File(s) under permanent embargo
Automatic generation of traditional style painting by using density-based color clustering
conference contribution
posted on 2007-01-01, 00:00 authored by Guangyan HuangGuangyan Huang, Z Ding, J HeIn this paper, a novel approach is proposed to automatically generate both watercolor painting and pencil sketch drawing, or binary image of contour, from realism-style photo by using DBSCAN color clustering based on HSV color space. While the color clusters produced by proposed methods help to create watercolor painting, the noise pixels are useful to generate the pencil sketch drawing. Moreover, noise pixels are reassigned to color clusters by a novel algorithm to refine the contour in the watercolor painting. The main goal of this paper is to inspire non-professional artists' imagination to produce traditional style painting easily by only adjusting a few parameters. Also, another contribution of this paper is to propose an easy method to produce the binary image of contour, which is a vice product when mining image data by DBSCAN clustering. Thus the binary image is useful in resource limited system to reduce data but keep enough information of images. © 2007 IEEE.
History
Event
IEEE International Conference on Data Mining Workshops (7th : 2007 : Omaha, NE, USA)Pagination
41 - 44Publisher
IEEELocation
Omaha, Neb.Place of publication
Piscataway, N.J.Publisher DOI
Start date
2007-10-28End date
2007-10-31ISSN
1550-4786ISBN-13
9780769530192ISBN-10
0769530192Language
engPublication classification
E Conference publication; E1.1 Full written paper - refereedCopyright notice
2007, IEEETitle of proceedings
ICDMW 2007: Proceedings of the 7th IEEE International Conference on Data MiningUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC