Match parser evidence rules to the crop's retained context

Cropping changes the evidence available to an OCR parser. A full-image parser may require a nearby field label, while a detector's tight number crop deliberately removes that label. Applying the same label-dependent acceptance rule to both inputs can turn correct recognition into nulls and unnecessary full-image fallback. Define the crop contract separately, retain whole-token, checksum and global ambiguity guards, and preserve the richer-context parser for full-image recovery. Do not manufacture a label to satisfy the latter parser. Neither checksum validity nor a detector proposal proves that the identifier belongs to the intended vehicle; evaluate negative and wrong-region cases separately.

Applies when: An OCR detector returns tight value-only regions but downstream parsing expects surrounding labels. Keywords: OCR RFDETR PaddleOCR crop parser labels checksum ambiguity fallback