feat: VIN Photo OCR Pipeline (#67) #75

egullickson · 2026-02-02T01:31:56Z

egullickson commented

2026-02-02 01:31:56 +00:00

Summary

Implements VIN-specific OCR extraction in the OCR service with optimized preprocessing and validation.

Add POST /extract/vin endpoint for VIN extraction from photos
VIN-optimized preprocessing: HEIC conversion, grayscale, deskew, CLAHE, denoise, adaptive threshold
VIN validator with check digit validation and common OCR error correction (I->1, O->0, Q->0)
VIN extractor using multiple Tesseract PSM modes (6/7/8) for robustness
Response includes confidence score, bounding box, and alternative candidates
Comprehensive unit tests for validator and preprocessor
Integration tests for VIN extraction endpoint

Files Changed

ocr/app/validators/vin_validator.py - VIN validation with check digit and OCR error correction
ocr/app/preprocessors/vin_preprocessor.py - VIN-optimized image preprocessing
ocr/app/extractors/vin_extractor.py - VIN extraction with pattern matching
ocr/app/routers/extract.py - Added /extract/vin endpoint
ocr/app/models/schemas.py - Added VinExtractionResponse model

Closes #67

Test plan

Unit tests pass for VIN validator
Unit tests pass for VIN preprocessor
Integration tests pass for VIN extraction endpoint
Test with clear VIN sticker photo (>90% confidence expected)
Test with angled VIN plate (>80% confidence expected)
Test with dashboard VIN through windshield (>70% confidence expected)
Processing time <3 seconds verified

Generated with Claude Code

## Summary Implements VIN-specific OCR extraction in the OCR service with optimized preprocessing and validation. - Add `POST /extract/vin` endpoint for VIN extraction from photos - VIN-optimized preprocessing: HEIC conversion, grayscale, deskew, CLAHE, denoise, adaptive threshold - VIN validator with check digit validation and common OCR error correction (I->1, O->0, Q->0) - VIN extractor using multiple Tesseract PSM modes (6/7/8) for robustness - Response includes confidence score, bounding box, and alternative candidates - Comprehensive unit tests for validator and preprocessor - Integration tests for VIN extraction endpoint ### Files Changed - `ocr/app/validators/vin_validator.py` - VIN validation with check digit and OCR error correction - `ocr/app/preprocessors/vin_preprocessor.py` - VIN-optimized image preprocessing - `ocr/app/extractors/vin_extractor.py` - VIN extraction with pattern matching - `ocr/app/routers/extract.py` - Added `/extract/vin` endpoint - `ocr/app/models/schemas.py` - Added VinExtractionResponse model Closes #67 ## Test plan - [ ] Unit tests pass for VIN validator - [ ] Unit tests pass for VIN preprocessor - [ ] Integration tests pass for VIN extraction endpoint - [ ] Test with clear VIN sticker photo (>90% confidence expected) - [ ] Test with angled VIN plate (>80% confidence expected) - [ ] Test with dashboard VIN through windshield (>70% confidence expected) - [ ] Processing time <3 seconds verified Generated with [Claude Code](https://claude.com/claude-code)

egullickson added 1 commit 2026-02-02 01:31:56 +00:00

feat: add VIN photo OCR pipeline (refs #67 )

Deploy to Staging / Build Images (pull_request) Successful in 31s

Details

Deploy to Staging / Deploy to Staging (pull_request) Successful in 31s

Details

Deploy to Staging / Verify Staging (pull_request) Successful in 2m19s

Details

Deploy to Staging / Notify Staging Ready (pull_request) Successful in 8s

Details

Deploy to Staging / Notify Staging Failure (pull_request) Has been skipped

Details

54cbd49171

Implement VIN-specific OCR extraction with optimized preprocessing:

- Add POST /extract/vin endpoint for VIN extraction
- VIN preprocessor: CLAHE, deskew, denoise, adaptive threshold
- VIN validator: check digit validation, OCR error correction (I->1, O->0)
- VIN extractor: PSM modes 6/7/8, character whitelist, alternatives
- Response includes confidence, bounding box, and alternatives
- Unit tests for validator and preprocessor
- Integration tests for VIN extraction endpoint

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

egullickson merged commit 944a5963ab into main

2026-02-02 01:36:27 +00:00

egullickson deleted branch issue-67-vin-ocr-pipeline

2026-02-02 01:36:27 +00:00

egullickson referenced this issue from a commit

2026-02-02 01:36:28 +00:00

Merge pull request 'feat: VIN Photo OCR Pipeline (#67)' (#75) from issue-67-vin-ocr-pipeline into main

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: egullickson/motovaultpro#75