Image Super-Resolution Reconstruction Using Image Registration and Error-Amended Sharp Edge Interpolation

摘要：

In this study, an image super-resolution (SR) reconstruction approach using image registration and erroramended sharp edge (EASE) interpolation is proposed. The proposed image SR reconstruction approach contains five stages, namely, noise smoothing by Gaussian filtering, image edge map extraction using Canny edge detection, high-resolution grid generation using image registration, EASE interpolation, and blocking artifact reduction by image restoration. Based on the experimental results obtained in this study, both the subjective visual quality and the objective PSNR values of the proposed approach are better than those of the three comparison approaches.

作者: Yung-Yuan CHIEN Jin-Jang LEOU Hsuan-Ying CHEN

作者单位: Department of Computer Science and Information Engineering National Chung Cheng University, Chiayi Department of Computer Science and Information EngineeringNational Chung Cheng University, Chiayi

会议类型: 国际会议

会议名称: 2011亚太信号与信息处理协会年度峰会(APSIPAASC 2011)

会议地点: 西安

会议语种:英文

页码: 1-6

在线出版日期: 2011-10-18（万方平台首次上网日期，不代表论文的发表时间）