app.py

import pandas as pd
import PIL
from PIL import Image
from PIL import ImageDraw
import gradio as gr
import torch
import easyocr
import cv2
import math
import numpy as np

torch.hub.download_url_to_file('https://i.pinimg.com/originals/45/d0/30/45d03054e15f4be731781eecba7458a4.jpg', 'korean.png')
def midpoint(x1, y1, x2, y2):
    x_mid = int((x1 + x2)/2)
    y_mid = int((y1 + y2)/2)
    return (x_mid, y_mid)

def draw_mask(img, bounds):
    draw = ImageDraw.Draw(img, "RGBA")
    for bound in bounds:
        p0, p1, p2, p3 = bound[0]
        
        """
        x0,y0 = p0
        x1,y1 = p1
        x2,y2 = p2
        x3,y3 = p3
        
        x_mid0, y_mid0 = midpoint(x1, y1, x2, y2)
        x_mid1, y_mi1 = midpoint(x0, y0, x3, y3)
        thickness = int(math.sqrt( (x2 - x1)**2 + (y2 - y1)**2 ))
        
        mask = np.zeros(img.shape[:2], dtype="uint8")
        cv2.line(mask, (x_mid0, y_mid0), (x_mid1, y_mi1), 255, thickness)
        img = cv2.inpaint(img, mask, 7, cv2.INPAINT_NS)
        """
        
        draw.polygon((*p0, *p1, *p2, *p3), fill=255) 
    
    #masking
       
    return img
"""    
def remove_text(img,imgwmask):
    masked = cv2.bitwise_and(img, img, mask=imgwmask)
    return img
"""        
def inference(img, lang):
    if lang == "english":
        lang = ['en']
    elif lang == "chinese":
        lang = ['ch_sim']
    elif lang == "korean":
        lang = ['ko']
    else:
        lang = ['ja']
    reader = easyocr.Reader(lang)
    bounds = reader.readtext(img.name)
    im = PIL.Image.open(img.name)
    mask = Image.new("L", im.size, 0)
    #w, h = im.size 
    
    draw_mask(mask, bounds)
    #remove_text(im, mask, bounds)
    lang = ""
    im.save('result.png')
    mask.save('mask.png')
    return ['result.png','mask.png', pd.DataFrame(bounds). iloc[: , 1:2]]

title = 'EasyOCR'
description = 'Gradio demo for EasyOCR. EasyOCR demo supports 80+ languages.To use it, simply upload your image and choose a language from the dropdown menu, or click one of the examples to load them. Read more at the links below.'
article = "<p style='text-align: center'><a href='https://www.jaided.ai/easyocr/'>Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.</a> | <a href='https://github.com/JaidedAI/EasyOCR'>Github Repo</a></p>"
css = ".output_image, .input_image {height: 40rem !important; width: 100% !important;}"
examples = [['korean.png',"korean"]]
choices = [
    "chinese",
    "english",
    "japanese",
    "korean"
]
gr.Interface(
    inference,
    [gr.inputs.Image(type='file', label='Input'),gr.inputs.Dropdown(choices, type="value", default="korean", label='language')],
    [gr.outputs.Image(type='file', label='Output'), gr.outputs.Image(type='file', label='Output'), gr.outputs.Dataframe()],
    title=title,
    description=description,
    article=article,
    examples=examples,
    css=css,
    enable_queue=True
    ).launch(debug=True)