Local Consistency Constrained Adaptive Neighbor Embedding for Text Image Super-Resolution
| Autor: | Jun Sun, Satoshi Naoi, Akihiro Minagawa, Wei Fan, Yoshinobu Hotta |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Computer science
business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Pattern recognition Iterative reconstruction Image (mathematics) Constraint (information theory) Local consistency Embedding Point (geometry) Computer vision Artificial intelligence business Image resolution Sub-pixel resolution |
| Zdroj: | Document Analysis Systems |
| DOI: | 10.1109/das.2012.52 |
| Popis: | This paper proposes a robust single-image super resolution method for enlarging low quality camera captured text image. The contribution of this work is twofold. First, we point out the non-local reconstruction problem in neighbor embedding based super-resolution by statistical analysis on an empirical data set. Second, we introduce a local consistency constraint to explicitly regularize the linear reconstruction process, and adaptively generate the most possible candidates for the high resolution image patch. For the non-consistent candidates, we rely on its adjacent overlapping patches for capability verification. Experimental results demonstrate that our solution produces visually pleasing enlargements for various text images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|