def analyzePixelRelevance():
"simplified implementation of paper: Zintgraf et al - Visualizing Deep Neural Network Decisions: Prediction Difference Analysis"
# setup model
model = Model(open(Constants.fnCharList).read(),
DecoderType.BestPath,
mustRestore=True)
# read image and specify ground-truth text
img = cv2.imread(Constants.fnAnalyze, cv2.IMREAD_GRAYSCALE)
(w, h) = img.shape
assert Model.imgSize[1] == w
# compute probability of gt text in original image
batch = Batch([Constants.gtText], [preprocess(img, Model.imgSize)])
(_, probs) = model.inferBatch(batch,
calcProbability=True,
probabilityOfGT=True)
origProb = probs[0]
grayValues = [0, 63, 127, 191, 255]
if Constants.distribution == 'histogram':
bins = [0, 31, 95, 159, 223, 255]
(hist, _) = np.histogram(img, bins=bins)
pixelProb = hist / sum(hist)
elif Constants.distribution == 'uniform':
pixelProb = [1.0 / len(grayValues) for _ in grayValues]
else:
raise Exception('unknown value for Constants.distribution')
# iterate over all pixels in image
pixelRelevance = np.zeros(img.shape, np.float32)
for x in range(w):
for y in range(h):
# try a subset of possible grayvalues of pixel (x,y)
imgsMarginalized = []
for g in grayValues:
imgChanged = copy.deepcopy(img)
imgChanged[x, y] = g
imgsMarginalized.append(preprocess(imgChanged, Model.imgSize))
# put them all into one batch
batch = Batch([Constants.gtText] * len(imgsMarginalized),
imgsMarginalized)
# compute probabilities
(_, probs) = model.inferBatch(batch,
calcProbability=True,
probabilityOfGT=True)
# marginalize over pixel value (assume uniform distribution)
margProb = sum(
[probs[i] * pixelProb[i] for i in range(len(grayValues))])
pixelRelevance[x, y] = weightOfEvidence(origProb, margProb)
print(x, y, pixelRelevance[x, y], origProb, margProb)
np.save(Constants.fnPixelRelevance, pixelRelevance)
def infer(model, fnImg): "recognize text in image provided by file path" #img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize) img = preprocess(fnImg, Model.imgSize) batch = Batch(None, [img]) (recognized, probability) = model.inferBatch(batch, True) return probability[0], recognized[0]
def infer(model, fnImg):
"recognize text in image provided by file path"
img = preprocessImage(fnImg, Model.imgSize, binary=True)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print('Recognized:', '"' + recognized[0] + '"')
print('Probability:', probability[0])
def infer(model, fnImg):
"recognize text in image provided by file path"
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print('Recognized:', '"' + recognized[0] + '"')
print('Probability:', probability[0])
def infer(model, fnImg):
"recognize text in image provided by file path"
'''img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print('Recognized:', '"' + recognized[0] + '"')
f = open("wordLists.txt","w",encoding='UTF8')
f.write(recognized[0])
f.close()
print('Probability:', probability[0])
'''
wordList = []
file_list = os.listdir(fnImg)
for item in file_list:
print(item)
imgName = fnImg + "\\" + item
img = preprocess(cv2.imread(imgName,cv2.IMREAD_GRAYSCALE),Model.imgSize)
batch = Batch(None,[img])
(recognized,probability) = model.inferBatch(batch, True)
print('Recognized:', '"' + recognized[0] + '"')
wordList.append(recognized[0])
#f = open("C:\\Users\\yea\\.spyder-py3\\answerSheet\\answerwordLists.txt","w",encoding='utf-8')
with codecs.open("/Users/hcy/Desktop/GP/answer/answerwordLists.txt","w",encoding='utf8') as f:
for i in range(0, len(wordList)):
f.write(wordList[i]+"\n")
#f.write(recognized[0])
f.close()
def infer(model, fnImg):
# if fnImg.shape[1] > 200 and fnImg.shape[0] > 60:
# fnImg1 = cv2.resize(fnImg, (100, 32)) # 100, 32 and 85,32
# elif 150 < fnImg.shape[1] < 200 and fnImg.shape[0] > 30:
# fnImg1 = cv2.resize(fnImg, (85, 32))
# else:
# fnImg1 = cv2.resize(fnImg, (65, 32))
if fnImg.shape[1] > 200:
fnImg1 = imutils.resize(fnImg, width=128)
else:
fnImg1 = imutils.resize(fnImg, width=100)
gray = cv2.cvtColor(fnImg1, cv2.COLOR_BGR2GRAY)
# thresh = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY,115,10)
pxmin = np.min(gray)
pxmax = np.max(gray)
imgContrast = (gray - pxmin) / (pxmax - pxmin) * 255
# increased line width
kernel = np.ones((1, 1), np.uint8)
imgMorph = cv2.erode(imgContrast, kernel, iterations=1)
