egullickson/motovaultpro
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: VIN OCR scanning fails with "No VIN Pattern found" on all images (#113) #114

Merged
egullickson merged 15 commits from issue-113-fix-vin-ocr-scanning into main 2026-02-07 15:47:37 +00:00
Conversation 0 Commits 15 Files Changed 11 +3 -2
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 432b3bda36 - Show all commits

5
ocr/app/extractors/vin_extractor.py
View File

@@ -299,11 +299,12 @@ class VinExtractor(BaseExtractor):
# Configure Tesseract for VIN extraction # Configure Tesseract for VIN extraction
# OEM 1 = LSTM neural network engine (best accuracy) # OEM 1 = LSTM neural network engine (best accuracy)
# Disable dictionaries since VINs are not dictionary words # NOTE: tessedit_char_whitelist does NOT work with OEM 1 (LSTM).
# Using it causes empty/erratic output. Character filtering is
# handled post-OCR by vin_validator.correct_ocr_errors() instead.
config = ( config = (
f"--psm {psm} " f"--psm {psm} "
f"--oem 1 " f"--oem 1 "
f"-c tessedit_char_whitelist={self.VIN_WHITELIST} "
f"-c load_system_dawg=false " f"-c load_system_dawg=false "
f"-c load_freq_dawg=false" f"-c load_freq_dawg=false"
) )