| Autor: |
Dan Sporici, Elena Cușnir, Costin-Anton Boiangiu |
| Jazyk: |
angličtina |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
Symmetry, Vol 12, Iss 5, p 715 (2020) |
| Druh dokumentu: |
article |
| ISSN: |
2073-8994 |
| DOI: |
10.3390/sym12050715 |
| Popis: |
Optical Character Recognition (OCR) is the process of identifying and converting texts rendered in images using pixels to a more computer-friendly representation. The presented work aims to prove that the accuracy of the Tesseract 4.0 OCR engine can be further enhanced by employing convolution-based preprocessing using specific kernels. As Tesseract 4.0 has proven great performance when evaluated against a favorable input, its capability of properly detecting and identifying characters in more realistic, unfriendly images is questioned. The article proposes an adaptive image preprocessing step guided by a reinforcement learning model, which attempts to minimize the edit distance between the recognized text and the ground truth. It is shown that this approach can boost the character-level accuracy of Tesseract 4.0 from 0.134 to 0.616 (+359% relative change) and the F1 score from 0.163 to 0.729 (+347% relative change) on a dataset that is considered challenging by its authors. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
