Abstract: Image super-resolution reconstruction is an important task in the study of image enhancement and image restoration.It is widely used in the fields of high definition television,medical imaging and remote sensing imaging,etc.In this paper,the wavelet analysis was adopted to detect the pixel edges,and the polynomial subdivision algorithm was used to locate the sub-pixel edges.Therefore,the original image was divided into three parts,namely smoothing region,neighborhood edge region and minuteness edge region.According to different regional characteristics,the different interpolation methods were carried out to realize the image super-resolution reconstruction.The simulation results show that the boundary of reconstructed high resolution image is clear and natural,and the subjective judgment and objective eva-luation are better than traditional reconstruction algorithm.The method in this paper achieves good effects and reaches good feasibility and validity.

Key words: Wavelet analysis,Polynomial subdivision,Sub-pixel,Super-resolution reconstruction