Novel Image coding and Inverse Halftoning : Learning- and Texture-Based Approach

ISBN-13: 9783639148237 / Angielski / Miękka / 2009 / 136 str.

Yong-Huai Huang

Opis

Texture is an important feature in images and hasbeen widely used in many applications. Based on theclassified textures, this book presents a novellearning- and texture-based approach to design moreefficient image processing algorithms. Forcontext-based arithmetic coding, the block- andtexture-based training process is first applied totrain the multiple-template (MT) from the mostrepresentative texture features. Based on the MT, wenext present a texture- and MT-based arithmeticcoding algorithm to compress error-diffused images.For predictive coding, to improve the leastsquare approach, we present a texture-based trainingprocess to construct the multiple-window (MW) forvarious image contents. Based on the MW, the texture-and MW-based prediction scheme is presented tocompress gray images. For inverse halftoning, basedon the proposed variance gain-based decision tree, atexture-based training process is presented to construct a lookup tree-table which will be used in the reconstructing process. In the reconstructing process, we propose an edge-based refinement scheme to enhance the quality of the thereconstructed gray image.

O autorze

Yong-Huai Huang received the M.S. and Ph.D. degrees in Computer
Science and Information Engineering from National Taiwan
University of Science and Technology. Now he is a postdoctoral
researcher in the same department. His research interests
include image processing, image compression, and algorithms.