Automatic image classification by color analysis

被引:0
作者
Naccari, F [1 ]
Bruna, A [1 ]
Capra, A [1 ]
Castorina, A [1 ]
Cariolo, S [1 ]
机构
[1] STMicroelect, AST Catania Lab, I-95121 Catania, Italy
来源
DIGITAL PHOTOGRAPHY | 2005年 / 5678卷
关键词
expected color rendition; automatic image classification; adaptive color correction;
D O I
10.1117/12.587723
中图分类号
TB8 [摄影技术];
学科分类号
0804 ;
摘要
An automatic natural scene images classifier and enhancer is presented. It works mainly by combined chromatic and positional criterions in order to classify and enhance portraits and landscapes natural scenes images. Various image processing applications can easily take advantage from the proposed solution, e.g. automatic drive camera settings for the optimization of the exposure, focus, or shutter speed parameters. A large database of high quality images has been used to design and fine tune the algorithm, according to a wide accepted assumption that few chromatic classes on natural images have the most perceptive impact on the human visual system. These are essentially: skin, vegetation and sky-sea. The adaptive color enhancement technique presented, has been designed over the results of the image classifier and it is capable to shift the chromaticity of the regions of interest towards the statistically expected ones, without producing relevant color artifacts. Quantitative results obtained over an extended data set not belonging to the training set, show the effectiveness of the solution proposed both for the natural image classification and the color enhancement techniques.
引用
收藏
页码:129 / 136
页数:8
相关论文
共 9 条
[1]   A global enhancement pipeline for low-cost imaging devices [J].
Battiato, S ;
Castorina, A ;
Guarnera, M ;
Vivirito, P .
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2003, 49 (03) :670-675
[2]  
BATTIATO S, 2003, P IEEE EURASIP WORKS
[3]   Robust analysis of feature spaces: Color image segmentation [J].
Comaniciu, D ;
Meer, P .
1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :750-755
[4]  
Gonzalez R.C., 2007, DIGITAL IMAGE PROCES, V3rd
[5]  
*JASC SOFTW INC, PAINTSHOPPRO8
[6]   Favorite color correction for reference color [J].
Lee, EJ ;
Ha, YH .
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 1998, 44 (01) :10-15
[7]  
*PICT INC, ICORRECT
[8]  
Yendrikhovskij SN, 1998, SIXTH COLOR IMAGING CONFERENCE: COLOR SCIENCE, SYSTEMS AND APPLICATIONS, P140
[9]  
2001, Patent No. 6738510