End-to-End Semantic Preservation in Text-Aware Image Compression Systems
This addresses the need for efficient, task-relevant image compression for automated understanding, particularly in resource-limited devices, though it builds incrementally on existing Coding for Machines principles.
The paper tackles the problem of preserving text-specific features for Optical Character Recognition (OCR) in image compression, achieving significant improvements in text extraction accuracy at low bitrates, even outperforming OCR on uncompressed images.
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.