Title | ||
---|---|---|
Convolutional Neural Networks for Online Arabic Characters Recognition with Beta-Elliptic Knowledge Domain |
Abstract | ||
---|---|---|
Handwriting recognition is challenging research filed in spite of the progress of techniques used on its recognition. Deeper neural networks have achieved good results in this field. Current neural networks especially deep convolutional networks, neglect spatial and temporal information of script and deal only with it as an image. Features can be a crucial fact for separating between handwriting scripts. In this paper, we propose a CNN based on Beta-elliptic parameters and Fuzzy Elementary Perceptual Codes for Online Arabic Characters Recognition. Experimental results on two databases, LMCA and MAYASTROUN, indicate that our novel system based on CNN is possible on an online script and gives good accuracy of 98.90% compared to recent works in the state of the art. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ICDARW.2019.50114 | 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW) |
Keywords | Field | DocType |
Online handwriting, Fuzzy Elementary Perceptual Codes, Segmentation, Recognition, Arabic Character, CNN, Beta-elliptic Parameters, Noise, Dropout | Handwriting,Pattern recognition,Convolutional neural network,Segmentation,Computer science,Fuzzy logic,Handwriting recognition,Artificial intelligence,Artificial neural network,Perception,Scripting language | Conference |
Volume | ISSN | ISBN |
6 | 1520-5363 | 978-1-7281-5055-0 |
Citations | PageRank | References |
4 | 0.42 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hanen Akouaydi | 1 | 5 | 1.11 |
Sourour Njah | 2 | 32 | 4.21 |
Wael Ouarda | 3 | 34 | 7.36 |
Anis Samet | 4 | 4 | 0.42 |
Mourad Zaied | 5 | 6 | 1.46 |
Mohamed Adel Alimi | 6 | 1947 | 217.16 |