103 lines
3.2 KiB
Python
103 lines
3.2 KiB
Python
|
"""
|
||
|
|
Visualize all template matches on the page to understand what's happening
|
||
|
|
"""
|
||
|
|
import cv2
|
||
|
|
import numpy as np
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
# Load page image
|
||
|
|
page_img_path = "test_reports_full/YDQ23_001838.pdf/doc_page.png"
|
||
|
|
page_img = cv2.imread(str(page_img_path))
|
||
|
|
if page_img is None:
|
||
|
|
print("ERROR: Could not load page image")
|
||
|
|
exit(1)
|
||
|
|
|
||
|
|
h, w = page_img.shape[:2]
|
||
|
|
print(f"Page size: {w}x{h}")
|
||
|
|
|
||
|
|
# Load template
|
||
|
|
template_path = "template/CMA_Logo.png"
|
||
|
|
template = cv2.imread(str(template_path), cv2.IMREAD_GRAYSCALE)
|
||
|
|
if template is None:
|
||
|
|
print("ERROR: Could not load template")
|
||
|
|
exit(1)
|
||
|
|
|
||
|
|
template_h, template_w = template.shape
|
||
|
|
print(f"Template size: {template_w}x{template_h}")
|
||
|
|
|
||
|
|
# Convert page to grayscale
|
||
|
|
page_gray = cv2.cvtColor(page_img, cv2.COLOR_BGR2GRAY)
|
||
|
|
|
||
|
|
# Run template matching
|
||
|
|
result = cv2.matchTemplate(page_gray, template, cv2.TM_CCORR_NORMED)
|
||
|
|
|
||
|
|
# Find all matches above different thresholds
|
||
|
|
print("\nFinding matches at different thresholds:")
|
||
|
|
for threshold in [0.3, 0.5, 0.7, 0.8, 0.9]:
|
||
|
|
loc = np.where(result >= threshold)
|
||
|
|
num_matches = len(loc[0])
|
||
|
|
print(f" Threshold {threshold}: {num_matches} matches")
|
||
|
|
|
||
|
|
# Find top 10 matches
|
||
|
|
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(result)
|
||
|
|
print(f"\nBest match:")
|
||
|
|
print(f" Confidence: {max_val:.3f}")
|
||
|
|
print(f" Location: {max_loc}")
|
||
|
|
print(f" Center: ({max_loc[0] + template_w // 2}, {max_loc[1] + template_h // 2})")
|
||
|
|
|
||
|
|
# Calculate relative position
|
||
|
|
rel_x = (max_loc[0] + template_w // 2) / w * 100
|
||
|
|
rel_y = (max_loc[1] + template_h // 2) / h * 100
|
||
|
|
print(f" Relative position: ({rel_x:.1f}%, {rel_y:.1f}%)")
|
||
|
|
|
||
|
|
# Find all matches above 0.3
|
||
|
|
threshold = 0.3
|
||
|
|
loc = np.where(result >= threshold)
|
||
|
|
|
||
|
|
print(f"\nAll matches above {threshold}:")
|
||
|
|
matches = []
|
||
|
|
for pt in zip(*loc[::-1]):
|
||
|
|
conf = result[pt[1], pt[0]]
|
||
|
|
center_x = pt[0] + template_w // 2
|
||
|
|
center_y = pt[1] + template_h // 2
|
||
|
|
rel_x = center_x / w * 100
|
||
|
|
rel_y = center_y / h * 100
|
||
|
|
|
||
|
|
matches.append({
|
||
|
|
'pos': pt,
|
||
|
|
'conf': conf,
|
||
|
|
'center': (center_x, center_y),
|
||
|
|
'rel': (rel_x, rel_y)
|
||
|
|
})
|
||
|
|
|
||
|
|
# Sort by confidence
|
||
|
|
matches.sort(key=lambda x: x['conf'], reverse=True)
|
||
|
|
|
||
|
|
for i, m in enumerate(matches[:20]):
|
||
|
|
print(f" Match #{i+1}:")
|
||
|
|
print(f" Position: {m['pos']}")
|
||
|
|
print(f" Center: {m['center']}")
|
||
|
|
print(f" Relative: ({m['rel'][0]:.1f}%, {m['rel'][1]:.1f}%)")
|
||
|
|
print(f" Confidence: {m['conf']:.3f}")
|
||
|
|
print()
|
||
|
|
|
||
|
|
# Visualize top 5 matches
|
||
|
|
viz = page_img.copy()
|
||
|
|
for i, m in enumerate(matches[:5]):
|
||
|
|
pt = m['pos']
|
||
|
|
cv2.rectangle(viz, pt, (pt[0] + template_w, pt[1] + template_h), (0, 255, 0), 2)
|
||
|
|
cv2.putText(viz, f"#{i+1}:{m['conf']:.2f}", (pt[0], pt[1] - 10),
|
||
|
|
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1)
|
||
|
|
|
||
|
|
# Draw 60% threshold line
|
||
|
|
threshold_y = int(h * 0.6)
|
||
|
|
cv2.line(viz, (0, threshold_y), (w, threshold_y), (255, 0, 0), 2)
|
||
|
|
cv2.putText(viz, "60% threshold", (10, threshold_y - 10),
|
||
|
|
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 1)
|
||
|
|
|
||
|
|
output_path = "test_reports_full/YDQ23_001838.pdf/all_matches_visualization.png"
|
||
|
|
cv2.imwrite(output_path, viz)
|
||
|
|
print(f"\nVisualization saved to: {output_path}")
|
||
|
|
print(f"Top 5 matches marked with green boxes")
|
||
|
|
print(f"Red line shows 60% threshold (matches below are filtered)")
|