Hybrid Multi-Phase Page Matching and Multi-Layer Diff Detection for Japanese Building Permit Document Review
This addresses a domain-specific problem for Japanese building permit reviewers by automating document comparison, though it appears incremental as it combines existing techniques like LCS and dynamic programming.
The paper tackles the problem of automating comparison of Japanese building permit document sets across revision cycles, which is labor-intensive and error-prone when done manually, and achieves F1=0.80 and precision=1.00 with zero false-positive matched pairs on real-world data.
We present a hybrid multi-phase page matching algorithm for automated comparison of Japanese building permit document sets. Building permit review in Japan requires cross-referencing large PDF document sets across revision cycles, a process that is labor-intensive and error-prone when performed manually. The algorithm combines longest common subsequence (LCS) structural alignment, a seven-phase consensus matching pipeline, and a dynamic programming optimal alignment stage to robustly pair pages across revisions even when page order, numbering, or content changes substantially. A subsequent multi-layer diff engine -- comprising text-level, table-level, and pixel-level visual differencing -- produces highlighted difference reports. Evaluation on real-world permit document sets achieves F1=0.80 and precision=1.00 on a manually annotated ground-truth benchmark, with zero false-positive matched pairs.