An improved super resolution reconstruction method based on initial value estimation

摘要

In order to improve the spatial resolution of the super resolution reconstructed image, an improved image super resolution reconstruction algorithm is proposed. In iterative back projection (IBP) algorithm, the initial value is estimated through wavelet locally adaptive interpolation method, other than in the traditional interpolation way. Image super resolution reconstruction is performed on multiple simulated low resolution images, experimental results show that the initial value plays an important part in super resolution reconstruction algorithm. The reconstructed image achieves better visual effect and higher peak signal to noise ratio (PSNR). The IBP algorithm has less estimation error and faster convergent speed than other method. This initial value estimation method can also be extensively used in other iterative super resolution algorithms.