def readCROHMEdB(locationList):
#Fa una llista amb els arxius a extreure la base de dades i ho ordena al sistema
sdB = []
tagClassification = {}
os.remove('toTrain.txt')
trainListFile = open('toTrain.txt', 'w')
for destiny in locationList:
filesInkML = ls(destiny)
for filenom in filesInkML:
if '.inkml' in filenom:
trainListFile.write(destiny + '/' + filenom + '\n')
trainListFile.close()
trainListFile = open('toTrain.txt', 'r')
linea = 'o'
lcont = 0
while linea != '':
lcont += 1
linea = trainListFile.readline()
if linea != '':
if os.path.exists('segmentedData/' + 'Folder000' + str(lcont)):
shutil.rmtree('segmentedData/' + 'Folder000' + str(lcont))
os.makedirs('segmentedData/' + 'Folder000' + str(lcont))
sg.main([
'GO', linea,
'segmentedData/' + 'Folder000' + str(lcont) + '/trainFile'
])
#Escaneja els arxius de la base de dades i guarda les coordenades
for cases in os.listdir('segmentedData'):
filesHere = sorted(os.listdir('segmentedData/' + cases))
filesHere.remove('trainFile_GT.txt')
filesHere = [
'trainFile' + str(
sorted([
int(filesHere[i].strip('trainFile').strip('.inkml'))
for i in range(len(filesHere))
])[j]) + '.inkml' for j in range(len(filesHere))
]
Gfile = open('segmentedData/' + cases + '/trainFile_GT.txt')
linea = 'o'
filco = 0
while linea != '':
linea = Gfile.readline()
if linea != '':
whereInd = linea.index(',')
etiq = linea[whereInd + 1:].rstrip('\n')
sdB.append(
ink2Traces.i2trained(
'segmentedData/' + cases + '/' + filesHere[filco],
etiq))
filco += 1
#Preprocessa i troba els atributs dels simbols de la base de dades
for symbol in sdB:
symbol.draw()
psdB = spp.preprocessing(sdB)
for symbol in psdB:
symbol.computeFeatures()
if symbol.tag not in tagClassification:
tagClassification[symbol.tag] = []
tagClassification[symbol.tag].append(symbol)
return psdB, tagClassification
def readUNIPENdB(location):
weHave = ls(location)
if 'data' in weHave:
sdB = []
tagClassification = {}
folders = ls(location + '/data')
for curFolder in folders:
altFol = ls(location + '/data/' + curFolder)
for curAltFold in altFol:
if curAltFold == 'aga':
dataFiles = ls(location + '/data/' + curFolder + '/' +
curAltFold)
for curFile in dataFiles:
fullPath = location + '/data/' + curFolder + '/' + curAltFold + '/' + curFile
print fullPath + ':'
sdB = sdB + tds.mountDS(fullPath, 'UNIPEN')
for symbol in sdB:
symbol.draw()
psdB = spp.preprocessing(sdB)
for symbol in psdB:
symbol.computeFeatures()
if symbol.tag not in tagClassification:
tagClassification[symbol.tag] = []
tagClassification[symbol.tag].append(symbol)
print type(tagClassification)
return psdB, tagClassification
def readUNIPENdB(location):
weHave=ls(location)
if 'data' in weHave:
sdB=[]
tagClassification={}
folders=ls(location+'/data')
for curFolder in folders:
altFol=ls(location+'/data/'+curFolder)
for curAltFold in altFol:
if curAltFold=='aga':
dataFiles=ls(location+'/data/'+curFolder+'/'+curAltFold)
for curFile in dataFiles:
fullPath=location+'/data/'+curFolder+'/'+curAltFold+'/'+curFile
print fullPath+':'
sdB=sdB+tds.mountDS(fullPath,'UNIPEN')
for symbol in sdB:
symbol.draw()
psdB=spp.preprocessing(sdB)
for symbol in psdB:
symbol.computeFeatures()
if symbol.tag not in tagClassification:
tagClassification[symbol.tag]=[]
tagClassification[symbol.tag].append(symbol)
print type(tagClassification)
return psdB,tagClassification
def readCROHMEdB(locationList):
#Fa una llista amb els arxius a extreure la base de dades i ho ordena al sistema
sdB=[]
tagClassification={}
os.remove('toTrain.txt')
trainListFile=open('toTrain.txt','w')
for destiny in locationList:
filesInkML=ls(destiny)
for filenom in filesInkML:
if '.inkml' in filenom:
trainListFile.write(destiny+'/'+filenom+'\n')
trainListFile.close()
trainListFile=open('toTrain.txt','r')
linea='o'
lcont=0
while linea!='':
lcont+=1
linea=trainListFile.readline()
if linea!='':
if os.path.exists('segmentedData/'+'Folder000'+str(lcont)):
shutil.rmtree('segmentedData/'+'Folder000'+str(lcont))
os.makedirs('segmentedData/'+'Folder000'+str(lcont))
sg.main(['GO',linea,'segmentedData/'+'Folder000'+str(lcont)+'/trainFile'])
#Escaneja els arxius de la base de dades i guarda les coordenades
for cases in os.listdir('segmentedData'):
filesHere=sorted(os.listdir('segmentedData/'+cases))
filesHere.remove('trainFile_GT.txt')
filesHere=['trainFile'+str(sorted([int(filesHere[i].strip('trainFile').strip('.inkml')) for i in range(len(filesHere))])[j])+'.inkml' for j in range(len(filesHere))]
Gfile=open('segmentedData/'+cases+'/trainFile_GT.txt')
