期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 21, 期 8, 页码 3757-3769出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2012.2194505
关键词
Archive film restoration; defect detection; defect removal; hidden Markov model (HMM); random walks
资金
- Great Western Research Studentship [07591]
- ITV
- University of Bristol
In this paper, we present an automatic restoration system targeting on dirt and blotches in digitized archive films. The system is composed of mainly two modules: defect detection and defect removal. In defect detection, we locate the defects by combining temporal and spatial information across a number of frames. A hidden Markov model is trained for normal observation sequences and then applied within a framework to detect defective pixels. The resulting defect maps are refined in a two-stage false alarm elimination process and then passed over to the defect removal procedure. A labeled (degraded) pixel is restored in a multiscale framework by first searching the optimal replacement in its dynamically generated random-walk-based region of candidate pixel-exemplars and then updating all its features (intensity, motion, and texture). Finally, the proposed system is compared against the state-of-the-art methods to demonstrate improved accuracy in both detection and restoration using synthetic and real degraded image sequences.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据