app.py

import gradio as gr
import torch
import cv2
import pytesseract
import numpy as np
from PIL import Image
import sys
import os

import sys
from pathlib import Path
import torch
import dill._dill
from torch.serialization import add_safe_globals, safe_globals

# Add yolov10 directory to Python path
sys.path.append(str(Path(__file__).resolve().parent / "yolov10"))

# Import your custom YOLOv10 model
from ultralytics.nn.tasks import YOLOv10DetectionModel
from ultralytics import YOLO

# Register the required classes/functions
add_safe_globals([YOLOv10DetectionModel, dill._dill._load_type])

# Load your trained YOLOv10 model
with safe_globals([YOLOv10DetectionModel, dill._dill._load_type]):
    model = YOLO('/home/user/app/best.pt')

    
# Frame processing function
def process_frame(frame):
    img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    img_tensor = torch.from_numpy(img).permute(2, 0, 1).float() / 255.0
    img_tensor = img_tensor.unsqueeze(0)

    results = model(img_tensor, augment=False)
    results = model.nms(results)[0]

    extracted_texts = []
    confidences = []

    for det in results:
        x1, y1, x2, y2, conf, cls = det.tolist()
        if conf > 0.5:
            x1, y1, x2, y2 = map(int, (x1, y1, x2, y2))
            cls = int(cls)

            label_map = {0: "Analog", 1: "Digital", 2: "Non-LP"}
            label = label_map.get(cls, "Unknown")
            percent = f"{conf * 100:.2f}%"

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

            # OCR
            lp_crop = frame[y1:y2, x1:x2]
            gray = cv2.cvtColor(lp_crop, cv2.COLOR_BGR2GRAY)
            text = pytesseract.image_to_string(gray, config="--psm 6 -l ben")
            extracted_texts.append(text.strip())
            confidences.append(percent)

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

# Input handler
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", ""

    processed_frame, text, confidence = process_frame(frame)
    processed_pil = Image.fromarray(cv2.cvtColor(processed_frame, cv2.COLOR_BGR2RGB))
    return processed_pil, text, confidence

# Gradio Interface
interface = gr.Interface(
    fn=process_input,
    inputs=gr.File(type="file", 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 plates and extracts Bangla text using OCR (CPU)."
)

interface.launch()