Models for Patch-Based Image Restoration
<p>Abstract</p> <p>We present a supervised learning approach for object-category specific restoration, recognition, and segmentation of images which are blurred using an unknown kernel. The novelty of this work is a multilayer graphical model which unifies the low-level vision task...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2009-01-01
|
| Series: | EURASIP Journal on Image and Video Processing |
| Online Access: | http://jivp.eurasipjournals.com/content/2009/641804 |
| _version_ | 1818863633092837376 |
|---|---|
| author | Petrovic Nemanja Das Gupta Mithun Rajaram Shyamsundar Huang ThomasS |
| author_facet | Petrovic Nemanja Das Gupta Mithun Rajaram Shyamsundar Huang ThomasS |
| author_sort | Petrovic Nemanja |
| collection | DOAJ |
| description | <p>Abstract</p> <p>We present a supervised learning approach for object-category specific restoration, recognition, and segmentation of images which are blurred using an unknown kernel. The novelty of this work is a multilayer graphical model which unifies the low-level vision task of restoration and the high-level vision task of recognition in a cooperative framework. The graphical model is an interconnected two-layer Markov random field. The restoration layer accounts for the compatibility between sharp and blurred images and models the association between adjacent patches in the sharp image. The recognition layer encodes the entity class and its location in the underlying scene. The potentials are represented using nonparametric kernel densities and are learnt from training data. Inference is performed using nonparametric belief propagation. Experiments demonstrate the effectiveness of our model for the restoration and recognition of blurred license plates as well as face images.</p> |
| first_indexed | 2024-12-19T10:18:51Z |
| format | Article |
| id | doaj.art-1c505ae3b40e4a30a626b7c91def3617 |
| institution | Directory Open Access Journal |
| issn | 1687-5176 1687-5281 |
| language | English |
| last_indexed | 2024-12-19T10:18:51Z |
| publishDate | 2009-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Image and Video Processing |
| spelling | doaj.art-1c505ae3b40e4a30a626b7c91def36172022-12-21T20:26:07ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-51761687-52812009-01-0120091641804Models for Patch-Based Image RestorationPetrovic NemanjaDas Gupta MithunRajaram ShyamsundarHuang ThomasS<p>Abstract</p> <p>We present a supervised learning approach for object-category specific restoration, recognition, and segmentation of images which are blurred using an unknown kernel. The novelty of this work is a multilayer graphical model which unifies the low-level vision task of restoration and the high-level vision task of recognition in a cooperative framework. The graphical model is an interconnected two-layer Markov random field. The restoration layer accounts for the compatibility between sharp and blurred images and models the association between adjacent patches in the sharp image. The recognition layer encodes the entity class and its location in the underlying scene. The potentials are represented using nonparametric kernel densities and are learnt from training data. Inference is performed using nonparametric belief propagation. Experiments demonstrate the effectiveness of our model for the restoration and recognition of blurred license plates as well as face images.</p>http://jivp.eurasipjournals.com/content/2009/641804 |
| spellingShingle | Petrovic Nemanja Das Gupta Mithun Rajaram Shyamsundar Huang ThomasS Models for Patch-Based Image Restoration EURASIP Journal on Image and Video Processing |
| title | Models for Patch-Based Image Restoration |
| title_full | Models for Patch-Based Image Restoration |
| title_fullStr | Models for Patch-Based Image Restoration |
| title_full_unstemmed | Models for Patch-Based Image Restoration |
| title_short | Models for Patch-Based Image Restoration |
| title_sort | models for patch based image restoration |
| url | http://jivp.eurasipjournals.com/content/2009/641804 |
| work_keys_str_mv | AT petrovicnemanja modelsforpatchbasedimagerestoration AT dasguptamithun modelsforpatchbasedimagerestoration AT rajaramshyamsundar modelsforpatchbasedimagerestoration AT huangthomass modelsforpatchbasedimagerestoration |