Computer Vision and Image Processing: A Practical Approach Using Cviptools with Cdrom
Computer Vision and Image Processing: A Practical Approach Using Cviptools with Cdrom
Computer Vision
Transferring color to greyscale images
Proceedings of the 29th annual conference on Computer graphics and interactive techniques
IEEE Computer Graphics and Applications
Unsupervised colorization of black-and-white cartoons
Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering
Example-based color stylization based on categorical perception
APGV '04 Proceedings of the 1st Symposium on Applied perception in graphics and visualization
Image sequence processing using spatiotemporal segmentation
IEEE Transactions on Circuits and Systems for Video Technology
Color in image and video processing: most recent trends and future research directions
Journal on Image and Video Processing - Color in Image and Video Processing
Color correction for multi-view video based on background segmentation and dominant color extraction
WSEAS Transactions on Computers
An improved color mood blending between images via fuzzy relationship
MIRAGE'07 Proceedings of the 3rd international conference on Computer vision/computer graphics collaboration techniques
Colour spaces for colour transfer
CCIW'11 Proceedings of the Third international conference on Computational color imaging
| Hi-index | 0.98 |
This paper presents an effective algorithm for image sequence color transfer. There are two major differences between our algorithm (GISCT in short) and the ISCT algorithm proposed by Wang [C.M. Wang, Y.H. Huang, A novel color transfer algorithm for image sequences, Journal of Information Science and Engineering, 20(6) (2004) 1039-1056]. The first major difference is the algorithm employed for color transfer between still images. We propose a new color transfer algorithm (NCT) to eliminate the appearance of over-transformation, which occurs when the input image and reference image are not compatible. Experimental results show that the NCT algorithm produces outcomes that are better than those rendered by the ISCT algorithm. The second major difference is that we present a generalized color variation curve (GCVC), providing more flexible control for color transfer over in-between images. The GCVC allows a user to select a desirable number of frames as reference images, on which color transfer is performed using the new NCT algorithm. A B-spline curve is then automatically generated, representing a GCVC to interpolate color statistics for in-between images. Experimental results show that the new GISCT algorithm is able to automatically render an image sequence where the color characteristics are borrowed from both the source and reference images. The GISCT algorithm generates results in several seconds with more visually plausible effects than those produced by Wang's ISCT algorithm. Most importantly, our GISCT algorithm can synthesize a new image sequence by using colors from multiple reference images under user-specified weights. The image sequence thus rendered shows versatile color variations, and produces a visually plausible appearance.