Aesthetical Attributes for Segmenting Arabic Word
Mohamed Hssini, Azzeddine Lazrek

TL;DR
This paper presents a method for segmenting Arabic words into individual graphemes by respecting calligraphic and aesthetic attributes, ensuring the integrity of each letter's design in the segmentation process.
Contribution
It introduces a novel segmentation approach that considers aesthetic and calligraphic features to accurately extract Arabic graphemes from words.
Findings
Effective segmentation respecting calligraphic design
Preserves the cursive connection in segmentation
Improves accuracy of Arabic letter extraction
Abstract
The connected allograph representing calligraphic Arabic word does not appear individually in any calligraphic resource but in association with other letters all adapted to each other. The graphic segmentation of the word by respecting aesthetical attributes indicating the grapheme of every letter is far from being an obvious task. The question consists in discovering every letter constituting the word, points of cutting which separate its grapheme from other constituents of word's shape. The obtained segment must be a complete drawing of the represented letter. This segmentation according to contextual graphic and qualitative criteria connecting the attached allograph will have to satisfy typographic constraints varying in conformity with the possibilities offered by the wanted technology. In this paper, we develop an approach for segmenting Arabic word from which the purpose is to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques
