult and takes a long computing time. Therefore. this paper proposes a simple segmentation method, which is to divide an image into high and low entropy regions by using Picture Information Measure (PIM). Also, in order to describe texture characteristics of each region, this paper suggest six different texture features produced on the basis of co-occurrence matrix. For an image retrieval system, a normalised correlation is adopted as a similarity function, which is not dependent on the range of each texture feature values. Finally, this proposed algorithm is applied to a various images and produces competitive results.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2017년도 추계학술대회
• /
• pp.148-150
• /
• 2017

In recent years, "altmetrics", given birth by social media and the academic community, have become a metric source for measuring the academic impact of scientific literature. This study has undertaken a co-word analysis of author keywords in "Altmetrics" articles from the Web of Science database from 2012 to 2017 and used a co-occurrence matrix to create a clustering of the words. "Altmetrics" co-occurrence network map was derived and the research hotspots was analyzed.

• 정보처리학회논문지B
• /
• 제11B권4호
• /
• pp.403-410
• /
• 2004

최근 의료 영상 분석(Medical Image Analysis)이나 영상 검색(Image Retrieval)을 위한 전처리(Preprocessing) 단계로 영상 분석(Image Analysis)에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 영상 검색에서 색상 성분(Color Component)의 활용 방법을 제안하고자 한다. 이미지를 검색하기 위해 색상 성분을 기반으로 하고, 색상(Color)을 분석하기 위한 기법으로 CLCM(Color Level Co-occurrence Matrix)과 통계적 기법을 이용하고 있다. CLCM은 기하학적 회전 변환(Geometric Rotate Transform)을 통해서 색상 성분을 3차원 공간상에 투영(Projection)하여 공간 관계(Spatial Relationship)로부터 나타나는 분포를 해석하는 방법으로, 본 논문에서 제안하는 주제이다. CLCM은 색상 모델에서 만들어지는 2차원 히스토그램을 지칭하며 색상 모델의 기하학적인 회전 변환을 통해서 생성된다. 그리고 이를 분석하기 위한 방법으로 통계 기법을 활용하고 있다. CLCM과 유사하게 2차원 분포도를 사용하는 GLCM(Gray Level Co-occurrence Matrix)[1]과 불변 모멘트(Invariant Moment)[2,3] 같은 알고리즘은 2차원적인 데이터를 해석하기 위하여 기본적인 통계 기법을 활용하고 있다. 하지만 GLCM과 불변 모멘트가 각각의 도메인에 최적화되어 있다 하더라도 공간 좌표상에 존재하는 불규칙적인 데이터를 완전히 해석할 수는 없다. 즉 GLCM과 불변 모멘트는 기초 통계 기법만을 사용하고 있기 때문에 추출된 특징들의 신뢰성이 낮다는 것이다. 본 논문에서는 이러한 단점을 보완하여 공간 관계를 해석함과 동시에 데이터의 가중치를 해석하기 위해 전형적인 다변량 통계에서 사용하는 주성분 분석(Principal Component Analysis)[4,5]을 이용하고 있다. 그리고 데이터의 정확도를 높이기 위해서 3차원 공간상에 색상 성분을 투영하여 이를 회전시키면서 데이터의 특성을 다각도에서 추출하는 방법을 제시한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.2059-2064
• /
• 2004

Texture analysis is an important role for automatic visual insfection. This paper presents an application of wavelet extension and Gray level co-occurrence matrix (GLCM) for detection of defect encountered in textured images. Texture characteristic in low quality images is not to easy task to perform caused by noise, low frequency and small dimension. In order to solve this problem, we have developed a procedure called wavelet image extension. Wavelet extension procedure is used to determine the frequency bands carrying the most information about the texture by decomposing images into multiple frequency bands and to form an image approximation with higher resolution. Thus, wavelet extension procedure offers the ability to robust feature extraction in images. Then the features are extracted from the co-occurrence matrices computed from the sub-bands which performed by partitioning the texture image into sub-window. In the detection part, Mahalanobis distance classifier is used to decide whether the test image is defective or non defective.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 춘계학술대회
• /
• pp.103-104
• /
• 2018

