I am using Pytesseract in python, to recognize only numbers of 1, 2 and 3 digits, (any) in a screenshot of the screen, but sometimes it is conjugated to numbers with letters, (a = 4) which is a problem. I think the numbers are very smallis the number in screenshot
import pytesseract
from PIL import Image
import cv2
import pyautogui
pytesseract.pytesseract.tesseract_cmd =r"C:\Users\Lenovo\AppData\Local\Tesseract-
OCR\tesseract.exe"
while True:
answer2 = pyautogui.screenshot("answer2.png",region=(456, 51, 28, 14))
im = cv2.imread("answer2.png",1)
answer2 = pytesseract.image_to_string(Image.fromarray(im), config="--psm 6")
answer2=float(answer2)
print(answer2)
Related
Hello everyone, im new hier and want to start learning how machine learning works. So i want to build a machine learning email spam detector in colab, but something seems to be wrong:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import nltk import string
from nltk.corpus import stopwords
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB, GaussianNB
from sklearn import svm
from sklearn.model_selection import GridSearchCV
from google.colab import files
uploaded = files.upload() filename = ('spam.tsv')
content = []
with open(filename, "r") as file_content:
for line in file_content.readlines():
line = line.strip() content.append(line)
spam = line
#print(spam) for testinn if it is working
z = spam['EmailText']
y = spam["Label"]
z_train, z_test,y_train, y_test = train_test_split(z,y,test_size = 0.2)
count_vector = CountVectorizer()
features = count_vector.transform(z_train)
model = svm.SVC()
model.fit(features,y_train)
features_test = count_vector.transform(z_test)
print(model.score(features_test,y_test))`
NotFittedError: Vocabulary not fitted or provided TypeError: string indices must be integers
i tried everything but nothing works really haha
i hope, you can help
thank you
Hi i want to overlay or paste an image on bigger images(have a folder containinf 10 images and want to overlay the smaller images on all 10) and save them in a different folder. I did try somethings but ran into errors.
import scipy.misc
import numpy as np
import os
import cv2
outPath = "C:\darkflow\Augmented Images\augmented_images\.."
cov = cv2.imread("C:\darkflow\Augmented Images\extracted\cover\extracted_cover.jpg")
bgs = [cv2.imread(file) for file in glob.glob("C:\darkflow\Augmented Images\images\*.jpg")]
for bg in bgs:
bg[y_offset:y_offset+s_img.shape[0], x_offset:x_offset+s_img.shape[1]] = cov
f_image = cv2.cvtColor(bg, cv2.COLOR_BGR2RGB)
fullpath = os.path.join(outPath, 'augmented_'+ bg)
misc.imsave(fullpath, f_image)
with this code i get an error : ufunc 'add' did not contain a loop with signature matching types dtype('
I found the answer while looking into the code. My code is
from scipy import ndimage, misc
import scipy.misc
import numpy as np
import os
import cv2
cov = cv2.imread("C:\darkflow\Augmented Images\extracted\cover\extracted_cover.jpg")
bgs = [cv2.imread(file) for file in glob.glob("C:\darkflow\Augmented Images\images\*.jpg")]
d=1
x_offset=100
y_offset= 100
for bg in bgs:
bg[y_offset:y_offset+ cov.shape[0], x_offset:x_offset+ cov.shape[1]] = cov
filename = "images/file_%d.jpg"%d
cv2.imwrite(filename, bg)
d+=1
I need to resize an screenshot taken by mss in order to get better reading by pytesseract and i get it done with pil+pyscreenshot but can't get it to with mss.
from numpy import array, flip
from mss import mss
from pytesseract import image_to_string
from time import sleep
def screenshot():
cap = array(mss().grab({'top': 171, 'left': 1088, 'width': 40, 'height': 17}))
cap = flip(cap[:, :, :3], 2)
return cap
def read(param):
tesseract = image_to_string(param)
return tesseract
while True:
print(read(screenshot()))
sleep(2)
here its working with pyscreenshot
from time import sleep
from PIL import Image, ImageOps
import pyscreenshot as ImageGrab
import pytesseract
while 1:
test = ImageGrab.grab(bbox=(1088,171,1126,187))
testt = ImageOps.fit(test, (50, 28), method=Image.ANTIALIAS)
testt.save('result.png')
read = pytesseract.image_to_string(testt)
print(read)
sleep(2)
And, i don't care about maintain aspect radio, works better that way with pytesseract.
Using TensorFlow I am trying to detect one object(png and grayscale image). I have trained and exported a model.ckpt successfully. Now I am trying to restore the saved model.ckpt for prediction. Here is the script:
import numpy as np
import os
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from collections import defaultdict
from io import StringIO
from matplotlib import pyplot as plt
from PIL import Image
if tf.__version__ != '1.4.0':
raise ImportError('Please upgrade your tensorflow installation to v1.4.0!')
