def recognize():
if request.method == 'POST':
# start = current_milli_time()
if 'image' not in request.files:
print('No file part')
return render_template('index.html')
file = request.files['image']
if file.filename == '':
print('No selected file')
return render_template('index.html')
if file:
file.save(os.path.join('images',file.filename))
filename = file.filename
# load the trained model
charClass = Graph(MODEL_LOC)
# load the saved image
image = cv2.cvtColor(cv2.imread("images/"+filename), cv2.COLOR_BGR2RGB)
crop = page.detection(image)
bBoxes = words.detection(crop)
cycler = Cycler.Cycler(crop,bBoxes,charClass)
allWords = []
for i in range(len(bBoxes)-1):
allWords.append(cycler.idxImage(i))
# print(allWords[i])
# stop = current_milli_time()
# print(stop - start)
return jsonify(allWords=allWords)
def process_image(imag):
# %matplotlib inline
IMG = imag
plt.rcParams['figure.figsize'] = (15.0, 10.0)
"""### Global Variables"""
"""## Load image"""
image = cv2.cvtColor(cv2.imread(IMG), cv2.COLOR_BGR2RGB)
implt(image)
# Crop image and get bounding boxes
crop = page.detection(image)
implt(crop)
boxes = words.detection(crop)
lines = words.sort_words(boxes)
implt(crop)
output_file = open("templates/output.html", 'w+')
output_file.write("")
output_file.close()
output_file = open("templates/output.html", 'a+')
for line in lines:
print(" ".join(
[recognise(crop[y1:y2, x1:x2]) for (x1, y1, x2, y2) in line]))
for (x1, y1, x2, y2) in line:
text_det = recognise(crop[y1:y2, x1:x2])
output_file.write(text_det + " ")
output_file.write("\n")
output_file.close()
def apply_with_source_info(self, im, source_info):
image = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
# Crop image and get bounding boxes
im = page.detection(image)
return im
def test_recognize():
charClass = Graph(MODEL_LOC)
# load the saved image
image = cv2.cvtColor(cv2.imread(FILE_LOC), cv2.COLOR_BGR2RGB)
crop = page.detection(image)
bBoxes = words.detection(crop)
cycler = Cycler.Cycler(crop, bBoxes, charClass)
allWords = []
for i in range(len(bBoxes) - 1):
allWords.append(cycler.idxImage(i))
isStructEmpty = structEmpty(allWords)
assert isStructEmpty == False
def main():
Infilename = sys.argv[1]
image = cv2.cvtColor(cv2.imread(Infilename), cv2.COLOR_BGR2RGB)
crop = page.detection(image)
boxes = words.detection(crop)
lines = words.sort_words(boxes)
crop = cv2.cvtColor(crop, cv2.COLOR_RGB2GRAY)
imLines = []
for line in lines:
imLine = []
for (x1, y1, x2, y2) in line:
imLine.append(crop[y1:y2, x1:x2])
imLines.append(imLine)
decoderType = DecoderType.WordBeamSearch
#decoderType = DecoderType.BeamSearch
#decoderType = DecoderType.BestPath
model = Model(open('../model/charList.txt').read(),
decoderType,
mustRestore=True)
file1 = open("myfile.txt", "w")
recognizedL = []
print(
"-------------------Predicted Handwritten Text-------------------------"
)
for line in imLines:
imgs = []
for word in line:
imgs.append(preprocess(word, Model.imgSize))
batch = Batch(None, imgs)
(recognized, probability) = model.inferBatch(batch, True)
l = ""
for pw in recognized:
l += pw
l += ' '
print(pw, end=" ")
print()
l += '\n'
recognizedL.append(l)
file1.writelines(recognizedL)
file1.close()
def textRecog(infilename):
image = cv2.cvtColor(cv2.imread(infilename), cv2.COLOR_BGR2RGB)
crop = page.detection(image)
boxes = words.detection(crop)
lines = words.sort_words(boxes)
crop = cv2.cvtColor(crop, cv2.COLOR_RGB2GRAY)
imLines = []
for line in lines:
imLine = []
for (x1, y1, x2, y2) in line:
imLine.append(crop[y1:y2, x1:x2])
imLines.append(imLine)
