def calculateErrorRate(groundTruthPath="NewDataset/text/", predictedPath="OutputTextFiles/", statsFile="CER.txt"):
with open(statsFile, 'w') as f:
files = os.listdir(predictedPath)
totalError = 0
for file in files:
realText = ' '.join(getText(groundTruthPath + file))
predictedText = ' '.join(getText(predictedPath + file))
error = levenshtein_distance(realText, predictedText) / len(realText)
totalError += error
f.write(f"file: {file}\t\tCER: {error}\n")
totalError /= len(files)
f.write(f"Total CER: {totalError}")
def img2txt(imgName, txtPath , outfile):
# read image
img = cv2.imread(imgName)
# import pdb; pdb.set_trace()
# segment character from image
print("Segmenting image to characters ...")
segmentedChars = img2Chars(img)
# determine spaces
spaces = [len(l[2]) for l in segmentedChars]
# list of character images only
segmentedChars = [c for l in segmentedChars for c in l[2]]
# compute features of chars
print("\nExtracting features for characters ...")
features = [prepareCharImg(c) for c in segmentedChars]
# predict characters
print("\nPredicting characters ...")
# predictions_prop = model.predict_proba(features)
# predictions = predictions_prop.argsort(axis=1)[:,-3:][:,::-1]
# predictions = np.argmax(predictions_prop, axis=1)
predictions = model.predict(features)
# adding spaces
wordsEncodes = []
for space in spaces: wordsEncodes.append(predictions[:space]); predictions = predictions[space:]
# decoding characters
textList = []
for wordEncoding in wordsEncodes: textList.append(''.join([chars_decode[charCode] for charCode in wordEncoding]))
finalText = ' '.join(textList)
# for wordEncoding in wordsEncodes: textList.append([[chars_decode[charCode] for charCode in charsCode] for charsCode in wordEncoding])
# # import pdb; pdb.set_trace()
# finalText = ' '.join([ ''.join([ c[0] for c in w ]) for w in textList])
# post processing heeeeere
print("\npost processing ...")
# withNGram = postProcessing(textList)
# withNGram = postprocessing_v2(finalText)
withNGram = finalText
# wordsList = loadWordsList()
# text = [getNearestWord(text[i], wordsList) for i in tqdm(range(len(text)))]
# text = ' '.join(text)
# writing text
writeText(outfile, finalText)
# writeText(outfile.split('.')[0] + '-Ngram.txt', withNGram)
originalTxt = getText(txtPath)
# finalText = originalTxt[:4] + finalText[4:]
error = editdistance.eval(finalText, originalTxt) / len(originalTxt)
errorNgram = editdistance.eval(withNGram, originalTxt) / len(originalTxt)
print('acc: ', 1-error, ' acc n gram: ', 1-errorNgram)
return 1-error, 1-errorNgram
def collectAllWords(path):
files = os.listdir(path)
wordSet = set()
for i in tqdm(range(len(files))):
words = getText(path + files[i])
for word in words:
wordSet.add(word)
wordSet = list(wordSet)
with open('all_words.pkl', 'wb') as fid:
cPickle.dump(wordSet, fid)
def saveSeparateLetters(fileName, pathText, pathImg, pathToSave):
image = cv2.imread(pathImg + fileName)
segmentedChars = img2Chars(image)
wordsText = getText(pathText + fileName[:-4] + ".txt")
if len(segmentedChars) == len(wordsText):
print("Saving Segmented Character ...")
for i in tqdm(range(len(segmentedChars))):
realLetters = word2Chars(wordsText[i])
if len(realLetters) == segmentedChars[i][1]:
for j, letImg in enumerate(segmentedChars[i][2]):
cv2.imwrite(
pathToSave + str(chars_codes[realLetters[j]]) +
f"/{lastChars[realLetters[j]]}.png", letImg)
lastChars[realLetters[j]] += 1
def img2txt2(imgName, textFile, outfile):
# read image
img = cv2.imread(imgName)
# real text
realText = ' '.join(getText(textFile))
# segment character from image
print("Segmenting image to characters ...")
segmentedChars = img2Chars(img)
# loading the model
model = loadModel(MODEL_NAME)
f = open(outfile, 'w')
allText = ""
for i in tqdm(range(len(segmentedChars))):
currentWord = ""
for c in segmentedChars[i][2]:
prediction = model.predict([prepareCharImg(c)])
char = chars_decode[prediction[0]]
currentWord += char
allText += char
allText += ' '
f.write(currentWord)
f.write(' ')
f.close()
with open("hello.txt", 'w') as f:
f.write(realText)
f.write("\n\n\n\n")
f.write(allText)
print("\n\n accuracy:")
print(len(allText), len(realText))
print(levenshtein_distance(realText, allText) / len(realText))
print("another accuracy")
realList = realText.split(' ')
allList = allText.split(' ')
errors = 0
for i in range(len(realList)):
errors += levenshtein_distance(realList[i], allList[i])
print(errors / len(realText))
def printSegmentedWordChars(fileName, pathText, pathImg):
image = cv2.imread(pathImg + fileName)
segmentedChars = img2Chars(image)
wordsText = getText(pathText + fileName[:-4] + ".txt")
# if numWords != len(wordsText):
if not os.path.exists(fileName[:-4]):
os.mkdir(fileName[:-4])
if not os.path.exists(fileName[:-4] + "/correct"):
os.mkdir(fileName[:-4] + "/correct")
if not os.path.exists(fileName[:-4] + "/false"):
os.mkdir(fileName[:-4] + "/false")
for i, word in enumerate(segmentedChars):
wordLength = len(wordsText[i])
if "لا" in wordsText[i]:
wordLength -= 1
if word[1] == wordLength:
cv2.imwrite(f"{fileName[:-4]}/correct/{i}.png", word[0])
else:
cv2.imwrite(f"{fileName[:-4]}/false/{i}.png", word[0])
file = open(f"{fileName[:-4]}/words.txt", 'w')
for j, i in enumerate(wordsText):
file.write(f"{i}\n")
file.close()
def postProcessFolder(srcFolder="OutputTextFiles/", dstFolder="LevTextFiles/"):
files = os.listdir(srcFolder)
for f in files:
text = ' '.join(getText(srcFolder + f))
processedText = postProcessTextWithLev(text)
writeText(dstFolder + f, processedText)