A semi-self-supervised learning model to recognize handwritten characters in ancient documents in Indian scripts

A Jindal, R Ghosh - Neural Computing and Applications, 2024 - Springer
An optical character recognition (OCR) system segments the character from the given
document before recognizing it. The recognition of such character images requires the class …

[HTML][HTML] Japanese historical character recognition by focusing on character parts

T Ishikawa, T Miyazaki, S Omachi - Pattern Recognition, 2024 - Elsevier
Japanese historical documents provide valuable information. Character recognition is a
critical technology for the digitalization of historical documents. Sample imbalance is a …

Handwritten Kannada character recognition using convolutional neural networks and transfer learning

SB Madhu, CV Aravinda… - Journal of Physics …, 2023 - iopscience.iop.org
Abstract Handwritten Kannada Character Recognition is special field of pattern recognition
as different human being will have their own handwritten styles, machine considers even …

Correction of an Image for Colour Blindness Using the Fusion of Ishihara Filter and Histogram Equalization

MS Sannidhan, JE Martis, CV Aravinda… - … Conference on Artificial …, 2023 - Springer
Colour blindness is one of the minor disorders in individuals appearing due to a genetic
mutation causing the intensity to few colours making the individual fail to discriminate …

Japanese literature organization and spatiotemporal database system creation for natural disaster analysis

B Lyu, X Yue, L Meng - Heritage Science, 2024 - Springer
Japan is one of the countries with the most frequent natural disasters in the world and is
faced with various threats of natural disasters every year, which significantly impact Japan's …

Artificial Intelligence based Approach for Virtual Character Recognition

D Balakrishnan, U Mariappan… - 2023 International …, 2023 - ieeexplore.ieee.org
Virtual teaching involves providing educational instruction and content to students using
digital methods, predominantly over the internet. In virtual teaching, educators and learners …

Bacterial Leaf Spot of Tomato (Solanum lycopersicum) detection using Image Processing and Convolution Neural Network

CV Aravinda, MA Shah, J Shetty, A Kini, S Shetty, M Lin - 2022 - researchsquare.com
In many regions of the world, lack of infrastructure makes it challenging to promptly assess
plant diseases, which is a major threat to agricultural output. Recognizing disease on crops …

Kuzushiji Character Recognition using Deep Learning: A Local Binary and Phase Quantization Patterns

DA CV, KH Reddy, J Shetty, S Shetty - Available at SSRN 4351166 - papers.ssrn.com
The Kuzushiji numerals are one of the ancient language scripts. It is challenging due to:
characters are often interconnected without explicit spaces, abbreviations are often used in …

[PDF][PDF] Error Correction on Digitization of Modern Japanese Documents with Pre-trained BERT Model

S XIE - 人間情報学研究科年誌, 2023 - tohoku-gakuin.repo.nii.ac.jp
Modern history from the Meiji era to the early Showa era (1868-1945) brought about major
changes in Japan. As a bridge from the early modern period to the present day, the …

[引用][C] Transformer-Based Unified Segmentation: Simultaneous Semantic and Instance Tasks on Point Clouds

L Pan, W Luan, J Li, Y Zhen, Q Fu - Journal of Circuits, Systems and …, 2024 - World Scientific
Traditionally, 3D segmentation tasks have operated in silos, focusing separately on
semantic and instance segmentation. However, this disjointed approach lacks …