#decoderType = DecoderType.WordBeamSearch
#decoderType = DecoderType.BeamSearch
decoderType = DecoderType.BestPath
model = Model(open('./model/charList.txt').read(),
decoderType,
mustRestore=True)
#file1 = open("myfile.txt", "w")
recognizedText = ""
for line in imLines:
imgs = []
for word in line:
imgs.append(preprocess(word, Model.imgSize))
batch = Batch(None, imgs)
(recognized, probability) = model.inferBatch(batch, True)
l = ""
for pw in recognized:
l += pw
l += ' '
recognizedText += l
return recognizedText
def fun(list1):
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf
import cv2
import random
# Import costume functions, corresponding to notebooks
from ocr.normalization import imageNorm, letterNorm
from ocr import page, words
#from ocr import charSeg
from ocr.helpers import implt, resize
from ocr.tfhelpers import Graph
from ocr.datahelpers import idx2char
from src import gsmain
import glob
import os
# ### Global Variables
for x_file in list1:
tf.reset_default_graph()
str1 = ''.join(x_file)
# Settings
IMG = str1 # 1, 2, 3
# ## Load image
image = cv2.cvtColor(cv2.imread(IMG), cv2.COLOR_BGR2RGB)
implt(image)
# Crop image and get bounding boxes
crop = page.detection(image)
implt(crop)
bBoxes = words.detection(crop)
lines = words.sort_words(bBoxes)
filelist = glob.glob("./new3/*.png")
for file in filelist:
os.remove(file)
indeximg = 0
nl = 0
for line in lines:
for (x1, y1, x2, y2) in line:
cv2.imwrite("new3/" + str(indeximg) + ".png", crop[y1:y2,
x1:x2])
#implt(cv2.imread("outcheck.png"))
indeximg = indeximg + 1
#gsmain.FilePaths.fnInfer = ["outcheck.png"]
#wordreco = gsmain.main()
#file.write(wordreco + ' ')
cv2.imwrite("new3/" + str(nl) + "space.png", crop[y1:y2, x1:x2])
nl = nl + 1
#Get all segmented words
list2 = glob.glob("./new3/*.png")
list2.sort(key=os.path.getmtime)
'''list2=list()
for ii in range(0,indeximg):
list2.append("")'''
#all files which have to be infer are loaded
rand_num = random.randint(100, 1000)
cv2.imwrite('final_output/' + str(rand_num) + '.jpg', image)
for i in range(0, len(list2)):
gsmain.FilePaths.fnInfer = gsmain.FilePaths.fnInfer + [list2[i]]
gsmain.main('final_output/' + str(rand_num))
import matplotlib.pyplot as plt import tensorflow as tf import cv2 from PIL import Image import pytesseract import os from ocr.helpers import implt, resize from ocr import page from ocr import words IMG = '1' # 1, 2, 3 filename = "test/2.jpg" save_filename = "test/2_1.jpg" image = cv2.cvtColor(cv2.imread(filename), cv2.COLOR_BGR2RGB) implt(image) crop = page.detection(image) implt(crop) gray = cv2.cvtColor(crop, cv2.COLOR_BGR2GRAY) gray = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1] gray = cv2.medianBlur(gray, 3) implt(gray) cv2.imwrite(save_filename, gray) text = pytesseract.image_to_string(Image.open(save_filename)) os.remove(save_filename) print(text)
plt.rcParams['figure.figsize'] = (15.0, 10.0)
# ### Global Variables
# In[3]:
IMG = "page09" # Image name/number
# # Finding the text areas and words
# In[4]:
# Loading image (converting to RGB)
image = cv2.cvtColor(cv2.imread("../data/pages/%s.jpg" % IMG),
cv2.COLOR_BGR2RGB)
image = page.detection(image)
img = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
implt(img, 'gray')
# In[5]:
def sobel(channel):
""" The Sobel Operator"""
sobelX = cv2.Sobel(channel, cv2.CV_16S, 1, 0)
sobelY = cv2.Sobel(channel, cv2.CV_16S, 0, 1)
# Combine x, y gradient magnitudes sqrt(x^2 + y^2)
sobel = np.hypot(sobelX, sobelY)
sobel[sobel > 255] = 255
return np.uint8(sobel)
def crop_image(image):
return page.detection(image)
