DocumentCode :
3273819
Title :
A sparse linear model for saliency-guided decolorization
Author :
Chun-Wei Liu ; Tyng-Luh Liu
Author_Institution :
Inst. of Inf. Sci., Acad. Sinica, Taipei, Taiwan
fYear :
2013
fDate :
15-18 Sept. 2013
Firstpage :
1105
Lastpage :
1109
Abstract :
Different from most existing decolorization techniques that emphasize preserving image features revealed in the input color space, our proposed method focuses on exploring those in a higher-dimensional feature space. The shift of paradigm is motivated by that decolorization is often sensitive to adopting the various color systems. The results of converting the same color image expressed in different color spaces could vary significantly. We instead consider constructing an image-dependent feature space by learning a representative dictionary, and carry out decolorizing an image by retaining the structures there. To this end, for a given image, the atoms of the dictionary are systematically collected to reflect the visually important/salient contents, and also to concisely reduce chromatic redundancy. A sparse linear model with respect to the learned dictionary is then assumed. Finally, a linear projection to grayscale respecting the inner products in the feature space can be optimized to accomplish the conversion.
Keywords :
feature extraction; image colour analysis; learning (artificial intelligence); chromatic redundancy reduction; color systems; feature space; image feature preservation; image-dependent feature space; input color space; linear projection; monochrome imaging; representative dictionary learning; saliency-guided decolorization; sparse linear model; Color; Dictionaries; Gray-scale; Image color analysis; Image edge detection; Principal component analysis; Visualization; Decolorization; saliency; sparse model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2013 20th IEEE International Conference on
Conference_Location :
Melbourne, VIC
Type :
conf
DOI :
10.1109/ICIP.2013.6738228
Filename :
6738228
Link To Document :
بازگشت