Hybrid Multi-Phase Page Matching and Multi-Layer Diff Detection for Japanese Building Permit Document Review

Mitsumasa Wada

cs.CLMar 27, 2026

Hybrid Multi-Phase Page Matching and Multi-Layer Diff Detection for Japanese Building Permit Document Review

Authors: Mitsumasa Wada

Organizations: Faculty of Engineering and Design, Kagawa University

Abstract

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.

Figures & tables

Approach	Page Reorder	Visual Diff	Domain-Specific	Legal Links
DiffPDF [ 2 ]	–	$\checkmark$	–	–
ChangeDistiller [ 13 ]	$\checkmark$	–	–	–
LayoutParser [ 8 ]	–	–	–	–
Ours	$\checkmark$	$\checkmark$	$\checkmark$	$\checkmark$

Table 1: Comparison of document comparison approaches.

\checkmark

= supported, – = not supported.

Panel of Figure 1 — Figure 1: Processing pipeline for PDF revision comparison. Both old and new PDFs feed into fingerprint extraction, followed by multi-phase matching, DP alignment, multi-layer diff, and report generation.

Panel of Figure 2 — Figure 2: The three diff layers computed for each matched page pair. (a) Text diff: deleted lines highlighted red, added lines green, via difflib unified diff. (b) Table diff: changed cells highlighted by cell-level comparison via pdfplumber . (c) Visual diff: OpenCV pixel-difference regions bounded by rectangles.

Method	Prec.	Rec.	F1
Sequential (baseline)	0.22	0.22	0.22
LCS only	1.00	0.67	0.80
Seven-phase only	1.00	0.67	0.80
Ours (full)	1.00	0.67	0.80

Table 2: Page matching accuracy on the 9-page/10-page document pair.

Panel of Figure 3 — Figure 3: Page alignment result for Pair 1 (9-page old revision, 10-page new revision). Solid arrows: matches recovered by the system (6 of 9 ground-truth pairs). Dashed arrows: ground-truth pairs not recovered due to blank pages ( $<$ 50 extracted characters). The red-shaded $N_{2}$ is the inserted page, correctly identified with no false match.

Pair	Pages	Text ext.	Match
Pair 1 (extract)	$9{+}10$	7.7 s	2.8 ms
Pair 2 (full)	$90{+}90$	6.4 s	19 ms

Table 3: Processing time. Hardware: Intel Core i7, CPU only.

Legal Document Analysis

Legal document analysis uses language technologies to classify, extract, compare, and reason over statutes, contracts, policies, and court decisions.

See all 76 papers

DOCFORGE-BENCH: A Comprehensive 0-shot Benchmark for Document Forgery Detection and Analysis
Mar 2, 2026Zengqi Zhao, Weidi Xia, En Wei +7Text Forgery Detection Digital Forensics
University of North Carolina at Chapel Hill · University of California, Irvine · Washington University in St. Louis +4
Source-preserving alignment for robust evidence localization in scientific PDFS
Sep 28, 2026Zihao Liu, Wei Yang, Zixiao Dong +4Document Information Extraction
School of Computer Science and Technology, University of Science and Technology of China · State Key Laboratory of Cognitive Intelligence · University of Science and Technology of China +1
ForMaT: Dataset for Visually-Grounded Multilingual PDF Translation
May 15, 2026Michał Ciesiółka, Dawid Wiśniewski, Adrian Charkiewicz +1Multimodal MT Machine Translation
Laniqo, Pozna´n, Poland · Faculty of Mathematics and Computer Science, Adam Mickiewicz University, Pozna´n, Poland · Pozna´n University of Technology

Mar 2, 2026J/K move · Enter open · S save

DOCFORGE-BENCH: A Comprehensive 0-shot Benchmark for Document Forgery Detection and Analysis

Zengqi Zhao, Weidi Xia, En Wei, Yan Zhang+6

University of North Carolina at Chapel Hill · University of California, Irvine · Washington University in St. Louis+4

Text Forgery Detection Digital Forensics Digital Image Forensics Model Calibration

Open paper AskPDF arXiv

We present DOCFORGE-BENCH, the first unified zero-shot benchmark for document forgery detection, evaluating 14 methods across eight datasets spanning text tampering, receipt forgery, and identity document manipulation. Unlike fine-tuning-oriented evaluations such as ForensicHub [Du et al., 2025], DOCFORGE-BENCH applies all methods with their published pretrained weights and no domain adaptation -- a deliberate design choice that reflects the realistic deployment scenario where practitioners lack labeled document training data. Our central finding is a pervasive calibration failure invisible under single-threshold protocols: methods achieve moderate Pixel-AUC (>=0.76) yet near-zero Pixel-F1. This AUC-F1 gap is not a discrimination failure but a score-distribution shift: tampered regions occupy only 0.27-4.17% of pixels in document images -- an order of magnitude less than in natural image benchmarks -- making the standard tau=0.5 threshold catastrophically miscalibrated. Oracle-F1 is 2-10x higher than fixed-threshold Pixel-F1, confirming that calibration, not representation, is the bottleneck. A controlled calibration experiment validates this: adapting a single threshold on N=10 domain images recovers 39-55% of the Oracle-F1 gap, demonstrating that threshold adaptation -- not retraining -- is the key missing step for practical deployment. Overall, no evaluated method works reliably out-of-the-box on diverse document types, underscoring that document forgery detection remains an unsolved problem. We further note that all eight datasets predate the era of generative AI editing; benchmarks covering diffusion- and LLM-based document forgeries represent a critical open gap on the modern attack surface.

Abstract

Legal Document Analysis

Explore similar work

DOCFORGE-BENCH: A Comprehensive 0-shot Benchmark for Document Forgery Detection and Analysis

Source-preserving alignment for robust evidence localization in scientific PDFS

ForMaT: Dataset for Visually-Grounded Multilingual PDF Translation