pragnakalp's picture
Update app.py
2d7b88a
raw
history blame
7.1 kB
import gradio as gr
import requests
import tensorflow as tf
import keras_ocr
import cv2
import os
import numpy as np
import pandas as pd
# sender="[email protected]"
# password="httscgatatbbxxur"
# reciever="[email protected]"
# s = smtplib.SMTP_TLS('smtp.gmail.com', 587)
# s.starttls()
# s.ehlo()
# # Pretend the SMTP server supports some forms of authentication.
# smtp.esmtp_features['auth'] = 'LOGIN DIGEST-MD5 PLAIN'
# s.login(sender,password)
# message = """Subject : Appointment Booking\n\n
# Hello,
# Your OCR generated successfully"""
# s.sendmail(sender, reciever, message)
# s.quit()
# mailsend=1
# print("Send mail successfully")
from datetime import datetime
import scipy.ndimage.interpolation as inter
import easyocr
from PIL import Image
from paddleocr import PaddleOCR
import socket
# from send_email_user import send_user_email
from huggingface_hub import HfApi
import smtplib
# api = HfApi()
# api.upload_folder(
# folder_path="/media/pragnakalpl20/Projects/Pragnakalp_projects/gradio_demo/images",
# path_in_repo="my-dataset/images",
# repo_id="pragnakalp/OCR-image-to-text",
# repo_type="dataset",
# ignore_patterns="**/logs/*.txt",
# )
# if not os.path.isdir('images'):
# os.mkdir('images')
# print("create folder--->")
print(os.getcwd())
def get_device_ip_address():
if os.name == "nt":
result = "Running on Windows"
hostname = socket.gethostname()
result += "\nHostname: " + hostname
host = socket.gethostbyname(hostname)
result += "\nHost-IP-Address:" + host
return result
elif os.name == "posix":
gw = os.popen("ip -4 route show default").read().split()
s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
s.connect((gw[2], 0))
ipaddr = s.getsockname()[0]
gateway = gw[2]
host = socket.gethostname()
result = "\nIP address:\t\t" + ipaddr + "\r\nHost:\t\t" + host
return result
else:
result = os.name + " not supported yet."
return result
"""
Paddle OCR
"""
def ocr_with_paddle(img):
finaltext = ''
ocr = PaddleOCR(lang='en', use_angle_cls=True)
# img_path = 'exp.jpeg'
result = ocr.ocr(img)
for i in range(len(result[0])):
text = result[0][i][1][0]
finaltext += ' '+ text
return finaltext
"""
Keras OCR
"""
def ocr_with_keras(img):
output_text = ''
pipeline=keras_ocr.pipeline.Pipeline()
images=[keras_ocr.tools.read(img)]
predictions=pipeline.recognize(images)
first=predictions[0]
for text,box in first:
output_text += ' '+ text
return output_text
"""
easy OCR
"""
# gray scale image
def get_grayscale(image):
return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Thresholding or Binarization
def thresholding(src):
return cv2.threshold(src,127,255, cv2.THRESH_TOZERO)[1]
def ocr_with_easy(img):
gray_scale_image=get_grayscale(img)
thresholding(gray_scale_image)
cv2.imwrite('image.png',gray_scale_image)
reader = easyocr.Reader(['th','en'])
bounds = reader.readtext('image.png',paragraph="False",detail = 0)
bounds = ''.join(bounds)
return bounds
"""
Generate OCR
"""
def generate_ocr(Method,img):
try:
text_output = ''
print("Method___________________",Method)
if Method == 'EasyOCR':
text_output = ocr_with_easy(img)
if Method == 'KerasOCR':
text_output = ocr_with_keras(img)
if Method == 'PaddleOCR':
text_output = ocr_with_paddle(img)
# save_details(Method,text_output,img)
# sender="[email protected]"
# password="httscgatatbbxxur"
# reciever="[email protected]"
# s = smtplib.SMTP_TLS('smtp.gmail.com', 587)
# s.starttls()
# s.ehlo()
# # Pretend the SMTP server supports some forms of authentication.
# smtp.esmtp_features['auth'] = 'LOGIN DIGEST-MD5 PLAIN'
# s.login(sender,password)
# message = """Subject : Appointment Booking\n\n
# Hello,
# Your OCR generated successfully"""
# s.sendmail(sender, reciever, message)
# s.quit()
# mailsend=1
# print("Send mail successfully")
# return text_output
# hostname = socket.gethostname()
# IPAddr = socket.gethostbyname(hostname)
# print(hostname)
# print("\nHost-IP-Address:" + IPAddr)
except Exception as e:
print("Error in ocr generation ==>",e)
text_output = "Something went wrong"
return text_output
"""
Save generated details
"""
def save_details(Method,text_output,img):
# print("//////////")
hostname = get_device_ip_address()
# url = 'https://pragnakalpdev33.pythonanywhere.com/HF_space_image_to_text'
# url = 'http://pragnakalpdev35.pythonanywhere.com/HF_space_image_to_text'
# myobj = {'Method': Method,'text_output':text_output,'img':img.tolist(),'hostname':hostname}
# x = requests.post(url, json = myobj)
# method = []
# img_path = []
# text = []
# input_img = ''
# hostname = ''
# picture_path = "image.jpg"
# curr_datetime = datetime.now().strftime('%Y-%m-%d %H-%M-%S')
# if text_output:
# splitted_path = os.path.splitext(picture_path)
# modified_picture_path = splitted_path[0] + curr_datetime + splitted_path[1]
# cv2.imwrite("myimage.jpg", img)
# with open('savedata.txt', 'w') as f:
# print("write test")
# f.write("testdata")
# print("write Successfully")
# # img = Image.open(r"/home/user/app/")
# # img.save(modified_picture_path)
# input_img = modified_picture_path
# try:
# df = pd.read_csv("AllDetails.csv")
# df2 = {'method': Method, 'input_img': input_img, 'generated_text': text_output}
# df = df.append(df2, ignore_index = True)
# df.to_csv("AllDetails.csv", index=False)
# except:
# method.append(Method)
# img_path.append(input_img)
# text.append(text_output)
# dict = {'method': method, 'input_img': img_path, 'generated_text': text}
# df = pd.DataFrame(dict,index=None)
# df.to_csv("AllDetails.csv")
return send_user_email()
# return x
"""
Create user interface for OCR demo
"""
image = gr.Image(shape=(224, 224),elem_id="img_div")
method = gr.Radio(["EasyOCR", "KerasOCR", "PaddleOCR"],elem_id="radio_div")
output = gr.Textbox(label="Output")
demo = gr.Interface(
generate_ocr,
[method,image],
output,
title="Optical Character Recognition",
description="Try OCR with different methods",
theme="darkpeach",
css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}",
allow_flagging = 'auto'
)
demo.launch(enable_queue = False)