Update app.py

app.py

@@ -1,78 +1,74 @@
 import gradio as gr
 from PIL import Image, ImageDraw, ImageFont
-
-
-# Use a pipeline as a high-level helper
 from transformers import pipeline
 
-
+# Initialize the object detection pipeline
 object_detector = pipeline("object-detection",
-                model="facebook/detr-resnet-50")
-
-
+                         model="facebook/detr-resnet-50")
 
-def draw_bounding_boxes(image, detections, font_path=None, font_size=20):
+def draw_bounding_boxes(image, detections, font_size=20):
     """
     Draws bounding boxes on the given image based on the detections.
-    :param image: PIL.Image object
-    :param detections: List of detection results, where each result is a dictionary containing
-                       'score', 'label', and 'box' keys. 'box' itself is a dictionary with 'xmin',
-                       'ymin', 'xmax', 'ymax'.
-    :param font_path: Path to the TrueType font file to use for text.
-    :param font_size: Size of the font to use for text.
-    :return: PIL.Image object with bounding boxes drawn.
     """
     # Make a copy of the image to draw on
     draw_image = image.copy()
     draw = ImageDraw.Draw(draw_image)
 
-    # Load custom font or default font if path not provided
-    if font_path:
-        font = ImageFont.truetype(font_path, font_size)
-    else:
-        # When font_path is not provided, load default font but it's size is fixed
-        font = ImageFont.load_default()
-        # Increase font size workaround by using a TTF font file, if needed, can download and specify the path
+    # Use default font since custom font paths might not be available
+    font = ImageFont.load_default()
 
     for detection in detections:
         box = detection['box']
-        xmin = box['xmin']
-        ymin = box['ymin']
-        xmax = box['xmax']
-        ymax = box['ymax']
+        xmin = int(box['xmin'])
+        ymin = int(box['ymin'])
+        xmax = int(box['xmax'])
+        ymax = int(box['ymax'])
 
         # Draw the bounding box
         draw.rectangle([(xmin, ymin), (xmax, ymax)], outline="red", width=3)
 
-        # Optionally, you can also draw the label and score
+        # Create label with score
         label = detection['label']
         score = detection['score']
         text = f"{label} {score:.2f}"
 
         # Draw text with background rectangle for visibility
-        if font_path:  # Use the custom font with increased size
-            text_size = draw.textbbox((xmin, ymin), text, font=font)
-        else:
-            # Calculate text size using the default font
-            text_size = draw.textbbox((xmin, ymin), text)
-
-        draw.rectangle([(text_size[0], text_size[1]), (text_size[2], text_size[3])], fill="red")
+        text_bbox = draw.textbbox((xmin, ymin), text, font=font)
+        draw.rectangle([
+            (text_bbox[0], text_bbox[1]),
+            (text_bbox[2], text_bbox[3])
+        ], fill="red")
         draw.text((xmin, ymin), text, fill="white", font=font)
 
     return draw_image
 
-
 def detect_object(image):
-    raw_image = image
-    output = object_detector(raw_image)
-    processed_image = draw_bounding_boxes(raw_image, output)
-    return processed_image
-
-demo = gr.Interface(fn=detect_object,
-                    inputs=[gr.Image(label="Select Image",type="pil")],
-                    outputs="Objects Detector using an images",
-                    description="THIS APPLICATION WILL BE USED TO DETECT OBJECTS INSIDE THE PROVIDED INPUT IMAGE.")
-demo.launch()
-
-# print(output)
-
+    if image is None:
+        return None
+    
+    try:
+        # Detect objects
+        output = object_detector(image)
+        
+        # Draw bounding boxes
+        processed_image = draw_bounding_boxes(image, output)
+        return processed_image
+    except Exception as e:
+        print(f"Error during object detection: {str(e)}")
+        return None
+
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=detect_object,
+    inputs=[
+        gr.Image(label="Upload Image", type="pil")
+    ],
+    outputs=[
+        gr.Image(label="Detected Objects")
+    ],
+    title="Object Detection using image",
+    description="Upload an image to detect and identify objects within it. The application will draw bounding boxes around detected objects and show their labels with confidence scores."
+)
+
+if __name__ == "__main__":
+    demo.launch()