app.py

import gradio as gr
import torch
import cv2
import pytesseract
import numpy as np
from PIL import Image
from ultralytics import YOLO

# Load model
model = YOLO("/home/user/app/best.pt")

# Label map
label_map = {0: "Analog", 1: "Digital", 2: "Non-LP"}

def process_frame(frame):
    # Resize to YOLO input shape
    input_img = cv2.resize(frame, (640, 640))
    results = model(input_img)[0]
    detections = results.boxes.data.cpu().numpy()

    extracted_texts = []
    confidences = []

    for det in detections:
        if len(det) < 6:
            continue

        x1, y1, x2, y2, conf, cls = det
        x1, y1, x2, y2 = map(int, [x1, y1, x2, y2])
        label = label_map.get(int(cls), "Unknown")
        percent = f"{conf * 100:.2f}%"

        # Draw box and label on image
        cv2.rectangle(input_img, (x1, y1), (x2, y2), (255, 0, 0), 2)
        cv2.putText(input_img, f"{label}: {percent}", (x1, y1 - 10),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)

        # OCR
        cropped = frame[y1:y2, x1:x2]  # Use original frame for OCR
        if cropped.size > 0:
            gray = cv2.cvtColor(cropped, cv2.COLOR_BGR2GRAY)
            text = pytesseract.image_to_string(gray, config="--psm 6 -l ben")
            extracted_texts.append(text.strip())
            confidences.append(percent)

    # Convert to PIL
    annotated = cv2.cvtColor(input_img, cv2.COLOR_BGR2RGB)
    pil_img = Image.fromarray(annotated)

    return pil_img, "\n".join(extracted_texts), ", ".join(confidences)


def process_input(input_file):
    file_path = input_file.name

    if file_path.endswith(('.mp4', '.avi', '.mov')):
        cap = cv2.VideoCapture(file_path)
        ret, frame = cap.read()
        cap.release()
        if not ret:
            return None, "Couldn't read video", ""
    else:
        frame = cv2.imread(file_path)
        if frame is None:
            return None, "Invalid image", ""

    return process_frame(frame)


interface = gr.Interface(
    fn=process_input,
    inputs=gr.File(type="filepath", label="Upload Image or Video"),
    outputs=[
        gr.Image(type="pil", label="Detected Output"),
        gr.Textbox(label="Detected Text (Bangla)"),
        gr.Textbox(label="Confidence (%)")
    ],
    title="YOLOv10n License Plate Detector (Bangla)",
    description="Upload an image or video. Detects license plates and extracts Bangla text using OCR."
)

interface.launch()