img = preprocess(imgMorph, Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
word = ''
return recognized[0]
def infer(model, fnImg):
#fnImg = fnImg
total_segments = open(path + '/segmented words/total_segments.txt','r')
file = total_segments.read()
file = int(file)
count = 0
for i in range(1,file+1):
segments = open(path + '/segmented words/' + str(i) + '/segments.txt','r')
file1 = segments.read()
file1 = int(file1)
for j in range(file1):
fnImg1 = fnImg + str(i) + '/segment_no_%d' % j + '.png'
for image_path in glob.glob(fnImg1 + "\\*.png"):
image = imageio.imread(image_path)
img = preprocess(image, Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
count+=1
file2 = open(path + '/results/output' + str(i) + '.txt','a')
file2.write(recognized[0])
file2.write(" ")
print('Recognized:', '"' + recognized[0] + '"')
print('Probability:', probability[0])
file3 = open(path + '/results/output' + str(i) + '.txt','a')
file3.write('\n')
def analyzeTranslationInvariance():
# setup model
model = Model(open(Constants.fnCharList).read(),
DecoderType.BestPath,
mustRestore=True)
# read image and specify ground-truth text
img = cv2.imread(Constants.fnAnalyze, cv2.IMREAD_GRAYSCALE)
(w, h) = img.shape
assert Model.imgSize[1] == w
imgList = []
for dy in range(Model.imgSize[0] - h + 1):
targetImg = np.ones((Model.imgSize[1], Model.imgSize[0])) * 255
targetImg[:, dy:h + dy] = img
imgList.append(preprocess(targetImg, Model.imgSize))
# put images and gt texts into batch
batch = Batch([Constants.gtText] * len(imgList), imgList)
# compute probabilities
(texts, probs) = model.inferBatch(batch,
calcProbability=True,
probabilityOfGT=True)
# save results to file
f = open(Constants.fnTranslationInvarianceTexts, 'wb')
pickle.dump(texts, f)
f.close()
np.save(Constants.fnTranslationInvariance, probs)
def testing():
imgdirs = os.listdir('../data/')
decoderType = DecoderType.BestPath
model = Model(open(FilePaths.fnCharList).read(),
decoderType,
mustRestore=True)
output = ''
for (j, dire) in enumerate(imgdirs):
imgFiles = os.listdir('../data/' + dire)
# print(imgFiles)
for (i, f) in enumerate(imgFiles):
#fnImg=input("Enter the image path in '../data/_____' format\n")
#fnImg=FilePaths.fnInfer
fnImg = '../data/' + str(dire) + '/' + f
print('fn=' + fnImg)
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE),
Model.imgSize)
batch = Batch(None, [img] * Model.batchSize
) # fill all batch elements with same input image
recognized = model.inferBatch(batch) # recognize text
print('Recognized:', '"' + recognized[0] + '"')
output = output + recognized[0] + ' '
output = output + '\n'
print(output)
def infer(model, input_image):
""" recognize input image """
img = preprocess(cv.imread(input_image, cv.IMREAD_GRAYSCALE), Model.image_size)
batch = Batch(None, [img])
recognized = model.infer_batch(batch)
print('Recognized:', '"' + recognized[0] + '"')
def infer(filePath):
"recognize text in image provided by file path"
model = Model(open(fnCharList).read(), mustRestore=True)
img = preprocess(cv2.imread(fnInfer, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img] * Model.batchSize)
recognized = model.inferBatch(batch)
print('Recognized:', '"' + recognized[0] + '"')
def make_batches(folder_name, images_list):
# Sort the images_list lexicographically
# print(images_list)
images_list.sort()
# print(images_list)
max_images_per_batch = 60
quo = len(images_list) // max_images_per_batch
rem = len(images_list) % max_images_per_batch
batch_range = range(0, max_images_per_batch)
batches_list = []
images_filepaths = []
cnt = 0
while (quo > 0):
new_images = []
gtTexts = [None for i in range(max_images_per_batch)]
imgs = [
preprocess(
cv2.imread(folder_name + "/" + images_list[i],
cv2.IMREAD_GRAYSCALE), img_size)
for i in range(cnt * max_images_per_batch, (cnt + 1) *
max_images_per_batch)
]
batches_list.append(Batch(gtTexts, imgs))
for i in range(cnt * max_images_per_batch,
(cnt + 1) * max_images_per_batch):
new_images.append(folder_name + "/" + images_list[i])
cnt += 1
quo -= 1
images_filepaths.append(new_images)
if (quo == 0 and rem > 0):
new_images = []
gtTexts = [None for i in range(rem)]
imgs = [
preprocess(
cv2.imread(folder_name + "/" + images_list[i],
cv2.IMREAD_GRAYSCALE), img_size)
for i in range(cnt * max_images_per_batch, len(images_list))
]
batches_list.append(Batch(gtTexts, imgs))
