ocr/app/extractors/vin_extractor.py

@@ -299,11 +299,12 @@ class VinExtractor(BaseExtractor):
 
         # Configure Tesseract for VIN extraction
         # 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 = (
             f"--psm {psm} "
             f"--oem 1 "
-            f"-c tessedit_char_whitelist={self.VIN_WHITELIST} "
             f"-c load_system_dawg=false "
             f"-c load_freq_dawg=false"
         )