I have an image that shows the text "Cafnote". Pytesseract recognizes this, and correctly sets the variable text = "Cafnote". I then check to see if text == 'Cafnote', and if it is, I want to print "Cafnote Found!", but right now the if statement returns false. How would I get this if statement to return true?
import PIL
from cv2 import cv2
import pytesseract
import time
while 1 < 6:
time.sleep(1)
screenshot = pyautogui.screenshot('screenshot.png', region=(1441,198,219,48))
img = cv2.imread(r'screenshot.png')
median = cv2.medianBlur(img,7)
text = pytesseract.image_to_string(median)
print(text)
if text == 'Cafnote':
print("Cafnote Found!")
Related
I am trying to run a OCR function in the background while displaying the findings in a GUI.
The OCR is working fine, but I can't seem to get the GUI started.
I think the issues is that there is not function to start the GUI, but I have not would a solution.
import time
import cv2
import mss
import numpy
import pytesseract
import matplotlib.pyplot as plt
import pandas as pd
from PIL import Image
import PySimpleGUI as sg
import os
import threading
from concurrent.futures import ThreadPoolExecutor
from PIL import Image
import pytesseract
pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
def ocr_function():
with mss.mss() as mss_instance:
mon = mss_instance.monitors[0]
screenshot = mss_instance.grab(mon) #Read all monitor(s)
with mss.mss() as sct:
while True:
im = numpy.asarray(sct.grab(mon))
plt.imshow(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))
text = pytesseract.image_to_string(im) #image to text
time.sleep(5) #One screenshot per 5 seconds
os.system('cls') #Clear output
print(text) #Print the output text
return text #Return text to function
#plt.show()
Output = ocr_function
t = threading.Thread(target=ocr_function) #Create a thread for the OCR function
t.start() #Start the OCR thread
Output = df.sort_values(by=['Match_Acc.','D-level', 'R-level'], ascending=[False, False, False]) # Sort columes
Output = Output[Output['Match_Acc.'] >= 1]
font = ('Areal', 11)
sg.theme('BrownBlue')
data = Output
headings = ['Result', 'Column1','Column2','Column3','D-level','R-level','n_matches','nan','nonnan','Match_Acc.']
df = pd.DataFrame(data)
headings = df.columns.tolist()
data = df.values.tolist()
layout = [[sg.Table(data, headings=headings, justification='left', key='-TABLE-')],
[sg.Button('Run'), sg.Button('Exit')]]
sg.Window("Overview", layout).read(close=True)
I need help to make the pytesseract could select or choose folder or location to save the outputt result.
This is the code that I use
from tkinter import filedialog
import pytesseract as tess
from PIL import Image
tess.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
def extract():
files = filedialog.askopenfilenames(title="Select Images")
text = []
n = len(files)
for i in range(0,n):
img = Image.open(files[i])
text.append(tess.image_to_pdf_or_hocr(img, lang='nld', config='--psm 11 --oem 3'))
text_files = open(f'test{i+1}.pdf',"+wb")
text_files.write(text[i])
if __name__ == "__main__":
extract()
I don't have python background but eager to learn more.
Thanks
I have try few code but still not working.
Even better if someone could write and add the code to make it works
I have a CSV file with url's and box coordinates (x coordinate of the top left corner, y coordinate of the top left corner, x coordinate of the bottom right corner and y coordinate of the bottom right corner) and I would like to acquire the image, crop it based on the coordinates (to 256x256) and then save the image. Unfortunately a solution to download the whole database and then create a separate with cropped images is difficult due to the size of the database. That for, it is necessary to create the image database with cropped images from the beginning. Another way is to save the image and then subsequently crop it and rewrite the initial image (and then i += 1 iterate to the next one).
