Skip to main content

​
Enabling Metrics

The OCR system automatically tracks metrics for all operations. Metrics include files processed, pages, characters, confidence scores, and processing time. 
from upsonic.ocr import OCR
from upsonic.ocr.easyocr import EasyOCR

# Create OCR instance
ocr = OCR(EasyOCR, languages=['en'])

# Process multiple files
ocr.get_text('document1.pdf')
ocr.get_text('document2.pdf')
ocr.get_text('image.png')

# Get metrics
metrics = ocr.get_metrics()

print(f"Files processed: {metrics.files_processed}")
print(f"Total pages: {metrics.total_pages}")
print(f"Total characters: {metrics.total_characters}")
print(f"Average confidence: {metrics.average_confidence:.2%}")
print(f"Total processing time: {metrics.processing_time_ms:.2f}ms")
print(f"Provider: {metrics.provider}")

# Reset metrics for new batch
ocr.reset_metrics()

​
Analyzing Performance

Use metrics to analyze and optimize OCR performance across different providers and configurations. 
from upsonic.ocr import OCR
from upsonic.ocr.easyocr import EasyOCR
from upsonic.ocr.rapidocr import RapidOCR
from upsonic.ocr.tesseract import TesseractOCR

def benchmark_providers(file_path):
    """Compare performance of different OCR providers."""
    providers = [
        ('EasyOCR', EasyOCR, {'languages': ['en'], 'gpu': False}),
        ('RapidOCR', RapidOCR, {'languages': ['en']}),
        ('Tesseract', TesseractOCR, {'languages': ['eng']})
    ]

    results = {}

    for name, provider_class, params in providers:
        ocr = OCR(provider_class, **params)
        ocr.reset_metrics()

        # Process file
        result = ocr.process_file(file_path)

        # Get metrics
        metrics = ocr.get_metrics()

        results[name] = {
            'confidence': result.confidence,
            'processing_time_ms': result.processing_time_ms,
            'characters': len(result.text)
        }

    # Print comparison
    print("Provider Performance Comparison:")
    for name, data in results.items():
        print(f"\n{name}:")
        print(f"  Confidence: {data['confidence']:.2%}")
        print(f"  Time: {data['processing_time_ms']:.2f}ms")
        print(f"  Characters: {data['characters']}")

    return results

# Run benchmark
benchmark_providers('test_document.pdf')