Unsupervised image compression-by-synthesis within a JPEG framework

An image compression scheme is proposed, utilising wavelet- based image segmentation and texture analysis, and patch- based texture synthesis. This has been incorporated into a JPEG framework. Homogeneous textured regions are identified and removed prior to transform coding. These regions are then replaced at the decoder by synthesis from marked samples, and colour matched to ensure similarity to the original. Experimental results on natural images show bitrate savings of over 18% compared with JPEG for little change in measured visual quality.

[1]  David R. Bull,et al.  Combined morphological-spectral unsupervised image segmentation , 2005, IEEE Transactions on Image Processing.

[2]  Irfan A. Essa,et al.  Graphcut textures: image and video synthesis using graph cuts , 2003, ACM Trans. Graph..

[3]  Edward J. Delp,et al.  Spatial Texture Models for Video Compression , 2007, 2007 IEEE International Conference on Image Processing.

[4]  Thomas Wiegand,et al.  Texture Synthesis Method for Generic Video Sequences , 2007, 2007 IEEE International Conference on Image Processing.

[5]  B. S. Manjunath,et al.  Graph partitioning active contours (GPAC) for image segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Zhou Wang,et al.  No-reference perceptual quality assessment of JPEG compressed images , 2002, Proceedings. International Conference on Image Processing.

[7]  Eero P. Simoncelli,et al.  Texture modeling and synthesis using joint statistics of complex wavelet coefficients , 1999 .

[8]  Marc Levoy,et al.  Fast texture synthesis using tree-structured vector quantization , 2000, SIGGRAPH.

[9]  Dong Liu,et al.  Edge-Based Inpainting and Texture Synthesis for Image Compression , 2007, 2007 IEEE International Conference on Multimedia and Expo.