File size: 2,831 Bytes
ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 be4a6f1 ce847d4 |
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 |
"""
OneOCR — Cross-platform OCR using Microsoft OneOCR engine.
Available backends (auto-selected):
1. OcrEngine: Windows-only DLL wrapper (100% accuracy, fastest)
2. OcrEngineUnified: Auto-selects best backend (DLL → Wine → ONNX)
3. OcrEngineOnnx: Cross-platform ONNX reimplementation (~53% match rate)
Usage:
python main.py <image_path>
python main.py # uses test.png
python main.py --backend dll # force DLL backend
python main.py --backend wine # force Wine backend (Linux)
python main.py --backend onnx # force ONNX backend
"""
import argparse
import sys
from pathlib import Path
from PIL import Image
def main():
parser = argparse.ArgumentParser(description="OneOCR — Cross-platform OCR")
parser.add_argument("image", nargs="?", default="test.png", help="Image path")
parser.add_argument("--backend", "-b", choices=["dll", "wine", "onnx", "auto"],
default="auto", help="OCR backend (default: auto)")
parser.add_argument("--output", "-o", help="Save results to JSON file")
args = parser.parse_args()
if not Path(args.image).exists():
print(f"Image not found: {args.image}")
print(f"Usage: python main.py <image_path>")
sys.exit(1)
img = Image.open(args.image)
print(f"Image: {args.image} ({img.size[0]}x{img.size[1]})")
print()
# Use unified engine (auto-selects best backend)
from ocr.engine_unified import OcrEngineUnified
force = args.backend if args.backend != "auto" else None
engine = OcrEngineUnified(force_backend=force)
result = engine.recognize_pil(img)
print(f"=== Backend: {engine.backend_name.upper()} ===")
print(f"Text: {result.text}")
print(f"Lines: {len(result.lines)}, Confidence: {result.average_confidence:.1%}")
if result.text_angle is not None:
print(f"Angle: {result.text_angle:.1f}")
print()
for i, line in enumerate(result.lines):
words = " | ".join(
f"{w.text} ({w.confidence:.0%})" for w in line.words
)
print(f" L{i}: {words}")
# Save JSON if requested
if args.output:
import json
data = {
"backend": engine.backend_name,
"text": result.text,
"text_angle": result.text_angle,
"lines": [
{
"text": line.text,
"words": [
{"text": w.text, "confidence": w.confidence}
for w in line.words
]
}
for line in result.lines
],
}
Path(args.output).write_text(json.dumps(data, indent=2, ensure_ascii=False))
print(f"\nResults saved to {args.output}")
if __name__ == "__main__":
main()
|