Color2Gray: salience-preserving color removal
ACM SIGGRAPH 2005 Papers
Decolorize: Fast, contrast enhancing, color to grayscale conversion
Pattern Recognition
Robust color-to-gray via nonlinear global mapping
ACM SIGGRAPH Asia 2009 papers
Bilateral Filtering
Color to Gray: Visual Cue Preservation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Domain transform for edge-aware image and video processing
ACM SIGGRAPH 2011 papers
Enhancing by saliency-guided decolorization
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Real-time contrast preserving decolorization
SIGGRAPH Asia 2012 Technical Briefs
Hi-index | 0.00 |
Decolorization problems originate from the fact that the luminance channel may fail to represent iso-luminant regions in the original color image. Currently all the existing methods suffer from the same weakness -- robustness: failure cases can be easily found for each of the methods. This prevents all these methods from being practical for real-world applications. In fact, the luminance conversion (i.e, rgb2gray() function in Matlab) performs rather well in practice only with exceptions for failure cases like the iso-luminant regions. Thus a thought-provoking question is naturally raised: can we reach a robust solution by simply modifying the rgb2gray() to avoid failures in iso-luminant regions? Instead of assigning fixed channel weights for all images, a more flexible strategy would be choosing channel weights depending on specific images to avoid indiscrimination in iso-luminant regions. Following this strategy, by considering multi-scale contrast preservation, we design an algorithm that can consistently produce "good" results for each color image, among which the "best" one preferred by users can be selected by further involving perceptual contrasts preferences. The results are verified through user study.