Delete test_adaptive_segmentation.py

test_adaptive_segmentation.py

@@ -1,98 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test script for adaptive content-aware segmentation.
-Processes sample documents to validate the improved segmentation approach.
-"""
-
-import os
-import sys
-import logging
-from pathlib import Path
-import cv2
-import numpy as np
-from PIL import Image
-import json
-
-# Configure logging
-logging.basicConfig(level=logging.INFO,
-                  format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-logger = logging.getLogger(__name__)
-
-# Import segmentation module
-from image_segmentation import segment_image_for_ocr, process_segmented_image
-
-# Test documents
-TEST_DOCUMENTS = [
-    "input/baldwin-15th-north.jpg",    # Document with varied text density and uppercase sections
-    "input/americae-retectio.jpg",     # Historical document
-    "input/handwritten-letter.jpg",    # Handwritten document
-]
-
-def test_adaptive_segmentation():
-    """
-    Run the adaptive segmentation on test documents and visualize the results.
-    """
-    # Create output directory
-    output_dir = Path("output") / "adaptive_test"
-    output_dir.mkdir(parents=True, exist_ok=True)
-    
-    results = {}
-    
-    # Process each test document
-    for document_path in TEST_DOCUMENTS:
-        document_file = Path(document_path)
-        if not document_file.exists():
-            logger.warning(f"Test document not found: {document_path}")
-            continue
-            
-        logger.info(f"Processing test document: {document_file.name}")
-        
-        # Process the document
-        segmentation_results = process_segmented_image(document_file, output_dir)
-        
-        # Create a combined visualization
-        if segmentation_results.get('text_regions_coordinates'):
-            # Print analysis
-            logger.info(f"Document: {document_file.name}")
-            logger.info(f"Found {len(segmentation_results['text_regions_coordinates'])} text regions")
-            logger.info(f"Output files: {segmentation_results.get('output_files', {})}")
-            
-            # Store results
-            results[document_file.name] = {
-                "regions_count": len(segmentation_results['text_regions_coordinates']),
-                "output_files": segmentation_results.get('output_files', {}),
-                "regions": segmentation_results.get('text_regions_coordinates', [])
-            }
-    
-    # Save summary report
-    with open(output_dir / "adaptive_segmentation_results.json", "w") as f:
-        json.dump(results, f, indent=2)
-    
-    # Create a summary report
-    with open(output_dir / "adaptive_segmentation_report.md", "w") as f:
-        f.write("# Adaptive Segmentation Test Results\n\n")
-        f.write("This report summarizes the results of testing the adaptive content-aware segmentation approach.\n\n")
-        
-        for document_name, result in results.items():
-            f.write(f"## {document_name}\n\n")
-            f.write(f"- Regions detected: {result['regions_count']}\n")
-            f.write(f"- Output files:\n")
-            for file_type, file_path in result.get('output_files', {}).items():
-                f.write(f"  - {file_type}: {file_path}\n")
-            f.write("\n")
-            
-            # Add region analysis
-            if result.get('regions'):
-                f.write("### Region Analysis\n\n")
-                f.write("| Region | X | Y | Width | Height |\n")
-                f.write("|--------|---|---|-------|--------|\n")
-                for i, region in enumerate(result['regions']):
-                    x, y, w, h = region
-                    f.write(f"| {i+1} | {x} | {y} | {w} | {h} |\n")
-                f.write("\n")
-    
-    logger.info(f"Test completed. Results saved to {output_dir}")
-    logger.info(f"Summary report: {output_dir / 'adaptive_segmentation_report.md'}")
-
-if __name__ == "__main__":
-    test_adaptive_segmentation()