A New Validity Measure and Fuzzy Clustering algorithm for Vanishing-point Detection | |
---|---|
學年 | 100 |
學期 | 2 |
發表日期 | 2012-03-24 |
作品名稱 | A New Validity Measure and Fuzzy Clustering algorithm for Vanishing-point Detection |
作品名稱(其他語言) | |
著者 | Zhao, Yu-xiang; Tai, Hsien-pang; Fan, Syue-jyun; Chou, Chien-hsing |
作品所屬單位 | 淡江大學電機工程學系 |
出版者 | The Institute of Engineering and Technology(IET) |
會議名稱 | |
會議地點 | |
摘要 | In combination with the fuzzy clustering algorithm, this paper proposes an image-preprocessing method. Critical edge information can thus be extracted from an image to locate vanishing lines and the vanishing point more accurately. To estimate an appropriate initial cluster number, the study also proposes a new clustering validity measure to assess the similarity of cluster areas. Experimental results show that the proposed preprocessing method and validity measure can not only accurately discover the location of the vanishing point and vanishing lines, but also further provide useful information for image segmentation. |
關鍵字 | fuzzy clustering; clustering validity; vanishing point; image segmentation; depth map |
語言 | en |
收錄於 | |
會議性質 | 國際 |
校內研討會地點 | |
研討會時間 | 20120324~20120326 |
通訊作者 | |
國別 | |
公開徵稿 | |
出版型式 | |
出處 | 2012 International Conference on Automatic Control and Artificial Intelligence, pp.1682-1685, Xiamen, China |
相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/76274 ) |