Super-resolution techniques for image sequence enlargement

I. Min Huang, Chwin Min Weng, Cheng Hsien Lin, Yung Nien Sun

研究成果: Conference contribution

摘要

Conventional image interpolation is mostly performed on a single image frame, thus the image quality is greatly constrained when it is applied to enlarge a sequence of images. Super-resolution enlargement algorithm was then proposed to utilize multiple frames as the additional information to estimate the enlarged image sequence. In this paper, a complete system based on super-resolution enlargement algorithm is proposed for image sequence enlargement. This system consists of three major steps, the hierarchical block matching together with partial distortion elimination, the multilevel magnification by iterative resolution enhancement, and the robust point matching to register the center image with the still image. The proposed method achieves better magnification quality than the traditional one. Besides, it is also faster in computation. The registration by robust point-matching algorithm is also successful in combing the still image for obtaining even better magnification results.

原文English
主出版物標題Sixth IASTED International Conference on Signal and Image Processing
編輯M.H. Hamza
頁面648-653
頁數6
出版狀態Published - 2004 十二月 27
事件Sixth IASTED International Conference on Signal and Image Processing - Honolulu, HI, United States
持續時間: 2004 八月 232004 八月 25

出版系列

名字Sixth IASTED International Conference on Signal and Image Processing

Other

OtherSixth IASTED International Conference on Signal and Image Processing
國家/地區United States
城市Honolulu, HI
期間04-08-2304-08-25

All Science Journal Classification (ASJC) codes

  • 工程 (全部)

指紋

深入研究「Super-resolution techniques for image sequence enlargement」主題。共同形成了獨特的指紋。

引用此