De-gan: A conditional generative adversarial network for document enhancement

MA Souibgui, Y Kessentini - IEEE Transactions on Pattern …, 2020 - ieeexplore.ieee.org
Documents often exhibit various forms of degradation, which make it hard to be read and
substantially deteriorate the performance of an OCR system. In this paper, we propose an …

Games of GANs: Game-theoretical models for generative adversarial networks

M Mohebbi Moghaddam, B Boroomand… - Artificial Intelligence …, 2023 - Springer
Abstract Generative Adversarial Networks (GANs) have recently attracted considerable
attention in the AI community due to their ability to generate high-quality data of significant …

[PDF][PDF] Event Factuality Identification via Generative Adversarial Networks with Auxiliary Classification.

Z Qian, P Li, Y Zhang, G Zhou, Q Zhu - IJCAI, 2018 - ijcai.org
Event factuality identification is an important semantic task in NLP. Traditional research
heavily relies on annotated texts. This paper proposes a twostep framework, first extracting …

Texrgan: a deep adversarial framework for text restoration from deformed handwritten documents

A Poddar, A Chakraborty, J Mukhopadhyay… - Proceedings of the …, 2021 - dl.acm.org
Free form handwritten document images commonly contains deformed text images such as
struck-out and underlined words. The deformed text images drastically degrades the …

Synthesizing and imitating handwriting using deep recurrent neural networks and mixture density networks

KM Kumar, H Kandala… - 2018 9th International …, 2018 - ieeexplore.ieee.org
Handwriting is a skill developed by humans from the very early stage in the order to
represent his/her thoughts visually using letters and making meaningful words and …

Combination of DE-GAN with CNN-LSTM for Arabic OCR on Images with Colorful Backgrounds

A Mars, K Dabbabi, S Zrigui, M Zrigui - International Conference on …, 2023 - Springer
In this paper, a combination of the conditional generative adversarial network (DE-GAN) with
the convolutional neural network (CNN) and long short time memory (LSTM) is proposed in …

Onkogan: Bangla handwritten digit generation with deep convolutional generative adversarial networks

S Haque, SA Shahinoor, AKMSA Rabby… - Recent Trends in Image …, 2019 - Springer
From a very early age human achieve a precious skill that is a handwriting. After this
invention, the ardor of it changed day by day. And every human has a different style of …

Generation of Handwritten Numbers Using Generative Adversarial Networks

Z Qin, Y Shan - Journal of Physics: Conference Series, 2021 - iopscience.iop.org
As a promising generative modeling method, Generative Adversarial Networks are a deep-
learning-based generative model, in which two networks, namely the generative network …

A real-time continuous automatic focus algorithm for digital cameras

M Gamadia, N Kehtarnavaz - 2006 IEEE Southwest Symposium …, 2006 - ieeexplore.ieee.org
Most conventional continuous auto-focus algorithms appearing in the literature fail to
address how to focus on a desired near object when there are multiple objects in the scene …

The character generation in handwriting feature extraction using variational autoencoder

T Yamada, M Hosoe, K Kato… - 2017 14th IAPR …, 2017 - ieeexplore.ieee.org
Handwriting identification is a method to identify an unknown writer by comparing a known
writer's characters with an unknown writer's characters by using the homeostasis of …