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)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print(f'Recognized: "{recognized[0]}"')
print(f'Probability: {probability[0]}')
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 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(f'Recognized: "{recognized[0]}"')
print(f'Probability: {probability[0]}')
apex = open("D:/SimpleHTR/data/output.txt", "a")
apex.write(recognized[0] + " ")
apex.close()
def infer(model, fnImg):
"recognize text in image provided by file path"
img = preprocess(cv2.imread(fnImg, cv2.IMREAD_GRAYSCALE), Model.imgSize)
print(img.shape)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
print(f'Recognized: "{recognized[0]}"')
print(f'Confidence: {probability[0]}')
recognizedWords = recognized[0].split('-')
word = ""
for i in recognizedWords:
corrected = correct_sentence(i)
word = word + corrected
print(f'Word Recognized after correction: "{word}"')
print("\n\nWriting Output\n\n")
f = open("output.txt", "w")
f.write(f'{word}\n')
f.close()
def infer(model, fnImg):
global prob
global now
global xaxis
global yaxis
"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(f'Recognized: "{recognized[0]}"')
xaxis.append(recognized[0])
print(f'Probability: {probability[0]}')
yaxis.append(probability[0] * 100)
prob = prob + probability[0]
now = now + 1
apex = open("D:/SimpleHTR/data/output.txt", "a")
apex.write(recognized[0] + " ")
apex.close()
def infer(model, Img):
img = preprocess(cv2.cvtColor(Img, cv2.COLOR_BGR2GRAY), Model.imgSize)
batch = Batch(None, [img])
(recognized, probability) = model.inferBatch(batch, True)
return recognized, probability