This paper discusses a super-resolution (SR) system implemented on a mobile device. We utilized an Android device�s\ncamera to take successive shots and applied a classical multiple-image super-resolution (SR) technique that utilized a\nset of low-resolution (LR) images. Images taken from the mobile device are subjected to our proposed filtering\nscheme wherein images that have noticeable presence of blur are discarded to avoid outliers from affecting the\nproduced high-resolution (HR) image. The remaining subset of images are subjected to non-local means denoising,\nthen feature-matched against the first reference LR image. Successive images are then aligned with respect to the first\nimage via affine and perspective warping transformations. The LR images are then upsampled using bicubic\ninterpolation. An L2-norm minimization approach, which is essentially taking the pixel-wise mean of the aligned\nimages, is performed to produce the final HR image.\nOur study shows that our proposed method performs better than the bicubic interpolation, which makes its\nimplementation in a mobile device quite feasible. We have also proven in our experiments that there are substantial\ndifferences from images captured using burst mode that can be utilized by an SR algorithm to create an HR image.
Loading....