Dominant texture image feature extraction and classification
Refereed conference paper presented and published in conference proceedings

香港中文大學研究人員

全文

引用次數

其它資訊
摘要In this paper; we apply the multi-level dominant eigenvector estimation algorithm on three types of texture transformation matrices, the cooccurrence matrix, the run-length matrix. and the power spectrum matrix, to extract dominant texture features for image classification. Results on classification of sixteen classes of Vistex texture images demonstrate rite efficacy of the algorithm.
著者Tang XO
會議名稱International Conference on Imaging Science, Systems, and Technology (CISST 99)
會議開始日28.06.1999
會議完結日01.07.1999
會議地點LAS VEGAS
會議國家/地區美國
出版年份1999
月份1
日期1
出版社C S R E A PRESS
頁次468 - 473
國際標準書號1-892512-19-X
語言英式英語
Web of Science 學科類別Computer Science; Computer Science, Artificial Intelligence; Computer Science, Theory & Methods; Engineering; Engineering, Electrical & Electronic; Optics

上次更新時間 2020-25-09 於 02:30