Would the current approach work or should I use a different method for it? Additonally, how would I save the acquired images to a specified folder, as currently it downloads to the same folder as the script.
import urllib.request
import csv
import numpy as np
import pandas as pd
from io import BytesIO
import requests
from PIL import Image
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
filename = "images"
# open file to read
with open("data_test.csv".format(filename), 'r') as csvfile:
reader = csv.reader(csvfile)
# pop header row (1st row in csv)
header = next(reader)
# iterate on all lines
i = 0
for line in csvfile:
splitted_line = line.split(',')
# check if we have an image URL
if splitted_line[1] != '' and splitted_line[1] != "\n":
response = requests.get(splitted_line[1])
img = Image.open(BytesIO(response.content))
#crop_img = img[splitted_line[2]:splitted_line[3], splitted_line[4]:splitted_line[5]]
#crop_img = img[315:105, 370:173]
img.save(str(i) + ".png")
#crop_img = img[105:105+173,315:315+370]
#[y: y + h, x: x + w]
new_img = img.resize((256, 256))
new_img.save(str(i) + ".png")
imgplot = plt.imshow(img)
plt.show()
# urllib.request.urlopen(splitted_line[1])
print("Image saved for {0}".format(splitted_line[0]))
# img = cv2.imread(img_path, 0)
i += 1
else:
print("No result for {0}".format(splitted_line[0]))
Any further recommendations are welcome.
Edit: The latest version gives me error :
crop_img = img[105:105+173,315:315+370]
TypeError: 'JpegImageFile' object is not subscriptable
I solved the problem using Bytes.IO and some cropping/resizing techniques.
import csv
from io import BytesIO
import requests
from PIL import Image
import matplotlib.pyplot as plt
filename = "images"
# open file to read
with open("data_test.csv".format(filename), 'r') as csvfile:
reader = csv.reader(csvfile)
# pop header row (1st row in csv)
header = next(reader)
# iterate on all lines
i = 0
for line in csvfile:
splitted_line = line.split(',')
# check if we have an image URL
if splitted_line[1] != '' and splitted_line[1] != "\n":
response = requests.get(splitted_line[1])
img = Image.open(BytesIO(response.content))
#im.crop(box) ⇒ 4-tuple defining the left, upper, right, and lower pixel coordinate
left_x = int(splitted_line[2])
top_y = int(splitted_line[3])
right_x = int(splitted_line[4])
bottom_y = int(splitted_line[5])
crop = img.crop((left_x, top_y, right_x, bottom_y))
new_img = crop.resize((256, 256))
"""
# preview new images
imgplot = plt.imshow(new_img)
plt.show()
"""
new_img.save(str(i) + ".png")
print("Image saved for {0}".format(splitted_line[0]))
i += 1
else:
print("No result for {0}".format(splitted_line[0]))
Hope it will help someone. Any optimization recommendations are still welcome.
Im using a csv file as my data source. I want the graph to update based on the radio button selection i make, please find my source code below.
import pandas as pd
import numpy as np
import plotly.graph_objs as go
import dash
import dash_core_components as dcc
import dash_html_components as html
from dash.dependencies import Input,Output
df = pd.read_csv('population2.csv')
fst_yvalues = df['PopEstimate2010']/1000000
scd_yvalues = df['PopEstimate2011']/1000000
trd_yvalues = df['PopEstimate2012']/1000000
app = dash.Dash()
app.layout = html.Div(children=[
html.H1('My first Interactive Graph'),
html.Div(dcc.RadioItems(id='radio_items',
options=[{'label':'PopEstimate2010','value':'pop2010'},
{'label':'PopEstimate2011','value': 'pop2011'},
{'label':'PopEstimate2011' ,'value':'pop2012'}],
value='pop2010')),
html.Br(),
html.Div(children=[
dcc.Graph(id='int_bar')])])
#app.callback(Output('int_bar','figure'),[Input('radio_items','value')])
def bar_chart(value):
trace = []`
if value == 'pop2010':
trarce = [go.Bar(x=df['Name'],y=fst_yvalues)]
elif value == 'pop2011':
trarce = [go.Bar(x=df['Name'],y=scd_yvalues)]
else:
trarce = [go.Bar(x=df['Name'],y=trd_yvalues)]
layout = go.Layout(title='MY FIRST GRAPH',
xaxis=dict(title='MY X-AXIS'),
yaxis=dict(title='MY Y-AXIS'),hovermode='closest')
figure = go.Figure(data=trace,layout=layout)enter code here
return figure
if __name__ == '__main__':
app.run_server(debug=True)
When i try to run this, it only gives me the layout but not the actual graph.
