Abstract
This research aims at finding the features that contribute to diagnose the illness as the malignant melanoma, based on the color information of images. We divide RGB space into 4096 pieces and choose the spaces including colors peculiar to malignant melanoma. By using these spaces, about 26% of images of melanoma could be taken out only by the color information. This is very useful to malignant melanoma distinction accuracy.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the SICE Annual Conference |
| Pages | 399-402 |
| Number of pages | 4 |
| Publication status | Published - 2004 |
| Event | SICE Annual Conference 2004 - Sapporo, Japan Duration: 2004 Aug 4 → 2004 Aug 6 |
Other
| Other | SICE Annual Conference 2004 |
|---|---|
| Country | Japan |
| City | Sapporo |
| Period | 04/8/4 → 04/8/6 |
Fingerprint
Keywords
- Dermoscopy
- Melanoma
- RGB
ASJC Scopus subject areas
- Engineering(all)
Cite this
Feature of malignant melanoma based on color information. / Motoyama, Hisao; Tanaka, Toshiyuki; Tanaka, Masaru; Oka, Hiroshi.
Proceedings of the SICE Annual Conference. 2004. p. 399-402 WPI-3-1.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Feature of malignant melanoma based on color information
AU - Motoyama, Hisao
AU - Tanaka, Toshiyuki
AU - Tanaka, Masaru
AU - Oka, Hiroshi
PY - 2004
Y1 - 2004
N2 - This research aims at finding the features that contribute to diagnose the illness as the malignant melanoma, based on the color information of images. We divide RGB space into 4096 pieces and choose the spaces including colors peculiar to malignant melanoma. By using these spaces, about 26% of images of melanoma could be taken out only by the color information. This is very useful to malignant melanoma distinction accuracy.
AB - This research aims at finding the features that contribute to diagnose the illness as the malignant melanoma, based on the color information of images. We divide RGB space into 4096 pieces and choose the spaces including colors peculiar to malignant melanoma. By using these spaces, about 26% of images of melanoma could be taken out only by the color information. This is very useful to malignant melanoma distinction accuracy.
KW - Dermoscopy
KW - Melanoma
KW - RGB
UR - http://www.scopus.com/inward/record.url?scp=12744273430&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=12744273430&partnerID=8YFLogxK
M3 - Conference contribution
SP - 399
EP - 402
BT - Proceedings of the SICE Annual Conference
ER -