for i in range(cnt * max_images_per_batch, len(images_list)):
new_images.append(folder_name + "/" + images_list[i])
images_filepaths.append(new_images)
return batches_list, images_filepaths
def infer(model, fnImg):
"""recognize text in image provided by file path"""
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
# print('Probability:', '"' + str(round(float(probability[0]) * 100, 2)) + '%"')
return recognized[0]
def infer(model, fnImg, sentence_list, img_num):
"recognize text in image provided by file path"
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(
None, [img] *
Model.batchSize) # fill all batch elements with same input image
recognized = model.inferBatch(batch) # recognize text
sentence_list.append((img_num, recognized[0]))
def infer(model, fnImg):
"recognize text in image provided by file path"
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img] * Model.batchSize) # fill all batch elements with same input image
recognized = model.inferBatch(batch) # recognize text
# print('Recognized:', '"' + recognized[0] + '"') # all batch elements hold same result
# print(recognized[0])
return recognized[0]
def infer(model, fnImg):
""" Recognize text in image provided by file path """
img = preprocessor(fnImg, model.imgSize, binary=True)
# Fill all batch elements with same input image
batch = Batch(None, [img] * Model.batchSize)
recognized = model.inferBatch(batch) # recognize text
# All batch elements hold same result
print('Recognized:', '"' + recognized[0] + '"')
def infer(model, wordImg):
"recognize text in image provided by file path"
img = preprocess(wordImg, Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
#print('Recognized:', '"' + recognized[0] + '"')
#print('Probability:', probability[0])
return recognized[0]
def infer(model, fnImg):
"recognize text in image provided by file path"
img = cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE)
ret, img = cv2.threshold(img, 155, 255, cv2.THRESH_BINARY)
img = preprocess(img, Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print('Recognized:', '"' + recognized[0] + '"')
print('Probability:', probability[0])
def classify(model, img):
print(img.shape)
img = cv2.resize(img, Model.imgSize)
img = preprocess2(img, Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print('Recognized:', '""' + recognized[0] + '""')
print('Probability: ', probability[0])
return (probability[0], recognized[0])
def infer(model, fnImg):
"recognize text in image provided by file path"
input_path = glob.glob(fnImg)
for file in input_path:
img = preprocess(cv2.imread(file, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print('Image: ',str(os.path.basename(file)))
print('Recognized:', '"' + recognized[0] + '"')
print('Probability:', probability[0])
def predict():
if request.method == 'POST':
img = np.array(
Image.open(io.BytesIO(
request.files['image'].read())).convert('L'))
img = preprocess(img, Model.imgSize, True)
batch = Batch(None, [img])
recognized, probability = model.inferBatch(batch, True)
return 'Prediction: {}'.format(recognized[0])
return 'Please upload an image'
def infer_model():
img = preprocess(cv2.imread('data/test.png', cv2.IMREAD_GRAYSCALE),
Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
#
return jsonify({
'recognized': str(recognized[0]),
'probability': str(probability[0])
})
def infer(model, fnImg):
"recognize text in image provided by file path"
#image = cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE)
# cv2.cvtColor(fnImg, cv2.COLOR_BGR2GRAY)
# image = cv2.resize(image,(500,500))
img = preprocess(fnImg, Model.imgSize)
batch = Batch(None, [img] * Model.batchSize)
recognized = model.inferBatch(batch)
print('Recognized:', '"' + recognized[0] + '"')
return recognized[0]
def infer(model, fnImg):
"recognize text in image provided by file path"
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img] * Model.batchSize) # fill all batch elements with same input image
recognized = model.inferBatch(batch) # recognize text
print('Recognized:', '"' + recognized[0] + '"') # all batch elements hold same result
f = open('../dataset/recognized/recognized.txt', 'a+')
f.write(recognized[0]+"\n")
f.close()
wordImg = cv2.imread('../dataset/test.png')
def infer(model, fnImg):
"recognize text in image provided by file path"