# This is needed to display the images.
#matplotlib inline
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
from utils import label_map_util
from utils import visualization_utils as vis_util
MODEL_NAME = 'melon_graph'
# Path to frozen detection graph. This is the actual model that is used for the object detection.
PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'
# List of the strings that is used to add correct label for each box.
PATH_TO_LABELS = os.path.join('training', 'object_detection.pbtxt')
NUM_CLASSES = 1
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
def load_image_into_numpy_array(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape((im_height, im_width, 1)).astype(np.float64)
# For the sake of simplicity we will use only 2 images:
# If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS.
PATH_TO_TEST_IMAGES_DIR = 'test_images'
TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'te_data{}.png'.format(i)) for i in range(1, 336) ]
# Size, in inches, of the output images.
IMAGE_SIZE = (12, 8)
with detection_graph.as_default():
with tf.Session(graph=detection_graph) as sess:
# Definite input and output Tensors for detection_graph
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Each box represents a part of the image where a particular object was detected.
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represent how level of confidence for each of the objects.
# Score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
num_detections = detection_graph.get_tensor_by_name('num_detections:0')
for image_path in TEST_IMAGE_PATHS:
image = Image.open(image_path)
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
image_np = load_image_into_numpy_array(image)
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
# Actual detection.
(boxes, scores, classes, num) = sess.run([detection_boxes, detection_scores, detection_classes, num_detections], feed_dict={image_tensor: image_np_expanded})
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(image_np,np.squeeze(boxes),np.squeeze(classes).astype(np.float64), np.squeeze(scores), category_index, use_normalized_coordinates=True, line_thickness=5)
plt.figure(figsize=IMAGE_SIZE)
plt.imshow(image_np)
and this is the error
Traceback (most recent call last): File "cochlear_detection.py",
line 81, in
(boxes, scores, classes, num) = sess.run([detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict={image_tensor: image_np_expanded}) File
"/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py",
line 889, in run
run_metadata_ptr) File "/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py",
line 1096, in _run
% (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape()))) ValueError: Cannot feed value of shape (1, 2048, 2048, 1) for Tensor
'image_tensor:0', which has shape '(?, ?, ?, 3)'
I literally copy and pasted the example of how to use the hover tool from bokeh's documentation and I still can't get this damn thing to work. I just want bokeh's hover tool to display the x and y coordinates. I think I've implemented it correctly but let me know if anything's wrong. (The ASCII file reads in flawlessly and the graph plots correctly and all the other tools work)
from bokeh.plotting import *
from bokeh.objects import HoverTool
from collections import OrderedDict
output_notebook()
%matplotlib inline
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import mpld3
from mpld3 import plugins, utils
mpld3.enable_notebook()
from pylab import *
import pandas as pd
chip1 = pd.io.parsers.read_table("Chip1_Buffer_ASCII", sep=";")
chip2 = pd.io.parsers.read_table("Chip2_Buffer_ASCII", sep=";")
chip3 = pd.io.parsers.read_table("Chip3_Buffer_ASCII", sep=";")
chip1_1=chip1
chip1_2=chip2
chip1_3=chip3
chip1_1["Frequency (Hz)"]=chip1["Frequency (Hz)"].map(lambda x: math.log10(x))
chip1_2["Frequency (Hz)"]=chip2["Frequency (Hz)"].map(lambda x: math.log10(x))
chip1_3["Frequency (Hz)"]=chip3["Frequency (Hz)"].map(lambda x: math.log10(x))
diff_1_2 = chip1 - chip2
diff_1_2["Frequency (Hz)"] = chip1_1["Frequency (Hz)"]
source1 = ColumnDataSource(chip1_1.to_dict("list"))
source2 = ColumnDataSource(chip1_2.to_dict("list"))
source3 = ColumnDataSource(chip1_3.to_dict("list"))
source4=ColumnDataSource(diff_1_2.to_dict("list"))
import bokeh.plotting as bk
bk.figure(plot_width=600, # in units of px
plot_height=600,
title="Hello World!",
tools="pan,wheel_zoom,box_zoom,select,reset,hover")
bk.hold()
bk.line("Frequency (Hz)", "-Phase (°)",line_width=2,source=source1,logx=True,color="red",xlim=[0, 10000])
bk.line("Frequency (Hz)", "-Phase (°)",line_width=2,source=source2,logx=True,color="green",xlim=[0, 10000])
bk.line("Frequency (Hz)", "-Phase (°)",line_width=2,source=source3,logx=True,color="orange",xlim=[0, 10000])
bk.line("Frequency (Hz)", "-Phase (°)",line_width=2,source=source4,logx=True,color="orange",xlim=[0, 10000])
hover = bk.curplot().select(dict(type=HoverTool))
hover.tooltips=OrderedDict([
("(x,y)", "($x, $y)"),
("index", "$index")
])
bk.show()