Khattat: Enhancing Readability and Concept Representation of Semantic Typography
Hussein, Ahmed Elsetohy, Alaa Hadhoud, Sama Bakr, Tameem Rohaim, Yasser AlKhamissi, Badr
Hussein, Ahmed
Elsetohy, Alaa
Hadhoud, Sama
Bakr, Tameem
Rohaim, Yasser
AlKhamissi, Badr
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Designing expressive typography that visually conveys a word’s meaning while maintaining readability is a complex task, known as semantic typography. It involves selecting an idea, choosing an appropriate font, and balancing creativity with legibility. We introduce an end-to-end system that automates this process. First, a Large Language Model (LLM) generates imagery ideas for the word, useful for abstract concepts like “freedom.” Then, the FontCLIP pre-trained model automatically selects a suitable font based on its semantic understanding of font attributes. The system identifies optimal regions of the word for morphing and iteratively transforms them using a pre-trained diffusion model. A key feature is our OCR-based loss function, which enhances readability and enables simultaneous stylization of multiple characters. We compare our method with other baselines, demonstrating great readability enhancement and versatility across multiple languages and writing scripts.
Citation
A. Hussein, A. Elsetohy, S. Hadhoud, T. Bakr, Y. Rohaim, and B. AlKhamissi, “Khattat: Enhancing Readability and Concept Representation of Semantic Typography,” pp. 278–295, 2025, doi: 10.1007/978-3-031-92808-6_18/FIGURES/11
Source
Lecture Notes in Computer Science
Conference
Workshops that were held in conjunction with the 18th European Conference on Computer Vision
ECCV 2024
ECCV 2024
Keywords
Font Selection, Large Language Models, Multi-letter, Multilingual, Ocr Loss, Semantic Typography, Computational Linguistics, Latent Semantic Analysis, Typesetting, Complex Task, End-to-end Systems, Expressive Typography, Font Selection, Language Model, Large Language Model, Multi-letter, Multilingual, Ocr Loss, Semantic Typography, Semantics
Subjects
Source
Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024
Publisher
Springer Nature