OCR improvement by debluring mobile phone shot doc

Avatar of 洪堯煬.
Avatar of 洪堯煬.

OCR improvement by debluring mobile phone shot doc

M.S. student
Hsinchu, Hsinchu City, Taiwan
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

Avatar of the user.
Please login to comment.

Published: 2021 Mar 4th
61
8
0

python
Tesseract
pytorch
Machine Learning
OCR
Computer Vision
debluring
Deep Learning

Share