End-to-End Semantic Preservation in Text-Aware Image Compression Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908593121394688 |
|---|---|
| author | Della Fiore, Stefano Gnutti, Alessandro Dalai, Marco Migliorati, Pierangelo Leonardi, Riccardo |
| author_facet | Della Fiore, Stefano Gnutti, Alessandro Dalai, Marco Migliorati, Pierangelo Leonardi, Riccardo |
| contents | Traditional image compression methods aim to reconstruct images for human perception, prioritizing visual fidelity over task relevance. In contrast, Coding for Machines focuses on preserving information essential for automated understanding. Building on this principle, we present an end-to-end compression framework that retains text-specific features for Optical Character Recognition (OCR). The encoder operates at roughly half the computational cost of the OCR module, making it suitable for resource-limited devices. When on-device OCR is infeasible, images can be efficiently compressed and later decoded to recover textual content. Experiments show significant improvements in text extraction accuracy at low bitrates, even outperforming OCR on uncompressed images.
We further extend this study to general-purpose encoders, exploring their capacity to preserve hidden semantics under extreme compression. Instead of optimizing for visual fidelity, we examine whether compact, visually degraded representations can retain recoverable meaning through learned enhancement and recognition modules. Results demonstrate that semantic information can persist despite severe compression, bridging text-oriented compression and general-purpose semantic preservation in machine-centered image coding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19495 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | End-to-End Semantic Preservation in Text-Aware Image Compression Systems Della Fiore, Stefano Gnutti, Alessandro Dalai, Marco Migliorati, Pierangelo Leonardi, Riccardo Image and Video Processing Computer Vision and Pattern Recognition Traditional image compression methods aim to reconstruct images for human perception, prioritizing visual fidelity over task relevance. In contrast, Coding for Machines focuses on preserving information essential for automated understanding. Building on this principle, we present an end-to-end compression framework that retains text-specific features for Optical Character Recognition (OCR). The encoder operates at roughly half the computational cost of the OCR module, making it suitable for resource-limited devices. When on-device OCR is infeasible, images can be efficiently compressed and later decoded to recover textual content. Experiments show significant improvements in text extraction accuracy at low bitrates, even outperforming OCR on uncompressed images. We further extend this study to general-purpose encoders, exploring their capacity to preserve hidden semantics under extreme compression. Instead of optimizing for visual fidelity, we examine whether compact, visually degraded representations can retain recoverable meaning through learned enhancement and recognition modules. Results demonstrate that semantic information can persist despite severe compression, bridging text-oriented compression and general-purpose semantic preservation in machine-centered image coding. |
| title | End-to-End Semantic Preservation in Text-Aware Image Compression Systems |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.19495 |