TY  - CONF
AU  - Mohamed Ali Souibgui
AU  - Sanket Biswas
AU  - Sana Khamekhem Jemni
AU  - Yousri Kessentini
AU  - Alicia Fornes
AU  - Josep Llados
AU  - Umapada Pal
A2  - ICPR
PY  - 2022//
TI  - DocEnTr: An End-to-End Document Image Enhancement Transformer
BT  - 26th International Conference on Pattern Recognition
SP  - 1699
EP  - 1705
KW  - Degradation
KW  - Head
KW  - Optical character recognition
KW  - Self-supervised learning
KW  - Benchmark testing
KW  - Transformers
KW  - Magnetic heads
N2  - Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for proper usage. To address this challenge, we present a new encoder-decoder architecture based on vision transformers to enhance both machine-printed and handwritten document images, in an end-to-end fashion. The encoder operates directly on the pixel patches with their positional information without the use of any convolutional layers, while the decoder reconstructs a clean image from the encoded patches. Conducted experiments show a superiority of the proposed model compared to the state-of the-art methods on several DIBCO benchmarks. Code and models will be publicly available at: https://github.com/dali92002/DocEnTR
L1  - http://refbase.cvc.uab.es/files/SBJ2022.pdf
UR  - http://dx.doi.org/10.1109/ICPR56361.2022.9956101
N1  - DAG; 600.121; 600.162; 602.230; 600.140
ID  - Mohamed Ali Souibgui2022
ER  -