app.py

import streamlit as st
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")
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")

# Authorized car database
authorized_cars = {"KA01AB1234", "MH12XY5678", "DL8CAF9090"}

# Detect License Plates
def detect_license_plate(frame):
    pil_image = Image.fromarray(frame)
    inputs = detr_processor(images=pil_image, return_tensors="pt")
    outputs = detr_model(**inputs)
    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

# Recognize Text from Plates
def recognize_text_from_plate(cropped_plate):
    inputs = trocr_processor(images=cropped_plate, return_tensors="pt")
    outputs = trocr_model.generate(**inputs)
    return trocr_processor.batch_decode(outputs, skip_special_tokens=True)[0]

# 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}"

# 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:
            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.rectangle(box.tolist(), outline="red", width=3)
            draw.text((box[0], box[1]), plate_text, fill="red")

        # Return processed frame
        processed_frame = np.array(pil_image)
        for plate_text in recognized_plates:
            st.write(verify_plate(plate_text))
        return av.VideoFrame.from_ndarray(processed_frame, format="bgr24")

# Streamlit UI
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)