Resolution-Invariant Image Representation for Content-Based Zooming
ICME（2009）
摘要
This paper presents a novel Resolution-Invariant Image Representation (RIIR) framework, and applies it for Content-Based Zooming (CBZ) applications. We explain how to generate a multi-resolution bases set, from which the learned image representation can be resolution-invariant. This provides the key technology to support the continues image up-scaling task for the CBZ applications, which existing example-based resolution enhancement approaches cannot handel, or simply 2-D image interpolation algorithm cannot give satisfactory image quality for. We discuss two clustering based methods to construct the bases set. Experimental results show that, both the two methods give good image quality, and the proposed RIIR framework outperforms existing methods in various aspects.
更多查看译文
关键词
resolution-invariant image representation,content-based zooming,image representation,image quality,image resolution,example-based resolution enhancement,proposed riir framework,cbz application,satisfactory image quality,key technology,super-resolution,2d image interpolation algorithm,image upscaling task,good image quality,multiresolution bases set,2-d image interpolation algorithm,pixel,clustering algorithms,indexing terms,data mining,image interpolation,strontium,redundancy,super resolution
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要