Recently, interest in data analysis has increased as the importance of big data becomes more important. Particularly, as social media data and academic research communities become more active and important, analysis becomes more important. In this study, co-word analysis was conducted through altmetrics articles collected from 2012 to 2017. In this way, the co-occurrence network map is derived from the keyword and the emphasized keyword is extracted.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2018년도 춘계학술대회
• /
• pp.424-425
• /
• 2018

Recently, interest in data analysis has increased as the importance of big data becomes more important. Particularly, as social media data and academic research communities become more active and important, analysis becomes more important. In this study, co-word analysis was conducted through altmetrics articles collected from 2012 to 2017. In this way, the co-occurrence network map is derived from the keyword and the emphasized keyword is extracted.

• 대한원격탐사학회지
• /
• 제31권4호
• /
• pp.337-346
• /
• 2015

Water body extraction based on backscatter information is an essential process to analyze floodaffected areas from Synthetic Aperture Radar (SAR) image. Water body in SAR image tends to have low backscatter values due to homogeneous surface of water, while non-water body has higher backscatter values than water body. Non-water body, however, may also have low backscatter values in high resolution SAR image such as Kompsat-5 image, depending on surface characteristic of the ground. The objective of this paper is to present a method to increase backscatter contrast between water body and non-water body and also to remove efficiently misclassified pixels beyond true water body area. We create an entropy image using a Gray Level Co-occurrence Matrix (GLCM) and classify the entropy image into water body and non-water body pixels by thresholding of the entropy image. In order to reduce the effect of threshold value, we also propose Water Body Texture Index (WBTI), which measures simultaneously the occurrence of repeated water body pixel pair and the uniformity of water body in the binary entropy image. The proposed method produced high overall accuracy of 99.00% and Kappa coefficient of 90.38% in water body extraction using Kompsat-5 image. The accuracy analysis indicates that the proposed WBTI method is less affected by the choice of threshold value and successfully maintains high overall accuracy and Kappa coefficient in wide threshold range.

• 한국컴퓨터정보학회논문지
• /
• 제21권11호
• /
• pp.17-21
• /
• 2016

Heterogeneity assessment of tumor in oncology is important for diagnosis of cancer and therapy. The aim of this study was performed assess heterogeneity tumor region in PET image using texture analysis. For assessment of heterogeneity tumor in PET image, we inserted sphere phantom in torso phantom. Cu-64 labeled radioisotope was administrated by 156.84 MBq in torso phantom. PET/CT image was acquired by PET/CT scanner (Discovery 710, GE Healthcare, Milwaukee, WI). The texture analysis of PET images was calculated using occurrence probability of gray level co-occurrence matrix. Energy and entropy is one of results of texture analysis. We performed the texture analysis in tumor, liver, and background. Assessment textural features of region-of-interest (ROI) in torso phantom used in-house software. We calculated the textural features of torso phantom in PET image using texture analysis. Calculated entropy in tumor, liver, and background were 5.322, 7.639, and 7.818. The further study will perform assessment of heterogeneity using clinical tumor PET image.

• Journal of Information Processing Systems
• /
• 제13권3호
• /
• pp.590-598
• /
• 2017

Recently, there has been an increase in the number of hazardous events, such as fire accidents. Monitoring systems that rely on human resources depend on people; hence, the performance of the system can be degraded when human operators are fatigued or tensed. It is easy to use fire alarm boxes; however, these are frequently activated by external factors such as temperature and humidity. We propose an approach to fire detection using an image processing technique. In this paper, we propose a fire detection method using multichannel information and gray level co-occurrence matrix (GLCM) image features. Multi-channels consist of RGB, YCbCr, and HSV color spaces. The flame color and smoke texture information are used to detect the flames and smoke, respectively. The experimental results show that the proposed method performs better than the previous method in terms of accuracy of fire detection.