Eric Gullickson
63c027a454
fix: always use min-channel and add grayscale-only OCR path (refs #113 )
...
Deploy to Staging / Build Images (pull_request) Successful in 35s
Deploy to Staging / Deploy to Staging (pull_request) Successful in 50s
Deploy to Staging / Verify Staging (pull_request) Successful in 8s
Deploy to Staging / Notify Staging Ready (pull_request) Successful in 7s
Deploy to Staging / Notify Staging Failure (pull_request) Has been skipped
Two fixes:
1. Always use min-channel for color images instead of gated comparison
that was falling back to standard grayscale (which has only 23%
contrast for white-on-green VIN stickers).
2. Add grayscale-only OCR path (CLAHE + denoise, no thresholding)
between adaptive and Otsu attempts. Tesseract's LSTM engine is
designed to handle grayscale input directly and often outperforms
binarized input where thresholding creates artifacts.
Pipeline order: adaptive threshold → grayscale-only → Otsu threshold
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-06 21:32:52 -06:00
Eric Gullickson
ff3858f750
fix: add debug image saving gated on LOG_LEVEL=debug (refs #113 )
...
Deploy to Staging / Build Images (pull_request) Successful in 36s
Deploy to Staging / Deploy to Staging (pull_request) Successful in 21s
Deploy to Staging / Verify Staging (pull_request) Successful in 8s
Deploy to Staging / Notify Staging Ready (pull_request) Successful in 7s
Deploy to Staging / Notify Staging Failure (pull_request) Has been skipped
Save original, adaptive, and Otsu preprocessed images to
/tmp/vin-debug/{timestamp}/ when LOG_LEVEL is set to debug.
No images saved at info level. Volume mount added for access.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-06 20:26:06 -06:00
Eric Gullickson
d5696320f1
fix: align VIN OCR logging with unified logging design (refs #113 )
...
Deploy to Staging / Build Images (pull_request) Successful in 3m25s
Deploy to Staging / Deploy to Staging (pull_request) Successful in 51s
Deploy to Staging / Verify Staging (pull_request) Successful in 2m36s
Deploy to Staging / Notify Staging Ready (pull_request) Successful in 9s
Deploy to Staging / Notify Staging Failure (pull_request) Has been skipped
Replace filesystem-based debug system (VIN_DEBUG_DIR) with standard
logger.debug() calls that flow through Loki when LOG_LEVEL=DEBUG.
Use .env.logging variable for OCR LOG_LEVEL. Increase image capture
quality to 0.95 for better OCR accuracy.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-06 19:36:35 -06:00
Eric Gullickson
6a4c2137f7
fix: resolve VIN OCR scanning failures on all images (refs #113 )
...
Deploy to Staging / Build Images (pull_request) Successful in 35s
Deploy to Staging / Deploy to Staging (pull_request) Successful in 51s
Deploy to Staging / Verify Staging (pull_request) Successful in 2m31s
Deploy to Staging / Notify Staging Ready (pull_request) Successful in 8s
Deploy to Staging / Notify Staging Failure (pull_request) Has been skipped
Root cause: Tesseract fragments VINs into multiple words but candidate
extraction required continuous 17-char sequences, rejecting all results.
Changes:
- Fix candidate extraction to concatenate adjacent OCR fragments
- Disable Tesseract dictionaries (VINs are not dictionary words)
- Set OEM 1 (LSTM engine) for better accuracy
- Add PSM 11 (sparse text) and PSM 13 (raw line) fallback modes
- Add Otsu's thresholding as alternative preprocessing pipeline
- Upscale small images to meet Tesseract's 300 DPI requirement
- Remove incorrect B->8 and S->5 transliterations (valid VIN chars)
- Fix pre-existing test bug in check digit expected value
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-06 15:57:14 -06:00
Eric Gullickson
54cbd49171
feat: add VIN photo OCR pipeline (refs #67 )
...
Deploy to Staging / Build Images (pull_request) Successful in 31s
Deploy to Staging / Deploy to Staging (pull_request) Successful in 31s
Deploy to Staging / Verify Staging (pull_request) Successful in 2m19s
Deploy to Staging / Notify Staging Ready (pull_request) Successful in 8s
Deploy to Staging / Notify Staging Failure (pull_request) Has been skipped
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 >
2026-02-01 19:31:36 -06:00
