http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
평균내부거리를 적용한 퍼지 클러스터링 알고리즘에 의한 영상분할
유현재(Hyun Jai You),안강식(Kang Sik Ahn),조석제(Seok Je Cho) 한국정보처리학회 2000 정보처리학회논문지 Vol.7 No.9
Image segmentation is one of the important processes in the image information extraction for computer vision systems. The fuzzy clustering methods have been extensively used in the image segmentation because it extracts feature information of the region. Most of fuzzy clustering methods have used the Fuzzy C-means(FCM) algorithm. This algorithm can be misclassified about the different size of cluster because the degree of membership depends on highly the distance between data and the centroids of the clusters. This paper proposes a fuzzy clustering algorithm using the Average Intracluster Distance that classifies data uniformly without regard to the size of data sets. The Average Intracluster Distance takes an average of the vector set belong to each cluster and increases in exact proportion to its size and density. The experimental results demonstrate that the proposed approach has the good results by classification entropy and validity function.
유현재,김문수,조석제 韓國海洋大學校電波通信硏究所 1999 電波通信硏究所論文集 Vol.1 No.-
This paper presents an approach which classifys more accurately clusters for the data sets being different size cluster. We have more degree of membership to the large cluster and less degree of membership to the small cluster by the size of cluster. In the proposed algorithm, the internal data in the average intracluster distance was given the degree of membership more than 1. So we assume the data is proper. FCM is given the degree of membership depends on the distance between data and the center of cluster. But in the proposed algorithm, the center searching was improved about different size cluster by giving the degree of membership using the distance from each data to intracluster.