gbanyan/pdf_signature_extraction
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3 Commits 2 Branches 1 Tag
8f231da3bc5960df203465787e7bda87071f9624
Commit Graph

3 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
gbanyan
8f231da3bc Complete OpenCV Method 3 implementation with 86.5% handwriting retention 
- Implemented comprehensive feature analysis based on size, stroke length, and regularity
- Size-based scoring: height >50px indicates handwriting
- Stroke length ratio: >0.4 indicates handwriting
- Irregularity metrics: low compactness/solidity indicates handwriting
- Successfully tested on sample PDF with 2 signatures (楊智惠, 張志銘)
- Created detailed documentation: CURRENT_STATUS.md and NEW_SESSION_HANDOFF.md
- Stable PaddleOCR 2.7.3 configuration documented (numpy 1.26.4, opencv 4.6.0.66)
- Prepared research plan for PP-OCRv5 upgrade investigation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-27 10:35:46 +08:00
gbanyan
479d4e0019 Add PaddleOCR masking and region detection pipeline 
- Created PaddleOCR client for remote server communication
- Implemented text masking + region detection pipeline
- Test results: 100% recall on sample PDF (found both signatures)
- Identified issues: split regions, printed text not fully masked
- Documented 5 solution options in PADDLEOCR_STATUS.md
- Next: Implement region merging and two-stage cleaning
 2025-10-28 22:28:18 +08:00
gbanyan
52612e14ba Add hybrid signature extraction with name-based verification 
Implement VLM name extraction + CV detection hybrid approach to
replace unreliable VLM coordinate system with name-based verification.

Key Features:
- VLM extracts signature names (周寶蓮, 魏興海, etc.)
- CV or PDF text layer detects regions
- VLM verifies each region against expected names
- Signatures saved with person names: signature_周寶蓮.png
- Duplicate prevention and rejection handling

Test Results:
- 5 PDF pages tested
- 7/10 signatures extracted (70% recall)
- 100% precision (no false positives)
- No blank regions extracted (previous issue resolved)

Files:
- extract_pages_from_csv.py: Extract pages from CSV (tested: 100 files)
- extract_signatures_hybrid.py: Hybrid extraction (current working solution)
- extract_handwriting.py: CV-only approach (component)
- extract_signatures_vlm.py: Deprecated VLM coordinate approach
- PROJECT_DOCUMENTATION.md: Complete project history and results
- SESSION_INIT.md: Session handoff documentation
- SESSION_CHECKLIST.md: Status checklist
- NEW_SESSION_PROMPT.txt: Template for next session
- HOW_TO_CONTINUE.txt: Visual handoff guide
- COMMIT_SUMMARY.md: Commit preparation guide
- README.md: Quick start guide
- README_page_extraction.md: Page extraction docs
- README_hybrid_extraction.md: Hybrid approach docs
- .gitignore: Exclude diagnostic scripts and outputs

Known Limitations:
- 30% of signatures missed due to conservative CV parameters
- Text layer method untested (all test PDFs are scanned images)
- Performance: ~24 seconds per PDF

Next Steps:
- Tune CV parameters for higher recall
- Test with larger dataset (100+ files)
- Process full dataset (86,073 files)

🤖 Generated with Claude Code
v1.0-hybrid-70percent 		2025-10-26 23:39:52 +08:00