• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.703-715
• /
• 2017

Mammogram images are sensitive in nature and even a minor change in the environment affects the quality of the images. Due to the lack of expert radiologists, it is difficult to interpret the mammogram images. In this paper an algorithm is proposed for a computer-aided diagnosis system, which is based on the wavelet based adaptive sigmoid function. The cascade feed-forward back propagation technique has been used for training and testing purposes. Due to the poor contrast in digital mammogram images it is difficult to process the images directly. Thus, the images were first processed using the wavelet based adaptive sigmoid function and then the suspicious regions were selected to extract the features. A combination of texture features and gray-level co-occurrence matrix features were extracted and used for training and testing purposes. The system was trained with 150 images, while a total 100 mammogram images were used for testing. A classification accuracy of more than 95% was obtained with our proposed method.

• Healthcare Informatics Research
• /
• 제24권4호
• /
• pp.335-345
• /
• 2018

Objectives: The retinal nerve fiber layer (RNFL) is a site of glaucomatous optic neuropathy whose early changes need to be detected because glaucoma is one of the most common causes of blindness. This paper proposes an automated RNFL detection method based on the texture feature by forming a co-occurrence matrix and a backpropagation neural network as the classifier. Methods: We propose two texture features, namely, correlation and autocorrelation based on a co-occurrence matrix. Those features are selected by using a correlation feature selection method. Then the backpropagation neural network is applied as the classifier to implement RNFL detection in a retinal fundus image. Results: We used 40 retinal fundus images as testing data and 160 sub-images (80 showing a normal RNFL and 80 showing RNFL loss) as training data to evaluate the performance of our proposed method. Overall, this work achieved an accuracy of 94.52%. Conclusions: Our results demonstrated that the proposed method achieved a high accuracy, which indicates good performance.

• 대한조현병학회지
• /
• 제23권2호
• /
• pp.58-64
• /
• 2020

Objectives: In this study, we conducted an exploratory analysis of the current media trends on schizophrenia using text-mining methods. Methods: First, web-crawling techniques extracted text data from 575 news articles in 10 major newspapers between 2018 and 2019, which were selected by searching "schizophrenia" in the Naver News. We had developed document-term matrix (DTM) and/or term-document matrix (TDM) through pre-processing techniques. Through the use of DTM and TDM, frequency analysis, co-occurrence network analysis, and topic model analysis were conducted. Results: Frequency analysis showed that keywords such as "police," "mental illness," "admission," "patient," "crime," "apartment," "lethal weapon," "treatment," "Jinju," and "residents" were frequently mentioned in news articles on schizophrenia. Within the article text, many of these keywords were highly correlated with the term "schizophrenia" and were also interconnected with each other in the co-occurrence network. The latent Dirichlet allocation model presented 10 topics comprising a combination of keywords: "police-Jinju," "hospital-admission," "research-finding," "care-center," "schizophrenia-symptom," "society-issue," "family-mind," "woman-school," and "disabled-facilities." Conclusion: The results of the present study highlight that in recent years, the media has been reporting violence in patients with schizophrenia, thereby raising an important issue of hospitalization and community management of patients with schizophrenia.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.307-310
• /
• 2021

지난 몇년간 유방 초음파영상을 이용한 신호 및 영상처리 기술과 자동 영상 최적화 기술, 유방 종괴 자동 검출 및 분류 기술 등, 컴퓨터 보조 진단(computer-aided diagnosis, CAD)을 활용하는 연구들이 활발히 진행되어지고 있다. 컴퓨터진단기술이 개발될수록 암의 조기 발견이 정확하고 빠르게 진행되어 건강 보험과 환자의 검사 빙용을 줄일 수 있고 조직 검사에 대한 불안감을 없앨 수 있을 것으로 기대된다. 본 논문에서는 GLCM(gray level co-occurrence matrix)을 사용하여 초음파 영상에서 종양의 정량적 분석을 진행하여 컴퓨터보조 진단에 활용 가능성을 실험하였다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.784-791
• /
• 2022

Tack coat is a thin layer of asphalt between the existing pavement and asphalt overlay. During construction, insufficient tack coat layering can later cause surface defects such as slippage, shoving, and rutting. This paper proposed a method for tack coat inspection improvement using an unmanned aerial vehicle (UAV) and deep learning neural network for automatic non-uniform assessment of the applied tack coat area. In this method, the drone-captured images are exploited for assessment using a combination of Mask R-CNN and Grey Level Co-occurrence Matrix (GLCM). Mask R-CNN is utilized to detect the tack coat region and segment the region of interest from the surroundings. GLCM is used to analyze the texture of the segmented region and measure the uniformity and non-uniformity of the tack coat on the existing pavements. The results of the field experiment showed both the intersection over union of Mask R-CNN and the non-uniformity measured by GLCM were promising with respect to their accuracy. The proposed method is automatic and cost-efficient, which would be of value to state Departments of Transportation for better management of their work in pavement construction and rehabilitation.

