Evaluation of Deep Super Resolution Methods for Textual Images
| Autor: | Ferdinand Ariandy Luwinda, Williem, Rini Wongso |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Similarity (geometry)
business.industry Computer science Deep learning Rank (computer programming) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020207 software engineering Pattern recognition 02 engineering and technology Optical character recognition computer.software_genre Superresolution 0202 electrical engineering electronic engineering information engineering Laplacian pyramid General Earth and Planetary Sciences 020201 artificial intelligence & image processing Artificial intelligence Focus (optics) business Image resolution computer General Environmental Science |
| Zdroj: | Procedia Computer Science. 135:331-337 |
| ISSN: | 1877-0509 |
| DOI: | 10.1016/j.procs.2018.08.181 |
| Popis: | Super-resolution (SR) is one of the important pre-processing methods to refine the text images quality. Though there are numerous introduced algorithms to increase the spatial resolution for textual images, analysis on SR methods using deep learning is still insufficient. In this paper, we focus on evaluating the performance of various deep SR methods which have already confirmed to perform well in natural images super-resolution. Three evaluation metrics are used to analyze the performance of each method, such as peak signal-to-noise ratio (PSNR), structure similarity index (SSIM), and optical character recognition accuracy (OCRAcc). Experimental results show that deeper networks perform better than shallow networks for super-resolution problem. In overall, deep recursive convolutional network (DRCN) and deep laplacian pyramid network (LapSRN) alternately achieve the best performance. Then, very deep super-resolution network (VDSR) obtains the 3rd rank following both methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|