Spaces:
Running
Running
File size: 5,183 Bytes
1569310 |
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 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
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
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
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)
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):
method = []
img_path = []
text = []
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('images/'+ modified_picture_path, img)
input_img = 'images/'+ 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")
hostname = get_device_ip_address()
return send_user_email(input_img,hostname,text_output,Method)
# return hostname
"""
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;}"
)
# .gradio-container.gap-2 {gap: 10rem;row-gap: 10rem;column-gap: 10rem;}
# .gradio-container {background-color: lightgray}
demo.launch()
# with gr.Blocks(css=".gradio-container {background-color: red}") as demo:
# input = [gr.Image(shape=(224, 224)), gr.Radio(["EasyOCR", "KerasOCR", "PaddleOCR"],text_color="blue")]
# sub_btn = gr.Button("Submit")
# output = gr.Textbox(label="Output")
# event = sub_btn.click(generate_ocr, inputs=input, outputs=output)
# demo.launch()
|