Training deep network models for accurate recognition of texts in scenes

The purpose of this report investigates and implement different state-of-the-art deep learning network models for the recognition of various text in scenes. Furthermore, fine-tuning of parameters and modifying of the model is conducted to investigate the effect and the changes to the accuracy.

Saved in:
Bibliographic Details
Main Author: Teo, Zhi Kai
Other Authors: Lu Shijian
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/157313
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Be the first to leave a comment!
You must be logged in first