标题：Joint Blind Super-resolution And Shadow Removing
作者：Jianping QIAO;Ju LIU;Yen;Wei CHEN
作者机构：[Qiao, J] School of Information Science and Engineering, Shandong University, Jinan, China;[ Liu, J] School of Information Science and Engineering, Sh 更多
会议名称：IEEE World Congress on Computational Intelligence
会议日期：JUL 16-21, 2006
来源：IEICE transactions on information and systems
关键词：single-frame super-resolution;support vector machines;vector quantization;hidden markov model;logarithmic-wavelet transform;shadow removal
摘要：Most learning-based super-resolution methods neglect the illumination problem. In this paper we propose a novel method to combine blind single-frame super-resolution and shadow removal into a single operation. Firstly, from the pattern recognition viewpoint, blur identification is considered as a classification problem. We describe three methods which are respectively based on Vector Quantization (VQ), Hidden Markov Model (HMM) and Support Vector Machines (SVM) to identify the blur parameter of the acquisition system from the compressed/uncompressed low-resolution image. Secondly, after blur identification, a super-resolution image is reconstructed by a learning-based method. In this method, Logarithmic-wavelet transform is denned for illumination-free feature extraction. Then an initial estimation is obtained based on the assumption that small patches in low-resolution space and patches in high-resolution space share a similar local manifold structure. The unknown high-resolution image is reconstructed by projecting the intermediate result into general reconstruction constraints. The proposed method simultaneously achieves blind single-frame super-resolution and image enhancement especially shadow removal. Experimental results demonstrate the effectiveness and robustness of our method.