added the valid xray image detection code

app.py

@@ -4,7 +4,6 @@ import cv2
 import tempfile
 import os
 import sys
-
 # Add project root to Python path
 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
@@ -13,7 +12,7 @@ from src.predict_fracture import FracturePredictor
 
 # Get current script location
 current_dir = os.path.dirname(os.path.abspath(__file__))
-project_root = os.path.dirname(current_dir)  # Go up from app/ to project root
+project_root = os.path.dirname(current_dir) # Go up from app/ to project root
 
 # CORRECTED MODEL PATHS
 MODEL_PATH = 'models/fracture_detection_model.joblib'
@@ -29,12 +28,51 @@ if os.path.exists(MODEL_PATH) and os.path.exists(ENCODER_PATH):
     predictor = FracturePredictor(model_path=MODEL_PATH, encoder_path=ENCODER_PATH)
 else:
     print("ERROR: Model files not found. Please run training first.")
+    # Provide detailed troubleshooting help
+    print(f"Current working directory: {os.getcwd()}")
+    print(f"Files in models directory: {os.listdir(os.path.join(project_root, 'models'))}")
     exit(1)
 
+def is_xray_image(img):
+    """Validate if image is an X-ray using intensity distribution"""
+    try:
+        if isinstance(img, np.ndarray):
+            # Convert to grayscale if needed
+            if len(img.shape) == 3 and img.shape[2] == 3:
+                img_gray = np.dot(img[...,:3], [0.2989, 0.5870, 0.1140])
+            elif len(img.shape) == 3 and img.shape[2] == 4:
+                img_gray = np.dot(img[...,:3], [0.2989, 0.5870, 0.1140])
+            else:
+                img_gray = img if len(img.shape) == 2 else img[:, :, 0]
+        else:
+            # Handle file path
+            img_array = cv2.imread(img, cv2.IMREAD_GRAYSCALE)
+            if img_array is None:
+                return False
+            img_gray = np.array(img_array)
+        
+        # Calculate statistics
+        mean_intensity = np.mean(img_gray)
+        std_intensity = np.std(img_gray)
+        
+        # X-ray characteristics:
+        # - Moderate brightness (not too dark/light)
+        # - Reasonable contrast
+        is_valid = (20 <= mean_intensity <= 230) and (std_intensity >= 10)
+        return is_valid
+        
+    except Exception as e:
+        print(f"Validation error: {str(e)}")
+        return False
+
 def predict_fracture(img):
     """Process uploaded image and return prediction results"""
     try:
-        # Handle different input types
+        # Step 1: Validate if it's an X-ray
+        if not is_xray_image(img):
+            return "⚠️ Not an X-ray image", "Upload a valid X-ray", None
+        
+        # Step 2: Process the image
         if isinstance(img, np.ndarray):
             # Convert to BGR format for OpenCV
             if img.shape[2] == 4:  # RGBA image
@@ -50,10 +88,10 @@ def predict_fracture(img):
             # Already a file path
             tmp_path = img
         
-        # Get prediction
+        # Step 3: Get prediction
         label, confidence, vis_path = predictor.predict(tmp_path)
         
-        # Read visualization image
+        # Step 4: Read visualization
         vis_img = cv2.imread(vis_path)
         if vis_img is not None:
             vis_img = cv2.cvtColor(vis_img, cv2.COLOR_BGR2RGB)
@@ -92,4 +130,3 @@ if __name__ == "__main__":
         server_port=7860,
         share=True  # Add this line to enable public access
     )
-