OCR improvement by debluring mobile phone shot doc

By洪堯煬
M.S. student
This is the final project for Deep Learning and NLP Research Methodologies course, NTHU. We propose our debluring model to handle OCR blurry input. Hence, we adopt the SmartDocQA, a real-world phone took text images dataset, as our deblur dataset. After our aligment of dataset and training, finally we get better OCR accuracy. report : https://drive.google.com/file/d/1YN7MRtP-H9nG6fFzkbsAzOiep2lWzLnj/view?usp=sharing
洪堯煬
Published: March 04, 2021
python
Tesseract
pytorch
Machine Learning
OCR
Computer Vision
debluring
Deep Learning
More from 洪堯煬
Hand-craft pokemon yellow web (GB)
Tea Factory Website
milk volume prediction
desktop clock
Discord Language Learning Bot
Vehicle trajectories prediction by machine learnin
chat placeholder

Build Your Professional Network

Click icon on the company page or under talent search engine to start the conversation.