Below is the approach i have taken to get this to work :
#app.callback(Output('int_bar','figure'),[Input('radio_items','value')])
def make_bar_chart(value):
if value == 'pop2010':
figure = {'data': [go.Bar(x=df['Name'],y=fst_yvalues)],
'layout': go.Layout(title='MY FIRST GRAPH',
xaxis=dict(title='MY X-AXIS'),
yaxis=dict(title='MY Y-AXIS'),hovermode='closest')
}
...
...
return figure
if __name__ == '__main__':
app.run_server(debug=True)
I am trying to use this code
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/udacity/5_word2vec.ipynb
But use tf.data to handle all the text data.
I am running both over Google Colaboratory using the GPU runtime option.
Here's is the original relevant code
from __future__ import print_function
import collections
import math
import numpy as np
import os
import random
import tensorflow as tf
import zipfile
from matplotlib import pylab
from six.moves import range
from six.moves.urllib.request import urlretrieve
from sklearn.manifold import TSNE
url = 'http://mattmahoney.net/dc/'
def maybe_download(filename, expected_bytes):
"""Download a file if not present, and make sure it's the right size."""
if not os.path.exists(filename):
filename, _ = urlretrieve(url + filename, filename)
statinfo = os.stat(filename)
if statinfo.st_size == expected_bytes:
print('Found and verified %s' % filename)
else:
print(statinfo.st_size)
raise Exception(
'Failed to verify ' + filename + '. Can you get to it with a browser?')
return filename
filename = maybe_download('text8.zip', 31344016)
def read_data(filename):
"""Extract the first file enclosed in a zip file as a list of words"""
with zipfile.ZipFile(filename) as f:
data = tf.compat.as_str(f.read(f.namelist()[0])).split()
return data
words = read_data(filename)
print('Data size %d' % len(words))
Here is my best attempt to alter this to use tf.data to handle the text data.
from __future__ import print_function
import collections
import math
import numpy as np
import os
import random
import tensorflow as tf
import zipfile
from matplotlib import pylab
from six.moves import range
from six.moves.urllib.request import urlretrieve
from sklearn.manifold import TSNE
url = 'http://mattmahoney.net/dc/'
def maybe_download(filename, expected_bytes):
"""Download a file if not present, and make sure it's the right size."""
if not os.path.exists(filename):
filename, _ = urlretrieve(url + filename, filename)
statinfo = os.stat(filename)
if statinfo.st_size == expected_bytes:
print('Found and verified %s' % filename)
else:
print(statinfo.st_size)
raise Exception(
'Failed to verify ' + filename + '. Can you get to it with a browser?')
return filename
filename = maybe_download('text8.zip', 31344016)
def read_data(filename):
"""Extract the first file enclosed in a zip file as a list of words"""
with zipfile.ZipFile(filename) as f:
data = tf.data.Dataset.from_tensor_slices( f.read(f.namelist()[0]) )
return data
datasetTest = read_data(filename)
Basically I changed this line from the original
data = tf.compat.as_str(f.read(f.namelist()[0])).split()
to this line
data = tf.data.Dataset.from_tensor_slices( f.read(f.namelist()[0]) )
The new one doesn't split the words by space like the old line, so I had another line #datasetTest = datasetTest.map(lambda string: tf.string_split([string]).values) but I commented it out to try to pin point where the bottle neck is.
The old code runs within a minute or two. The new one can never finish executing. It usually runs for 30-40 minutes before colab says it has crashed and is restarting the runtime.