Update app.py

app.py

@@ -8,7 +8,7 @@ import pickle
 # function which is returning the number of object detected 
 def number_object_detected(image):
     
-    custom_model = YOLO('best.pt') # custome yolo model path
+    custom_model = YOLO('runs/detect/train4/weights/best.pt') # custome yolo model path
     results = custom_model(image,verbose= False)
 
     dic = results[0].names
@@ -20,7 +20,8 @@ def number_object_detected(image):
     for e , count in zip(unique_elements,counts):
         a = dic[e]
         class_count[a] = count
-    return class_count,results
+    print(class_count)
+    return (class_count,results )
 
 
 def car_detection_and_Cropping(image_path):
@@ -46,28 +47,88 @@ def car_detection_and_Cropping(image_path):
       # Load the image using OpenCV
       image = cv2.imread(image_path)
       
-      
       # Crop the image
       crop_image = image[boxes[max_index][1]:boxes[max_index][3], boxes[max_index][0]:boxes[max_index][2]]
 
       # passing the crop image to the detection model
 
-      class_c , result = number_object_detected(crop_image)
+      class_c ,result = number_object_detected(crop_image)
     else:
-      class_c , result = number_object_detected(image_path)
+      class_c ,result= number_object_detected(image_path)
     return class_c ,result
 
 
+severity_points = {
+    'scratch': 1,
+    'dent': 2,
+    'rust': 2,
+    'paint-damage': 2,
+    'crack':2
+}
+
+def calculate_condition_score(detections):
+    total_score = 0
+    for detection, count in detections.items():
+        if detection in severity_points:
+            total_score += severity_points[detection] * count
+    return total_score
+
+def normalize_score(score, max_score):
+    return (score / max_score) * 10
+
 
+## this function will take the image url and call all the related functions
+def estimate_condition(detections):
+    print("Detedtion list",detections)
+    max_possible_score = sum(severity_points.values())  # Assuming all types of damage detected
+    score = calculate_condition_score(detections)
+    normalized_score = normalize_score(score, max_possible_score)
     
+    if normalized_score <= 2:  # If score is low, condition is Excellent
+        print("Condition Excellent")
+        return "Excellent"
+    elif (normalized_score >2 and normalized_score <=7):  # If score is moderately low, condition is Good
+        print("Condition Good")
+        return "Good"
+    elif (normalized_score >7 and normalized_score <15):  # If score is moderate, condition is Fair
+        print("Condition Fair")
+        return "Fair"
+    elif (normalized_score >15 and normalized_score<=20):  # If score is moderately high, condition is Poor
+        print("Condition Poor")
+        return "Poor"
+    else:  # If score is high, condition is Very Poor
+        print("Condition Very Poor")
+        return "Very Poor"
+
+
 
 
 ## loading the model
-def process_data(file):
-    damage , result_image = car_detection_and_Cropping(file)
+def process_data(files):
+    print(files)
+    file_names = [f[0] for f in files]
+    image_r = []
+    print('fileName',file_names)
     
-    return (damage,result_image)
-
-interface = gr.Interface(fn=process_data, inputs=gr.Image(label='Upload Image of Car',type= 'filepath'), 
-                         outputs=[gr.Textbox(label="Number of Objects detected "),gr.Image(label="Process Image")], title=" 🚘Car Scratch and Dent Detection")
+    damage_dic = {}
+
+    for f in file_names:
+        print('image is ',f)
+        damage, result = car_detection_and_Cropping(f)
+        for r in result:
+            im_array = r.plot(pil = True)  # plot a BGR numpy array of predictions
+            array = im_array[..., ::-1]  # Convert BGR to RGB PIL image
+            image_r.append(array)
+        for key in damage.keys():
+                      if key in damage_dic:
+                        damage_dic[key] += damage[key]
+                      else:
+                          damage_dic[key] = damage[key]
+    condition = estimate_condition(damage_dic)
+
+
+    return (condition,image_r)
+
+interface = gr.Interface(fn=process_data, inputs=gr.Gallery(label='Upload Image of Car',type= 'filepath'), 
+                         outputs=[gr.Textbox(label="Number of Objects detected "),gr.Gallery(label='output',type='pil')], title=" 🚘Car Scratch and Dent Detection")
 interface.launch()