Bionic vision improves the performances of super resolution imaging
- 7 March 2019
- conference paper
- Published by SPIE-Intl Soc Optical Eng in Tenth International Symposium on Precision Engineering Measurements and Instrumentation
- Vol. 11053, 110531J
- https://doi.org/10.1117/12.2511338
Abstract
A novel super resolution reconstruction method is proposed to improve super resolution image performances. The proposed method uses bionic vision sampling model to obtain low resolution images and performs super resolution reconstruction in logarithmic polar coordinates. We carry out comparative experiments between the proposed method and the traditional method in terms of Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and Mean Squared Error (MSE). The results show that the performances of proposed method are better than that of the traditional method. Especially the SSIM of global image (butterfly), the proposed method is 34.45% higher than the traditional method.Keywords
This publication has 7 references indexed in Scilit:
- Image super-resolution: The techniques, applications, and futureSignal Processing, 2016
- Super-Resolution Reconstruction for Multi-Angle Remote Sensing Images Considering Resolution DifferencesRemote Sensing, 2014
- Automatic spread of attentional response modulation along Gestalt criteria in primary visual cortexNature Neuroscience, 2011
- Rotation and Scale-Invariant Texture Classification Using Log-Polar and Ridgelet TransformJournal of Pattern Recognition Research, 2010
- Super-Resolution Without Explicit Subpixel Motion EstimationIEEE Transactions on Image Processing, 2009
- Fast and Robust Multiframe Super ResolutionIEEE Transactions on Image Processing, 2004
- Example-based super-resolutionIEEE Computer Graphics and Applications, 2002