Text Image Enhancer for OCR

# Example: Enhance image before OCR processing
import requests
import pytesseract
from PIL import Image

# 1. Enhance image using TextSharp API
def enhance_for_ocr(image_path):
    with open(image_path, 'rb') as f:
        response = requests.post(
            'https://api.textsharp.com/enhance',
            files={'image': f},
            data={'optimize_for': 'ocr'}
        )
    return response.content

# 2. Process with OCR
enhanced_image = enhance_for_ocr('document.jpg')
text = pytesseract.image_to_string(Image.open(enhanced_image))
print(f"Extracted text: {text}")

# Batch process multiple documents
import os
from concurrent.futures import ThreadPoolExecutor

def process_document(file_path):
    # Enhance image
    enhanced = enhance_for_ocr(file_path)
    
    # Extract text with OCR
    text = pytesseract.image_to_string(enhanced)
    
    # Save results
    output_path = file_path.replace('.jpg', '_extracted.txt')
    with open(output_path, 'w') as f:
        f.write(text)
    
    return len(text.split())

# Process all images in directory
image_files = [f for f in os.listdir('.') if f.endswith('.jpg')]
with ThreadPoolExecutor(max_workers=4) as executor:
    results = executor.map(process_document, image_files)