show the exact image that the model analyzed

app.py

@@ -106,45 +106,41 @@ async def full_detection_pipeline(image: UploadFile = File(...)):
         if not detect_faces_roboflow(temp_image_path):
             return JSONResponse(status_code=400, content={"error": "No face detected."})
 
+        # --- NEW: Logic to track which image is used for analysis ---
+        image_for_analysis = raw_image
+
         # First, try to detect eyes on the original image
         print("--- Attempting detection on original image... ---")
         eye_crops, error_msg = detect_eyes_roboflow(temp_image_path, raw_image)
-        
+
         # If that fails, create a mirrored version and try again
         if len(eye_crops) != 2:
             print("--- Original failed. Attempting detection on mirrored image... ---")
-            mirrored_image = cv2.flip(raw_image, 1) # 1 means a horizontal flip
-        
-            # We need a new temporary file for the mirrored image to send to Roboflow
+            mirrored_image = cv2.flip(raw_image, 1)
+            image_for_analysis = mirrored_image # Set the mirrored image as the one to use
+
             with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tmp_mirrored:
                 cv2.imwrite(tmp_mirrored.name, mirrored_image)
                 temp_mirrored_image_path = tmp_mirrored.name
-        
             try:
-                # Run detection again on the new mirrored image
-                # NOTE: We use mirrored_image for cropping, not raw_image
                 eye_crops, error_msg = detect_eyes_roboflow(temp_mirrored_image_path, mirrored_image)
             finally:
-                # Always clean up the second temporary file
                 os.remove(temp_mirrored_image_path)
-        
-        # Finally, after trying both original and mirrored, check if we have a valid result
+
+        # After trying both, check if we have a valid result
         if error_msg or len(eye_crops) != 2:
             return JSONResponse(
                 status_code=400,
                 content={"error": "Could not detect exactly two eyes. Please try another photo."}
             )
-        
-        eye_crops.sort(key=lambda c: cv2.boundingRect(cv2.cvtColor(c, cv2.COLOR_BGR2GRAY))[0])
 
-        # Prepare to store all our results
+        eye_crops.sort(key=lambda c: cv2.boundingRect(cv2.cvtColor(c, cv2.COLOR_BGR2GRAY))[0])
+        
         flags = {}
         eye_images_b64 = {}
 
         for i, eye_crop in enumerate(eye_crops):
             side = "right" if i == 0 else "left"
-
-            # --- NEW: Encode the cropped eye image to Base64 ---
             is_success, buffer = cv2.imencode(".jpg", eye_crop)
             if is_success:
                 eye_images_b64[side] = "data:image/jpeg;base64," + base64.b64encode(buffer).decode("utf-8")
@@ -159,11 +155,18 @@ async def full_detection_pipeline(image: UploadFile = File(...)):
             else:
                 flags[side] = None
 
-        # --- NEW: Include the images in the final response ---
+        # --- NEW: Encode the successfully analyzed image to send back ---
+        is_success_main, buffer_main = cv2.imencode(".jpg", image_for_analysis)
+        analyzed_image_b64 = ""
+        if is_success_main:
+            analyzed_image_b64 = "data:image/jpeg;base64," + base64.b64encode(buffer_main).decode("utf-8")
+
+        # --- NEW: Add the analyzed_image to the final response ---
         return JSONResponse(content={
             "leukocoria": flags,
             "warnings": [],
-            "two_eyes": eye_images_b64 # Add the eye images here
+            "two_eyes": eye_images_b64,
+            "analyzed_image": analyzed_image_b64 # This is the new field
         })
 
     finally: