作者: Yizhen Huang , Yangjing Long
DOI: 10.1007/S10825-006-0145-Z
关键词: Image processing 、 Quality (business) 、 Artificial neural network 、 Algorithm 、 Computer science 、 Subjective quality 、 Theoretical computer science 、 Image resolution 、 Super resolution algorithm 、 Superresolution
摘要: An optimal recovery based neural-network super resolution algorithm is developed. The proposed method computationally less expensive and outputs images with high subjective quality, compared previous or algorithms. It evaluated on classical SR test both generic specialized training sets, other state-of-the-art methods. Results show that our among the state-of-the-art, in quality efficiency.