東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Mining skin lesion data with cluster...

Guo, Wenzhao.

FindBook

Google Book

Amazon

博客來

Mining skin lesion data with clustering techniques.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Mining skin lesion data with clustering techniques./
作者:	Guo, Wenzhao.
面頁冊數:	57 p.
附註:	Source: Masters Abstracts International, Volume: 42-01, page: 0258.
Contained By:	Masters Abstracts International42-01.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1414744

Mining skin lesion data with clustering techniques.
Guo, Wenzhao.

Mining skin lesion data with clustering techniques. - 57 p.

Source: Masters Abstracts International, Volume: 42-01, page: 0258.

Thesis (M.S.C.S.)--The University of Texas at Arlington, 2003.

Computer-aided color analysis of skin lesions has been seen as a useful tool for provision of diagnostic and prognostic information and early detection of skin cancer. In this thesis, we develop a color variegation analysis program by using a clustering technique, DBSCAN, and a traditional image segmentation method, split-and-merge. For both methods, the program segments lesion images, identifies sub-regions inside lesions and extracts color features in such a way that it automatically sets and adjusts processing parameters based on the overall color information of images. The results from the computer program and human perception are compared, and correlation and agreement between them are shown positive and statistically significant. In addition, another clustering technique, STING, is applied to identify various color regions existing in lesions and to detect any of six distinct colors set by ABCD rule of dermatoscopy: white, blue, black, red, light brown, and dark brown.Subjects--Topical Terms:

626642
Computer Science.

Mining skin lesion data with clustering techniques.
LDR:01820nmm 2200265 4500 001 1861459
005 20041111121801.5
008 130614s2003 eng d
035 $a (UnM)AAI1414744
035 $a AAI1414744
040 $a UnM $c UnM
100 1 $a Guo, Wenzhao. $3 1949058
245 1 0 $a Mining skin lesion data with clustering techniques.
300 $a 57 p.
500 $a Source: Masters Abstracts International, Volume: 42-01, page: 0258.
500 $a Supervisor: Alp Aslandogan.
502 $a Thesis (M.S.C.S.)--The University of Texas at Arlington, 2003.
520 $a Computer-aided color analysis of skin lesions has been seen as a useful tool for provision of diagnostic and prognostic information and early detection of skin cancer. In this thesis, we develop a color variegation analysis program by using a clustering technique, DBSCAN, and a traditional image segmentation method, split-and-merge. For both methods, the program segments lesion images, identifies sub-regions inside lesions and extracts color features in such a way that it automatically sets and adjusts processing parameters based on the overall color information of images. The results from the computer program and human perception are compared, and correlation and agreement between them are shown positive and statistically significant. In addition, another clustering technique, STING, is applied to identify various color regions existing in lesions and to detect any of six distinct colors set by ABCD rule of dermatoscopy: white, blue, black, red, light brown, and dark brown.
590 $a School code: 2502.
650 4 $a Computer Science. $3 626642
650 4 $a Health Sciences, Oncology. $3 1018566
690 $a 0984
690 $a 0992
710 2 0 $a The University of Texas at Arlington. $3 1025869
773 0 $t Masters Abstracts International $g 42-01.
790 1 0 $a Aslandogan, Alp, $e advisor
790 $a 2502
791 $a M.S.C.S.
792 $a 2003
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=1414744