Two-step CNN framework for text line recognition in camera-captured images
YS Chernyshova, AV Sheshkus, VV Arlazarov - IEEE Access, 2020 - ieeexplore.ieee.org
In this paper, we introduce an “on the device” text line recognition framework that is
designed for mobile or embedded systems. We consider per-character segmentation as a …
designed for mobile or embedded systems. We consider per-character segmentation as a …
High performance text recognition using a hybrid convolutional-lstm implementation
TM Breuel - 2017 14th IAPR international conference on …, 2017 - ieeexplore.ieee.org
Optical character recognition (OCR) has made great progress in recent years due to the
introduction of recognition engines based on recurrent neural networks, in particular the …
introduction of recognition engines based on recurrent neural networks, in particular the …
Multi-lingual optical character recognition system using the reinforcement learning of character segmenter
In this article, we present a new multi-lingual Optical Character Recognition (OCR) system
for scanned documents. In the case of Latin characters, current open source systems such …
for scanned documents. In the case of Latin characters, current open source systems such …
Efficient, lexicon-free OCR using deep learning
M Namysl, I Konya - 2019 international conference on …, 2019 - ieeexplore.ieee.org
Contrary to popular belief, Optical Character Recognition (OCR) remains a challenging
problem when text occurs in unconstrained environments, like natural scenes, due to …
problem when text occurs in unconstrained environments, like natural scenes, due to …
[HTML][HTML] Towards a unified framework for identity documents analysis and recognition
Identity documents recognition is far beyond classical optical character recognition
problems. Automated ID document recognition systems are tasked not only with the …
problems. Automated ID document recognition systems are tasked not only with the …
Which OCR toolset is good and why: A comparative study
Abstract Optical Character Recognition (OCR) is a very active research area in many
scientific disciplines like pattern recognition, natural language processing (NLP), computer …
scientific disciplines like pattern recognition, natural language processing (NLP), computer …
MIDV-LAIT: A challenging dataset for recognition of IDs with Perso-Arabic, Thai, and Indian scripts
Y Chernyshova, E Emelianova, A Sheshkus… - … on Document Analysis …, 2021 - Springer
In this paper, we present a new dataset for identity documents (IDs) recognition called MIDV-
LAIT. The main feature of the dataset is the textual fields in Perso-Arabic, Thai, and Indian …
LAIT. The main feature of the dataset is the textual fields in Perso-Arabic, Thai, and Indian …
A conditional gan based approach for distorted camera captured documents recovery
Many of the existing documents are digitized using smart phone's cameras. These are highly
vulnerable to capturing distortions (perspective angle, shadow, blur, warping, etc.), making …
vulnerable to capturing distortions (perspective angle, shadow, blur, warping, etc.), making …
Recognition of images of Korean characters using embedded networks
SA Ilyuhin, AV Sheshkus… - … Conference on Machine …, 2020 - spiedigitallibrary.org
Despite the significant success in the field of text recognition, complex and unsolved
problems still exist in this field. In recent years, the recognition accuracy of the English …
problems still exist in this field. In recent years, the recognition accuracy of the English …
Mobile phone sensing using the built-in camera
Modern mobile phones or smartphones have multipurpose functions apart from being used
as a device for voice and text communications. They are also embedded with many useful …
as a device for voice and text communications. They are also embedded with many useful …