Update app.py

app.py

@@ -75,11 +75,9 @@ def custom_nms(preds, iou_threshold=0.7):
             filtered_preds.append(pred)
     return filtered_preds
 
-# The process_image function merges the box detection code (from your 1st prompt)
-# with the ArUco marker detection and measurement (from the code you provided now).
-# The only change is an added step to slightly expand each detected box (by 5%)
-# before drawing and computing its size. This extra "padding" has been found to
-# improve the accuracy of the measured dimensions.
+# This function merges the robust box-detection from your first prompt
+# (including upscaling if needed, prediction processing, and custom NMS)
+# with the ArUco marker detection & measurement exactly as in your current code.
 def process_image(job_id, image_path, object_type, multiplier):
     try:
         jobs[job_id]['progress'] = 10
@@ -102,8 +100,7 @@ def process_image(job_id, image_path, object_type, multiplier):
                 jobs[job_id]['result'] = {"error": "Roboflow model not available."}
                 return
 
-            # --- BOX DETECTION (from your 1st prompt) ---
-            # Upscale the image if it is small to help detect small boxes.
+            # --- BOX DETECTION (exactly as in your first prompt) ---
             scale_factor = 1
             if img_width < 1000 or img_height < 1000:
                 scale_factor = 2
@@ -147,7 +144,6 @@ def process_image(job_id, image_path, object_type, multiplier):
                 except Exception as e:
                     continue
 
-            # Use a higher NMS IoU threshold to avoid merging valid nearby detections.
             box_detections = custom_nms(processed_preds, iou_threshold=0.7)
             jobs[job_id]['progress'] = 60
 
@@ -176,26 +172,15 @@ def process_image(job_id, image_path, object_type, multiplier):
             except Exception as e:
                 conversion_factor = None
 
-            # --- Draw boxes and compute measurements ---
-            # Here we add a slight expansion (5%) to each detected bounding box
-            # before drawing it and computing its dimensions.
-            expansion_factor = 0.05
+            # --- Draw boxes and compute measurements exactly as in your first prompt ---
             for pred in box_detections:
                 x1, y1, x2, y2 = pred["box"]
-                # Expand the box by 5% on each side
-                box_w = x2 - x1
-                box_h = y2 - y1
-                x1_exp = int(max(0, x1 - box_w * expansion_factor))
-                y1_exp = int(max(0, y1 - box_h * expansion_factor))
-                x2_exp = int(min(img_width - 1, x2 + box_w * expansion_factor))
-                y2_exp = int(min(img_height - 1, y2 + box_h * expansion_factor))
-                
                 label = pred["class"]
                 confidence = pred["confidence"]
-                cv2.rectangle(image, (x1_exp, y1_exp), (x2_exp, y2_exp), (0, 255, 0), thickness)
+                cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), thickness)
                 if conversion_factor is not None:
-                    box_width_pixels = x2_exp - x1_exp
-                    box_height_pixels = y2_exp - y1_exp
+                    box_width_pixels = x2 - x1
+                    box_height_pixels = y2 - y1
                     box_width_cm = box_width_pixels * conversion_factor
                     box_height_cm = box_height_pixels * conversion_factor
                     detection_info.append({
@@ -213,8 +198,8 @@ def process_image(job_id, image_path, object_type, multiplier):
                     })
                 text = f"{label} ({confidence:.2f})"
                 (text_width, text_height), baseline = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)
-                cv2.rectangle(image, (x1_exp, y1_exp - text_height - baseline - 5), (x1_exp + text_width, y1_exp - 5), (0, 255, 0), -1)
-                cv2.putText(image, text, (x1_exp, y1_exp - 5 - baseline), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1)
+                cv2.rectangle(image, (x1, y1 - text_height - baseline - 5), (x1 + text_width, y1 - 5), (0, 255, 0), -1)
+                cv2.putText(image, text, (x1, y1 - 5 - baseline), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1)
 
         elif object_type in {"person", "car"}:
             if yolov5_model is None:
@@ -249,7 +234,7 @@ def process_image(job_id, image_path, object_type, multiplier):
                 jobs[job_id]['result'] = {"error": "Error during YOLOv5 inference."}
                 return
 
-        # Build summary text (drawn on image)
+        # Build summary text drawn on the image
         detection_counts = Counter(det["class"] for det in detection_info)
         if detection_counts:
             top_text = ", ".join(f"{cls}: {count}" for cls, count in detection_counts.items())