Image OCR

import pytesseract
from PIL import Image
import json
import os

{
  "success": true,
  "filename": "example.jpg",
  "extracted_text": "Full raw text extracted from the image...",
  "confidence": "high|medium|low",
  "metadata": {
    "language_detected": "en",
    "text_regions": 3,
    "has_tables": false,
    "has_handwriting": false
  },
  "warnings": [
    "Text partially obscured in bottom-right corner",
    "Low contrast detected in header section"
  ]
}

import pytesseract
from PIL import Image

def extract_text_from_image(image_path):
    """Extract text from a single image using Tesseract OCR."""
    img = Image.open(image_path)
    text = pytesseract.image_to_string(img)
    return text.strip()

import pytesseract
from PIL import Image

def extract_with_confidence(image_path):
    """Extract text with per-word confidence scores."""
    img = Image.open(image_path)

    # Get detailed OCR data including confidence
    data = pytesseract.image_to_data(img, output_type=pytesseract.Output.DICT)

    words = []
    confidences = []

    for i, word in enumerate(data['text']):
        if word.strip():  # Skip empty strings
            words.append(word)
            confidences.append(data['conf'][i])

    # Calculate average confidence
    avg_confidence = sum(c for c in confidences if c > 0) / len([c for c in confidences if c > 0]) if confidences else 0

    return {
        'text': ' '.join(words),
        'average_confidence': avg_confidence,
        'word_count': len(words)
    }

import pytesseract
from PIL import Image
import json
import os

def ocr_to_json(image_path):
    """Perform OCR and return results as JSON."""
    filename = os.path.basename(image_path)
    warnings = []

    try:
        img = Image.open(image_path)

        # Get detailed OCR data
        data = pytesseract.image_to_data(img, output_type=pytesseract.Output.DICT)

        # Extract text preserving structure
        text = pytesseract.image_to_string(img)

        # Calculate confidence
        confidences = [c for c in data['conf'] if c > 0]
        avg_conf = sum(confidences) / len(confidences) if confidences else 0

        # Determine confidence level
        if avg_conf >= 80:
            confidence = "high"
        elif avg_conf >= 50:
            confidence = "medium"
        else:
            confidence = "low"
            warnings.append(f"Low OCR confidence: {avg_conf:.1f}%")

        # Count text regions (blocks)
        block_nums = set(data['block_num'])
        text_regions = len([b for b in block_nums if b > 0])

        result = {
            "success": True,
            "filename": filename,
            "extracted_text": text.strip(),
            "confidence": confidence,
            "metadata": {
                "language_detected": "en",
                "text_regions": text_regions,
                "has_tables": False,
                "has_handwriting": False
            },
            "warnings": warnings
        }

    except Exception as e:
        result = {
            "success": False,
            "filename": filename,
            "extracted_text": "",
            "confidence": "low",
            "metadata": {
                "language_detected": "unknown",
                "text_regions": 0,
                "has_tables": False,
                "has_handwriting": False
            },
            "warnings": [f"OCR failed: {str(e)}"]
        }

    return result

# Usage
result = ocr_to_json("document.jpg")
print(json.dumps(result, indent=2))

import pytesseract
from PIL import Image
import json
import os
from pathlib import Path

def process_image_directory(directory_path, output_file):
    """Process all images in a directory and save results."""
    image_extensions = {'.jpg', '.jpeg', '.png', '.webp'}
    results = []

    for file_path in sorted(Path(directory_path).iterdir()):
        if file_path.suffix.lower() in image_extensions:
            result = ocr_to_json(str(file_path))
            results.append(result)
            print(f"Processed: {file_path.name}")

    # Save results
    with open(output_file, 'w') as f:
        json.dump(results, f, indent=2)

    return results

# Specify language (default is English)
text = pytesseract.image_to_string(img, lang='eng')

# Multiple languages
text = pytesseract.image_to_string(img, lang='eng+fra+deu')

# PSM 3: Fully automatic page segmentation (default)
text = pytesseract.image_to_string(img, config='--psm 3')

# PSM 4: Assume single column of text
text = pytesseract.image_to_string(img, config='--psm 4')

# PSM 6: Assume uniform block of text
text = pytesseract.image_to_string(img, config='--psm 6')

# PSM 11: Sparse text - find as much text as possible
text = pytesseract.image_to_string(img, config='--psm 11')

from PIL import Image, ImageFilter, ImageOps

def preprocess_image(image_path):
    """Preprocess image for better OCR results."""
    img = Image.open(image_path)

    # Convert to grayscale
    img = img.convert('L')

    # Increase contrast
    img = ImageOps.autocontrast(img)

    # Apply slight sharpening
    img = img.filter(ImageFilter.SHARPEN)

    return img

# Use preprocessed image for OCR
img = preprocess_image("document.jpg")
text = pytesseract.image_to_string(img)