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.

Xehetasun bibliografikoak
Egile nagusia: Khan, Mohammad Meraj
Beste egile batzuk: Rahman, Md. Khalilur
Formatua: Thesis
Hizkuntza:English
Argitaratua: Brac University 2022
Gaiak:
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)
Sarrera elektronikoa:http://hdl.handle.net/10361/16368

Internet

http://hdl.handle.net/10361/16368

Antzeko izenburuak