Spaces:
Configuration error
Configuration error
File size: 2,936 Bytes
f1ba785 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | """ONNX-adjunct Tesseract beam producer for whitelisted numeric crops."""
from __future__ import annotations
from .arabic_tesseract_engine import (
POLARITY_RETRY_MEAN_CONF,
bytes_to_bgr,
extract_structured_numeric_tokens,
invert_polarity,
mean_token_confidence,
noir_filter_preprocess,
tokens_to_text,
)
from .contracts import BeamCandidate, SemanticClass
def _tokens_to_beam(
tokens: list[dict],
text: str,
variant: str,
) -> BeamCandidate | None:
if not text:
return None
confidences = [max(0.0, min(1.0, float(item["confidence"]) / 100.0)) for item in tokens]
if not confidences:
confidences = [0.5] * len(text)
elif len(confidences) < len(text):
mean = sum(confidences) / len(confidences)
confidences = confidences + [mean] * (len(text) - len(confidences))
else:
confidences = confidences[: len(text)]
mean_prob = sum(confidences) / len(confidences)
min_prob = min(confidences)
return BeamCandidate(
text=text,
probability=mean_prob,
min_character_probability=min_prob,
beam_margin=0.15,
character_confidences=tuple(confidences),
character_confidence_sources=tuple("engine" for _ in confidences),
preprocessing_variant=variant,
)
class TesseractNumericRecognizer:
version = "tesseract-numeric-v1"
@staticmethod
def available() -> bool:
try:
import cv2 # noqa: F401
import pytesseract
pytesseract.get_tesseract_version()
return True
except Exception:
return False
def recognize(self, image_bytes: bytes, semantic_class: SemanticClass) -> list[BeamCandidate]:
if not self.available():
return []
try:
bgr = bytes_to_bgr(image_bytes)
except ValueError:
return []
beams: list[BeamCandidate] = []
processed = noir_filter_preprocess(bgr)
tokens = extract_structured_numeric_tokens(
bgr, semantic_class=semantic_class, processed=processed
)
text = tokens_to_text(tokens, semantic_class)
primary = _tokens_to_beam(tokens, text, "tesseract_adaptive")
if primary:
beams.append(primary)
if mean_token_confidence(tokens) < POLARITY_RETRY_MEAN_CONF:
inverted = invert_polarity(processed)
retry_tokens = extract_structured_numeric_tokens(
bgr, semantic_class=semantic_class, processed=inverted
)
retry_text = tokens_to_text(retry_tokens, semantic_class)
retry = _tokens_to_beam(retry_tokens, retry_text, "tesseract_polarity_inverted")
if retry and retry.text not in {item.text for item in beams}:
beams.append(retry)
return beams
|