Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.7%) to scientific vocabulary
Repository
Capstone Project Group 24
Basic Info
- Host: GitHub
- Owner: ashishk007
- Language: Jupyter Notebook
- Default Branch: main
- Size: 205 MB
Statistics
- Stars: 3
- Watchers: 2
- Forks: 2
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
MAST90106Group24
Capstone Project Group 24
Pre-processing:
For the pre-processing part, since our final result is CRNN model is not that useful, and we shouldn't use most preprocessing steps before using the AWS, GCP, or Azure, thus the only valueable part for pre processing is data type conversion. In order to run this code, you need to make sure you download the latest version of poppler. If you are using windows system, do remember to add the file into the system dir. You can google how to do this. If you are using Mac book, you can just download the poppler and run the code.
However, if you want to repeat everything, you can run the preprocessing main file, and do remember to change parameters.
CRNN model:
Credits for CRNN source code:
de Sousa Neto, A. F., Bezerra, B. L. D., Toselli, A. H., \& Lima, E. B. (2020, September). Htr-flor++ a handwritten text recognition system based on a pipeline of optical and language models. In Proceedings of the ACM Symposium on Document Engineering 2020 (pp. 1-4).
github: https://github.com/arthurflor23/handwritten-text-recognition