Entropy Heat-Mapping: Localizing GPT-Based OCR Errors with Sliding-Window Shannon Analysis
This provides a lightweight tool for post-editing GPT-based OCR, particularly for mathematical documents, but it is incremental as it builds on existing entropy analysis methods.
The paper tackled the problem of localizing OCR errors in GPT-based transcription of mathematical documents by developing an entropy-heat-mapping method that uses sliding-window Shannon analysis to identify high-entropy regions likely containing errors, and it showed that the vast majority of true errors are concentrated in these regions.
Vision-language models such as OpenAI GPT-4o can transcribe mathematical documents directly from images, yet their token-level confidence signals are seldom used to pinpoint local recognition mistakes. We present an entropy-heat-mapping proof-of-concept that turns per-token Shannon entropy into a visual ''uncertainty landscape''. By scanning the entropy sequence with a fixed-length sliding window, we obtain hotspots that are likely to contain OCR errors such as missing symbols, mismatched braces, or garbled prose. Using a small, curated set of scanned research pages rendered at several resolutions, we compare the highlighted hotspots with the actual transcription errors produced by GPT-4o. Our analysis shows that the vast majority of true errors are indeed concentrated inside the high-entropy regions. This study demonstrates--in a minimally engineered setting--that sliding-window entropy can serve as a practical, lightweight aid for post-editing GPT-based OCR. All code and annotation guidelines are released to encourage replication and further research.