File size: 3,116 Bytes
dd2ba72 1f353b4 dd2ba72 4735088 dd2ba72 78753d4 dd2ba72 1dd705c d85faf4 bfa5692 1f353b4 e51c033 1f353b4 dd2ba72 e51c033 1f353b4 e51c033 dd2ba72 1f353b4 e51c033 1f353b4 e51c033 1f353b4 dd2ba72 1f353b4 dd2ba72 1f353b4 dd2ba72 1f353b4 dd2ba72 1f353b4 dd2ba72 e51c033 1f353b4 dd2ba72 1f353b4 dd2ba72 1f353b4 28eb4e5 1f353b4 dd2ba72 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
import gradio as gr
import torch
import cv2
import pytesseract
import numpy as np
from PIL import Image
import sys
import os
from ultralytics import YOLO
# Load model
model = YOLO("/home/user/app/best.pt") # আপনি যেই path এ best.pt রেখেছেন
# Frame processing function
def process_frame(frame):
# Resize image to 640x640
frame_resized = cv2.resize(frame, (640, 640))
img = cv2.cvtColor(frame_resized, cv2.COLOR_BGR2RGB)
img_tensor = torch.from_numpy(img).permute(2, 0, 1).float() / 255.0
img_tensor = img_tensor.unsqueeze(0)
# Run inference with the YOLO model (no need to manually apply nms)
results = model(img_tensor, augment=False)
# Extract results (list of detections)
detections = results.xywh[0] # YOLO's detection results
extracted_texts = []
confidences = []
for det in detections:
x_center, y_center, width, height, conf, cls = det.tolist()
if conf > 0.5:
# Convert from YOLO format to bounding box format
x1 = int((x_center - width / 2) * 640)
y1 = int((y_center - height / 2) * 640)
x2 = int((x_center + width / 2) * 640)
y2 = int((y_center + height / 2) * 640)
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
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 plates and extracts Bangla text using OCR (CPU)."
)
interface.launch()
|