A survey comparing specialized hardware and evolution in TPUs for neural networks

A Shahid, M Mushtaq - 2020 IEEE 23rd International Multitopic …, 2020 - ieeexplore.ieee.org
This survey paper is based on the evolution of TPUs from first generation TPUs to edge
TPUs and their architectures. This paper compares CPUs, GPUs, FPGAs and TPUs, their …

A comprehensive review of one-stage networks for object detection

Y Zhang, X Li, F Wang, B Wei… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Object detection has always been a hot topic in image processing, which is important in a
variety of applications. With the advent of the era of big data and the continuous …

Assistive system for the blind with voice output based on optical character recognition

D Dhinakaran, D Selvaraj, SM Udhaya Sankar… - … : Proceedings of ICICC …, 2022 - Springer
Everyone deserves to live freely, even those who are impaired. In recent decades,
technology has focused on empowering disabled people to have as much control over their …

The potential of artificial intelligence for assistive technology in education

K Zdravkova - Handbook on Intelligent Techniques in the Educational …, 2022 - Springer
The right to education is a fundamental human right and an indispensable prerequisite for
the development of human beings. To become well-rounded and independent from others …

Exploring deep learning approaches to recognize handwritten arabic texts

M Eltay, A Zidouri, I Ahmad - IEEE Access, 2020 - ieeexplore.ieee.org
Recognition of cursive handwritten Arabic text is a difficult problem because of context-
sensitive character shapes, the non-uniform spacing between words and within a word …

Mmu-ocr-21: Towards end-to-end urdu text recognition using deep learning

T Nasir, MK Malik, K Shahzad - IEEE Access, 2021 - ieeexplore.ieee.org
Optical Character Recognition (OCR) is a technique that generates text from an image.
Recognizing the importance of OCR in real-world settings, a plethora of techniques have …

Efficient CRNN: Towards end-to-end low resource Urdu text recognition using depthwise separable convolutions and gated recurrent units

T Nasir, MK Malik - Information Processing & Management, 2024 - Elsevier
In this study, a novel technique is proposed to recognize printed text in images for Urdu, a
low-resource language with a scarcity of benchmark datasets. The proposed technique is …

Deep learning-aided OCR techniques for Chinese uppercase characters in the application of Internet of Things

Y Yin, W Zhang, S Hong, J Yang, J Xiong, G Gui - IEEE Access, 2019 - ieeexplore.ieee.org
Optical character recognition (OCR) has become one of the most important techniques in
computer vision, given that it can easily obtain digital information from various images on the …

A proposed framework for recognition of handwritten cursive english characters using DAG-CNN

PV Bhagyasree, A James… - 2019 1st International …, 2019 - ieeexplore.ieee.org
Handwritten Character Recognition (HCR) plays an important role in Optical character
Recognition (OCR) and Pattern Recognition (PR), as it has a good number of applications in …

Recognition of multifont English electronic prescribing based on convolution neural network algorithm

MJ Mohammed, EA Mohammed… - Bio-Algorithms and Med …, 2020 - degruyter.com
The printed character recognition is an efficient and automatic method for inputting
information to a computer nowadays that is used to translate the printed or handwritten …