Update app.py

app.py

@@ -1,9 +1,10 @@
 import streamlit as st
-import cv2
-import numpy as np
-from PIL import Image, ImageDraw
+from streamlit_webrtc import webrtc_streamer, VideoProcessorBase
+import av
 from transformers import DetrImageProcessor, DetrForObjectDetection, TrOCRProcessor, VisionEncoderDecoderModel
+from PIL import Image, ImageDraw
 import torch
+import numpy as np
 
 # Load Models
 detr_processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
@@ -11,20 +12,14 @@ detr_model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
 trocr_processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-stage1")
 trocr_model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-stage1")
 
-# Streamlit App Configuration
-st.title("Real-Time Car Number Plate Recognition")
-st.write("This app uses Hugging Face Transformers, OpenCV, and Streamlit for detecting and recognizing car number plates in real-time.")
-
-# Authorized Car Database
-authorized_cars = {"KA01AB1234", "MH12XY5678", "DL8CAF9090"}  # Dummy data for verification
+# Authorized car database
+authorized_cars = {"KA01AB1234", "MH12XY5678", "DL8CAF9090"}
 
 # Detect License Plates
 def detect_license_plate(frame):
-    pil_image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+    pil_image = Image.fromarray(frame)
     inputs = detr_processor(images=pil_image, return_tensors="pt")
     outputs = detr_model(**inputs)
-
-    # Post-process outputs to get bounding boxes
     target_sizes = torch.tensor([pil_image.size[::-1]])
     results = detr_processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)
     return results[0]["boxes"], pil_image
@@ -35,56 +30,35 @@ def recognize_text_from_plate(cropped_plate):
     outputs = trocr_model.generate(**inputs)
     return trocr_processor.batch_decode(outputs, skip_special_tokens=True)[0]
 
-# Verify Plate Text
+# Verify Plate
 def verify_plate(plate_text):
     if plate_text in authorized_cars:
         return f"✅ Access Granted: {plate_text}"
     else:
         return f"❌ Access Denied: {plate_text}"
 
-# Real-Time Video Processing with OpenCV
-def live_feed():
-    cap = cv2.VideoCapture(0)  # Open webcam
-    if not cap.isOpened():
-        st.error("Unable to access the camera.")
-        return
-
-    stframe = st.image([])  # Placeholder for video feed
-
-    while True:
-        ret, frame = cap.read()
-        if not ret:
-            st.error("Failed to capture frame from the camera. Exiting...")
-            break
-
-        # Detect plates
+# Custom Video Processor
+class LicensePlateProcessor(VideoProcessorBase):
+    def recv(self, frame: av.VideoFrame):
+        frame = frame.to_ndarray(format="bgr24")
         boxes, pil_image = detect_license_plate(frame)
         draw = ImageDraw.Draw(pil_image)
 
         recognized_plates = []
         for box in boxes:
-            # Crop and recognize plate
             cropped_plate = pil_image.crop((box[0], box[1], box[2], box[3]))
             plate_text = recognize_text_from_plate(cropped_plate)
             recognized_plates.append(plate_text)
-
-            # Draw box and label
             draw.rectangle(box.tolist(), outline="red", width=3)
             draw.text((box[0], box[1]), plate_text, fill="red")
 
-        # Convert back to OpenCV format
-        processed_frame = cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGB2BGR)
-
-        # Stream video to Streamlit
-        stframe.image(processed_frame, channels="BGR", use_column_width=True)
-
-        # Display results
+        # Return processed frame
+        processed_frame = np.array(pil_image)
         for plate_text in recognized_plates:
             st.write(verify_plate(plate_text))
-
-    cap.release()
-    cv2.destroyAllWindows()
+        return av.VideoFrame.from_ndarray(processed_frame, format="bgr24")
 
 # Streamlit UI
-if st.button("Start Camera"):
-    live_feed()
+st.title("Real-Time Car Number Plate Recognition")
+st.write("Streamlit with WebRTC for camera streaming.")
+webrtc_streamer(key="plate-recognition", video_processor_factory=LicensePlateProcessor)