R
Russell M. Mersereau
Researcher at Georgia Institute of Technology
Publications - 229
Citations - 12104
Russell M. Mersereau is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Motion compensation & Image restoration. The author has an hindex of 48, co-authored 229 publications receiving 11716 citations. Previous affiliations of Russell M. Mersereau include Massachusetts Institute of Technology & Georgia Tech Research Institute.
Papers
More filters
Proceedings ArticleDOI
Single Image Super-Resolution Based on Support Vector Regression
TL;DR: Initial results show that even when trained on as little as a single image, SVR is able to learn a generally applicable model that can super-resolve dissimilar images.
Proceedings ArticleDOI
Lossy compression of images corrupted by film grain noise
TL;DR: This paper presents an MMSE image restoration algorithm based on modeling the image as a Markov random field and the performance of this preprocessing step is studied when using JPEG.
Journal ArticleDOI
Two-band wavelets and filterbanks over finite fields with connections to error control coding
TL;DR: The theory of wavelet decompositions of signals in vector spaces defined over Galois fields is introduced and the application of this transform to the construction of error correcting codes, including double circulant codes that are generated by wavelets are given.
Proceedings ArticleDOI
The symmetric convolution approach to the nonexpansive implementations of FIR filter banks for images
TL;DR: The authors explain how to use symmetric convolution to implement a multiband filter bank for finite-length data that restricts the number of samples in the subbands but still gives perfect reconstruction.
Journal ArticleDOI
Quantitative Performance Evaluation Algorithms for Pavement Distress Segmentation
TL;DR: In this paper, the buffered Hausdorff distance is used to estimate the deviation of the cracks in the segmented image from the ground truth cracks, which can capture the local effectiveness of segmentation methods around the crack region without compromising its robustness to isolated pixel deviations caused by noise.