Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.03748 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910634373808128 |
|---|---|
| author | Hussein, Ahmed Elsetohy, Alaa Hadhoud, Sama Bakr, Tameem Rohaim, Yasser AlKhamissi, Badr |
| author_facet | Hussein, Ahmed Elsetohy, Alaa Hadhoud, Sama Bakr, Tameem Rohaim, Yasser AlKhamissi, Badr |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_03748 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Khattat: Enhancing Readability and Concept Representation of Semantic Typography Hussein, Ahmed Elsetohy, Alaa Hadhoud, Sama Bakr, Tameem Rohaim, Yasser AlKhamissi, Badr Computation and Language Machine Learning 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. |
| title | Khattat: Enhancing Readability and Concept Representation of Semantic Typography |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2410.03748 |