A squeeze and excitation ResNeXt-based deep learning model for Bangla handwritten basic to compound character recognition

A squeeze and excitation ResNeXt-based deep learning model for Bangla handwritten basic to compound character recognition

This thesis is submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science and Engineering, 2021.

Opis bibliograficzny
1. autor: Khan, Mohammad Meraj
Kolejni autorzy: Rahman, Md. Khalilur
Format: Praca dyplomowa
Język:English
Wydane: Brac University 2022
Hasła przedmiotowe:
Bangla handwritten-character recognition
Deep convolutional neural network
Squeeze and excitation ResNext
Optical character recognition
Global average pooling
Character recognition
Artificial intelligence.
Simulation.
Neural networks (Computer science)
Cognitive learning theory (Deep learning)
Dostęp online:http://hdl.handle.net/10361/16368
Opis
Streszczenie:This thesis is submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science and Engineering, 2021.

Podobne zapisy