R
Reem Alaasam
Researcher at Ben-Gurion University of the Negev
Publications - 15
Citations - 85
Reem Alaasam is an academic researcher from Ben-Gurion University of the Negev. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 3, co-authored 10 publications receiving 44 citations.
Papers
More filters
Proceedings ArticleDOI
VML-HD: The historical Arabic documents dataset for recognition systems
TL;DR: A new database with handwritten Arabic script based on five books written by different writers from the years 1088–1451 designed for training and testing recognition systems for handwritten Arabic sub-words is presented.
Proceedings ArticleDOI
Experiment study on utilizing convolutional neural networks to recognize historical Arabic handwritten text
TL;DR: This work experiments with extending a small labeled dataset of Arabic continuous subwords by an orders of magnitude, which is used to synthesize a large collection of labeled dataset, which consist of handwritten Arabic subwords.
Proceedings ArticleDOI
Layout Analysis on Challenging Historical Arabic Manuscripts using Siamese Network
TL;DR: This paper presents layout analysis for historical Arabic documents using siamese network, and shows the effectiveness of the method by comparing with other works that use deep learning approaches, and has state of art results.
Book ChapterDOI
Text Line Extraction Using Fully Convolutional Network and Energy Minimization
TL;DR: Li et al. as discussed by the authors used a fully convolutional network for text line detection and energy minimization for textline extraction. But text line extraction from handwritten documents remains an unsolved task.
Proceedings ArticleDOI
Unsupervised Deep Learning for Handwritten Page Segmentation
TL;DR: An unsupervised deep learning method for page segmentation, which revokes the need for annotated images, which uses a siamese neural network to differentiate between patches using their measurable properties such as number of foreground pixels, and average component height and width.