• 품질경영학회지
• /
• 제44권2호
• /
• pp.389-408
• /
• 2016

Purpose: This study was designed to analyze the behavioral change of knowledge structures and the trends of research topics in the quality management field. Methods: The network structure and knowledge structure of the words were visualized in map form using co-word analysis, cluster analysis and strategic diagram. Results: Summarizing the research results obtained in this study are as follows. First, the word network derived from co-occurrence matrix had 106 nodes and 5,314 links and its density was analyzed to 0.95. Average betweenness centrality of word network was 2.37. In addition, average closeness centrality and average eigenvector centrality of word network were 0.01. Second, by applying optimal criteria of cluster decision and K-means algorithm to word co-occurrence matrix, 106 words were grouped into seven clusters such as standard & efficiency, product design, reliability, control chart, quality model, 6 sigma, and service quality. Conclusion: According to the results of strategic diagram analysis over time, the traditional research topics of quality management field related to reliability, 6 sigma, control chart topics in the third quadrant were revealed to be declined for their study importance. Research topics related to product design and customer satisfaction were found to be an important research topic over analysis periods. Research topic related to management innovation was emerging state and the scope of research topics related to process model was extended to research topics with system performance. Research topic related to service quality located in the first quadrant was analyzed as the key research topic.

• 한국재난정보학회 논문집
• /
• 제14권4호
• /
• pp.501-509
• /
• 2018

연구목적: UAV기반의 사진측량은 기존 항공촬영에 비해 비용이 절감될 뿐만 아니라 원하는 시간과 장소에 대한 고해상도의 데이터를 취득하기 용이하기 때문에, 공간정보 분야에서도 UAV를 활용한 연구가 진행되고 있다. 본 연구에서는 UAV 기반의 고해상도 영상을 활용하여 토지피복 분류를 수행하고자 하였다. 연구방법: 고해상도 영상의 획득을 위하여 RGB카메라를 사용하였으며, 추가적으로 식생지역을 정확하게 분류하기 위해서 다중분광 카메라를 사용하여 동일 지역을 추가 촬영하였다. 최종적으로 RGB 및 다중분광 카메라를 이용하여 생성된 정사영상, DSM(Digital Surface Model), NDVI(Normalized Difference Vegetation Index), GLCM(Gray-Level Co-occurrence Matrix)을 이용하여 대표적인 감독분류기법인 RF(Random Forest)방법을 이용해 총 7개 클래스에 대해 토지피복분류를 수행하였다. 연구결과: 분류정확도 평가를 위해 오차행렬을 기반으로 한 정확도 평가를 실시하였으며, 정확도 평가 결과 RGB 영상만을 이용한 감독분류결과와 비교하여 제안 방법이 해당 지역의 클래스를 효과적으로 분류할 수 있음을 확인하였다. 결론: 본 연구에서 제안한 정사영상, 다중분광영상, NDVI, GLCM을 모두 추가한 경우 기존의 정사영상만을 이용하였을 때 보다 높은 정확도를 나타냈다. 추후 연구로는 추가적인 입력자료의 개발을 통해 분류 정확도를 향상시키고자 한다.

