File size: 1,958 Bytes
26b8deb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""OCR processing using Tesseract and Pillow."""
from __future__ import annotations
import io
import logging
from typing import Optional

try:
    from PIL import Image, ImageEnhance, ImageFilter
    PIL_AVAILABLE = True
except ImportError:
    PIL_AVAILABLE = False

try:
    import pytesseract
    TESSERACT_AVAILABLE = True
except ImportError:
    TESSERACT_AVAILABLE = False

logger = logging.getLogger(__name__)


def preprocess_image_for_ocr(image: "Image.Image") -> "Image.Image":
    """Enhance image for better OCR accuracy."""
    img = image.convert("L")
    enhancer = ImageEnhance.Contrast(img)
    img = enhancer.enhance(2.0)
    img = img.filter(ImageFilter.SHARPEN)
    w, h = img.size
    if w < 1000:
        scale = 1000 / w
        img = img.resize((int(w * scale), int(h * scale)), Image.LANCZOS)
    return img


def ocr_image(image: "Image.Image", lang: str = "eng") -> str:
    """Run Tesseract OCR on a PIL Image."""
    if not PIL_AVAILABLE:
        raise RuntimeError("Pillow is not installed. Install it with: pip install pillow")
    if not TESSERACT_AVAILABLE:
        raise RuntimeError("pytesseract is not installed. Install it with: pip install pytesseract")
    processed = preprocess_image_for_ocr(image)
    config = "--oem 3 --psm 6"
    text = pytesseract.image_to_string(processed, lang=lang, config=config)
    return text.strip()


def ocr_image_file(path: str, lang: str = "eng") -> str:
    """OCR an image file by path."""
    if not PIL_AVAILABLE:
        raise RuntimeError("Pillow is not installed.")
    with Image.open(path) as img:
        img = img.convert("RGB")
        return ocr_image(img, lang=lang)


def ocr_image_bytes(data: bytes, lang: str = "eng") -> str:
    """OCR image from raw bytes."""
    if not PIL_AVAILABLE:
        raise RuntimeError("Pillow is not installed.")
    with Image.open(io.BytesIO(data)) as img:
        img = img.convert("RGB")
        return ocr_image(img, lang=lang)