Update app.py

app.py

@@ -3,24 +3,34 @@ import cv2
 import numpy as np
 from skimage.metrics import structural_similarity as ssim
 
+def preprocess_image(image):
+    # Convert to grayscale
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    # Apply Gaussian blur to reduce noise
+    blurred = cv2.GaussianBlur(gray, (5, 5), 0)
+    return blurred
+
 def compare_images(image1, image2):
-    # Convert images to grayscale
-    gray1 = cv2.cvtColor(image1, cv2.COLOR_BGR2GRAY)
-    gray2 = cv2.cvtColor(image2, cv2.COLOR_BGR2GRAY)
+    # Preprocess images
+    gray1 = preprocess_image(image1)
+    gray2 = preprocess_image(image2)
     
     # Compute SSIM between the two images
     score, diff = ssim(gray1, gray2, full=True)
     diff = (diff * 255).astype("uint8")
     
-    # Threshold the difference image to get regions with major changes
-    _, thresh = cv2.threshold(diff, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
+    # Apply adaptive thresholding for better object isolation
+    _, thresh = cv2.threshold(diff, 30, 255, cv2.THRESH_BINARY_INV)
     
     # Find contours of differences
     contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
     
+    # Filter out small noise using contour area threshold
+    filtered_contours = [cnt for cnt in contours if cv2.contourArea(cnt) > 500]
+    
     # Create a mask to isolate only the significant added object
     mask = np.zeros_like(image1)
-    cv2.drawContours(mask, contours, -1, (255, 255, 255), thickness=cv2.FILLED)
+    cv2.drawContours(mask, filtered_contours, -1, (255, 255, 255), thickness=cv2.FILLED)
     
     # Apply the mask to highlight the object added in the second image
     highlighted = cv2.bitwise_and(image2, mask)