Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2005-10-03
Lect. Notes Comput. Sc. 3696 (2005) 499-506
Computer Science
Computer Vision and Pattern Recognition
6 pages with 3 figures. ICANN 2005
Scientific paper
Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require iterative minimization procedures, with high computational costs. Recently, the authors proposed a method to tackle this problem, based on the use of a hybrid MLP-PNN architecture. In this paper, we present a novel superresolution method, based on an evolution of this concept, to incorporate the use of local image models. A neural processing stage receives as input the value of model coefficients on local windows. The data dimensionality is firstly reduced by application of PCA. An MLP, trained on synthetic sequences with various amounts of noise, estimates the high-resolution image data. The effect of varying the dimension of the network input space is examined, showing a complex, structured behavior. Quantitative results are presented showing the accuracy and robustness of the proposed method.
Miravet Carlos
Rodriguez Francisco B.
No associations
LandOfFree
Accurate and robust image superresolution by neural processing of local image representations does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Accurate and robust image superresolution by neural processing of local image representations, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Accurate and robust image superresolution by neural processing of local image representations will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-134083