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img] * Model.batchSize)
(recognized, probability) = model.inferBatch(batch, True)
words = '../data/test.txt'
f = open(words, "w+", encoding="utf-8")
f.write(recognized[0])
print('Probability:', probability[0])
return recognized[0]
def inferBatch(model):
"recognize text in set of images provided by file path"
col_names = [
'Jacard Similarity', 'Cosine similarity', 'Levenstein Similarity',
'Euclidian distance', 'Character Level Accuracy', 'Actual image',
'Predicted Text'
]
df = pd.DataFrame(columns=col_names)
f = open(FilePaths.fnTrain + 'validation.txt')
for line in f:
# ignore comment line
if not line or line[0] == '#':
continue
lineSplit = line.strip().split(' ')
assert len(lineSplit) >= 9
# filename: part1-part2-part3 --> part1/part1-part2/part1-part2-part3.png
fileNameSplit = lineSplit[0].split('-')
fileName = FilePaths.fnTrain + 'validation/' + fileNameSplit[
0] + '/' + fileNameSplit[0] + '-' + fileNameSplit[
1] + '/' + lineSplit[0] + '.png'
# GT text are columns starting at 9
gtText = DataLoader.truncateLabel('self', ' '.join(lineSplit[8:]),
Model.maxTextLen)
# check if image is not empty
if not os.path.getsize(fileName):
#bad_samples.append(lineSplit[0] + '.png')
continue
# put sample into list
#self.samples.append(Sample(gtText, fileName))
img = preprocess(cv2.imread(fileName, cv2.IMREAD_GRAYSCALE),
Model.imgSize)
batch = Batch(None, [img])
try:
(recognized, probability) = model.inferBatch(batch, True)
print('Recognized:', '"' + recognized[0] + '"')
print('Probability:', probability[0])
jaccard_score, cosine_score, levens_score, euclidean_score = get_AccuracyMetrics(
gtText, recognized[0])
acc = getCharacterLevelAccuracy(gtText, recognized[0])
print('Character Accuracy:', acc)
df.loc[len(df)] = [
jaccard_score, cosine_score, levens_score, euclidean_score,
acc, gtText, recognized[0]
]
except:
continue
df.to_csv(r'C:\Projects\Handwriting recognition\Validation_IAM_HAN.csv')
def infer(model, fnImg):
imgs = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize,
True, False)
print('Recognized: ')
text = ""
for img in imgs:
batch = Batch(None, [img])
recognized = model.inferBatch(batch, True)
text = text + " " + recognized[0]
print(text)
return text
def infer(model, fnImg):
"recognize text in image provided by file path"
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print('1) Model: Recognized:', '"' + recognized[0] + '"' + ' Probability:',
probability[0])
output = dictionary_test.input_word(recognized[0], probability[0], fnImg)
return output
def infer(model, fnImg):
"recognize text in image provided by file path"
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print('Recognized:', '"' + recognized[0] + '"')
print('Probability:', probability[0])
file = open("E:/project ml/SimpleHTR-master/dataextract.txt", "w")
file.write(recognized[0] + "\n")
file.close()
messagebox.showinfo("Information",
"SUCCESSFULLY CONVERTED TO DIGITAL TEXT")
def main():
Infilename = sys.argv[1]
img = cv2.imread(Infilename, cv2.IMREAD_GRAYSCALE)
# increase contrast
pxmin = np.min(img)
pxmax = np.max(img)
imgContrast = (img - pxmin) / (pxmax - pxmin) * 255
# increase line width
kernel = np.ones((3, 3), np.uint8)
imgMorph = cv2.erode(imgContrast, kernel, iterations = 1)
img = prepareImg(imgMorph, 50)
res = wordSegmentation(img, kernelSize=25, sigma=11, theta=7, minArea=100)
if os.path.isdir(path):
shutil.rmtree(path)
os.mkdir(path)
for (j, w) in enumerate(res):
(wordBox, wordImg) = w
cv2.imwrite('../SegWords/%d.png'%j, wordImg)
files = []
for filename in sorted(os.listdir(path)):
files.append(os.path.join(path,filename))
decoderType = DecoderType.WordBeamSearch
#decoderType = DecoderType.BeamSearch
#decoderType = DecoderType.BestPath
model = Model(open('../model/charList.txt').read(), decoderType, mustRestore=True)
imgs = []
for fp in files:
imgs.append(preprocess(cv2.imread(fp, cv2.IMREAD_GRAYSCALE), Model.imgSize))
batch = Batch(None, imgs)
(recognized, probability) = model.inferBatch(batch, True)
model = Model(open('../model/charList.txt').read(), decoderType, mustRestore=True)
file1 = open("myfile.txt","w")
l=''
print('The predicted sentence is : ',end="'")
for pw in recognized:
l += pw
l += ' '
print(pw, end=" ")
print("'")
l += '\n'
file1.write(l)
file1.close()
