Summary of Muharaf: Manuscripts Of Handwritten Arabic Dataset For Cursive Text Recognition, by Mehreen Saeed et al.
Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition
by Mehreen Saeed, Adrian Chan, Anupam Mijar, Joseph Moukarzel, Georges Habchi, Carlos Younes, Amin Elias, Chau-Wai Wong, Akram Khater
First submitted to arxiv on: 13 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research presents the Manuscripts of Handwritten Arabic (Muharaf) dataset, comprising over 1,600 historic handwritten page images with expert transcriptions in archival Arabic. Each image is accompanied by spatial coordinates for text lines and basic page elements. The Muharaf dataset aims to advance handwritten text recognition (HTR) not only for Arabic manuscripts but also for cursive texts generally. It features diverse handwriting styles and a wide range of document types, including personal letters, diaries, notes, poems, church records, and legal correspondences. The paper describes the data acquisition pipeline, notable dataset features, and statistics, as well as providing a preliminary baseline result achieved by training convolutional neural networks using this data. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research creates a special collection of handwritten Arabic texts called Muharaf. It has over 1,600 pictures of old documents written in cursive style. Each picture comes with extra information like where the text is on the page and what kind of document it is. This helps machines learn to read handwriting better. The collection includes many different styles of writing and types of documents, such as letters, notes, and poems. |