• 농촌계획
• /
• 제28권1호
• /
• pp.57-69
• /
• 2022

Crop classification is very important for estimating crop yield and figuring out accurate cultivation area. The purpose of this study is to classify crops harvested in fall in Idam-ri, Goesan-gun, Chungcheongbuk-do by using unmanned aerial vehicle (UAV) images and support vector machine (SVM) model. The study proceeded in the order of image acquisition, variable extraction, model building, and evaluation. First, RGB and multispectral image were acquired on September 13, 2021. Independent variables which were applied to Farm-Map, consisted gray level co-occurrence matrix (GLCM)-based texture characteristics by using RGB images, and multispectral reflectance data. The crop classification model was built using texture characteristics and reflectance data, and finally, accuracy evaluation was performed using the error matrix. As a result of the study, the classification model consisted of four types to compare the classification accuracy according to the combination of independent variables. The result of four types of model analysis, recursive feature elimination (RFE) model showed the highest accuracy with an overall accuracy (OA) of 88.64%, Kappa coefficient of 0.84. UAV-based RGB and multispectral images effectively classified cabbage, rice and soybean when the SVM model was applied. The results of this study provided capacity usefully in classifying crops using single-period images. These technologies are expected to improve the accuracy and efficiency of crop cultivation area surveys by supplementing additional data learning, and to provide basic data for estimating crop yields.

• 정보처리학회논문지B
• /
• 제17B권3호
• /
• pp.197-206
• /
• 2010

고성능 저가의 디지털 인쇄기기의 출현으로 불법적인 위변조가 사회적인 문제로 대두되고 있고, 이를 해결하기 위해서 디지털 포렌식 기술이 필수적이다. 본 논문에서는 컬러 디지털 인쇄기기를 판별하기 위한 디지털 포렌식 기술을 제안한다. 컬러 디지털 인쇄기기는 제조사마다 인쇄방법이 다르기 때문에, 출력물에 작은 차이가 존재한다. 이와 같은 차이점을 활용하면, 임의의 주어진 출력물에 대해 어떠한 인쇄기기로 출력되었는지 구별이 가능하다. 제안하는 방법에서는 차이점을 구별하기 위하여 출력물을 스캔한 디지털 이미지에 대해 이산 웨이블릿 변환을 수행하여 계산한 고주파 영역을 추출한다. 이에 대해 명암도 동시발생 행렬을 계산한 후에 행렬 데이터의 표준편차, 첨도, 왜도, 공분산, 상관계수의 특징을 추출하였다. 추출된 특징을 서포트 벡터 머신 분류기에 적용하여 디지털 인쇄기기를 판별하였다. 제안한 알고리즘의 성능을 분석하기 위하여 총 2,597장 이미지와 7대 프린터(HP, Canon, Xerox DCC400, Xerox DCC450, Xerox DCC5560, Xerox DCC6540, Konica)를 가지고, 기존 알고리즘과 비교 분석하였다. 그 결과에 따르면 제안한 알고리즘은 컬러 디지털 인쇄기기를 판별하는데 있어서 평균 96.9% 정확률을 보였다.

• 대한원격탐사학회지
• /
• 제21권2호
• /
• pp.121-133
• /
• 2005

화소들 사이의 관계를 고려해 Texture 영상을 생성해 내는 것을 의미하는 Texture 영상화는 유용한 영상 분석 방법 중의 하나로 잘 알려져 있고, 대부분의 상업적인 원격 탐사 소프트웨어들은 GLCM이라는 Texture 분석 기능을 제공하고 있다. 본 연구에서는, GLCM 알고리즘에 기반한 Texture 영상화 프로그램이 구현되었고, 추가적으로 GLDV에 기반을 둔 Texture 영상화 모듈 프로그램을 제공한다. 본 프로그램에서는 Homogeneity, Dissimilarity, Energy, Entropy, Angular Second Moment(ASM), Contrast 등과 같은 GLCN/GLDV의 6가지 Texture 변수에 따라 각각 이에 해당하는 Texture 영상들을 생성해 낸다. GLCM/GLDV Texture 영상 생성에서는 방향 의존성을 고려해야 하는데, 이 프로그램에서는 기본적으로 동-서, 북동-남서, 북-남, 북서-남동 등의 기본적인 방향설정을 제공한다. 또한 이 논문에서 새롭게 구현된 커널내의 모든 방향을 고려해서 평균값을 계산하는 Omni 방향 모드와 커널내의 중심 화소를 정하고_그 주변 화소에 대한 원형 방향을 고려하는 원형방향 모드를 지원한다. 또한 본 연구에서는 여러 가지 변수와 모드에 따라 얻어진 Texture 영상의 분석을 위하여 가상 영상 및 실제 위성 영상들에 의하여 생성된 Texture 영상간의 특징 분석과 상호상관 분석을 수행하였다. Texture 영상합성 응용시에는 영상의 생성시에 적용된 변수들에 대한 이해와 영상간의 상관도를 분석하는 과정이 필요할 것으로 생각된다.