linea='o'
filco=0
while linea!='':
linea=Gfile.readline()
if linea!='':
whereInd=linea.index(',')
etiq=linea[whereInd+1:].rstrip('\n')
sdB.append(ink2Traces.i2trained('segmentedData/'+cases+'/'+filesHere[filco],etiq))
filco+=1
#Preprocessa i troba els atributs dels simbols de la base de dades
for symbol in sdB:
symbol.draw()
psdB=spp.preprocessing(sdB)
for symbol in psdB:
symbol.computeFeatures()
if symbol.tag not in tagClassification:
tagClassification[symbol.tag]=[]
tagClassification[symbol.tag].append(symbol)
return psdB,tagClassification
genTags={}
for character in tagClassification:
if character[:-1] not in genTags:
genTags[character[:-1]]=[]
genTags[character[:-1]].append([character,len(tagClassification[character])])
for onlySym in genTags:
for i in range(len(genTags[onlySym])):
if genTags[onlySym][i][1]<0.05*sum([genTags[onlySym][caseID][1] for caseID in range(len(genTags[onlySym]))]):
del tagClassification[genTags[onlySym][i][0]]
del average[genTags[onlySym][i][0]]
filenom='algb02.inkml'
Coord=ink2Traces.i2t(filenom) #Extreure les coordenades donades pel fitxer
img,byAxis,difs=drawTraces.draw(Coord) #Mostrar resultat obtingut i montar imatge
Symb,groupedStrokes=fileSeg.segment(Coord,byAxis,difs) #Agrupar traces en simbols
Symb=drawRegions.drawS(Symb)
symbol=spp.preprocessing([Symb[1]])
symbol[0].computeFeatures()
#pprint(vars(symbol[0]))
#for i in range(len(symbol[0].LP)):
# print str(symbol[0].LP[i])+', '
auxAverage=copy.deepcopy(average)
auxAverage['21'].computeFeatures()
auxAverage['r1'].computeFeatures()
os.remove('features.txt')
report=open('features.txt','w')
report.write('||||||||||||||||||||||||||||||||||||||||||||||||||||||\n')
report.write('LP:\n')
for i in range(len(tagClassification['21'])):
for j in range(len(tagClassification['21'][i].LP)):
report.write(str(tagClassification['21'][i].LP[j])+', ')
report.write('\n')
for onlySym in genTags:
for i in range(len(genTags[onlySym])):
if genTags[onlySym][i][1] < 0.05 * sum([
genTags[onlySym][caseID][1]
for caseID in range(len(genTags[onlySym]))
]):
del tagClassification[genTags[onlySym][i][0]]
del average[genTags[onlySym][i][0]]
filenom = 'algb02.inkml'
Coord = ink2Traces.i2t(filenom) #Extreure les coordenades donades pel fitxer
img, byAxis, difs = drawTraces.draw(
Coord) #Mostrar resultat obtingut i montar imatge
Symb, groupedStrokes = fileSeg.segment(Coord, byAxis,
difs) #Agrupar traces en simbols
Symb = drawRegions.drawS(Symb)
symbol = spp.preprocessing([Symb[1]])
symbol[0].computeFeatures()
#pprint(vars(symbol[0]))
#for i in range(len(symbol[0].LP)):
# print str(symbol[0].LP[i])+', '
auxAverage = copy.deepcopy(average)
auxAverage['21'].computeFeatures()
auxAverage['r1'].computeFeatures()
os.remove('features.txt')
report = open('features.txt', 'w')
report.write('||||||||||||||||||||||||||||||||||||||||||||||||||||||\n')
report.write('LP:\n')
for i in range(len(tagClassification['21'])):
for j in range(len(tagClassification['21'][i].LP)):
report.write(str(tagClassification['21'][i].LP[j]) + ', ')
report.write('\n')
from pprint import pprint
import elasticMatching as eM
import pytemplate as temp
import featurePonderation as fp
import pyStructural as stru
#Sistema sencer, llegeix nom del fitxer inkml a analitzar i retorna l'expressio (ex: overAll.py fitxerAClassificar.inkml)
filenom = sys.argv[1] #Llegir el nom del fitxer InkML de la consola
Coord = ink2Traces.i2t(filenom) #Extreure les coordenades donades pel fitxer
img, byAxis, difs = drawTraces.draw(
Coord) #Mostrar resultat obtingut i montar imatge
Symb, groupedStrokes = fileSeg.segment(Coord, byAxis,
difs) #Agrupar traces en simbols
Symb = drawRegions.drawS(
Symb) #Buscar la bounding box i el centre de cada simbol
Symb = spp.preprocessing(Symb) #Preprocessar tots els simbols
print 'Computing features..........'
for i in range(len(Symb)):
Symb[i].computeFeatures() #Calcular les features de cada simbol
print 'Features extracted.'
symboldB, tagClassification, averages = temp.readTemplate(
) #Llegeix la base de dades per extreure tots els simbols etiquetats, totes les mostres ordenades per caracter(etiqueta) i el template de cada caracter
genTags = {
} #Busca el significat independent de cada caracter i si la proporcio del caracter respecte el significat independent es molt baixa ho considera soroll i elimina el caracter
#Elimina components sorollosos de la base de dades
for character in tagClassification:
if character[:-1] not in genTags:
genTags[character[:-1]] = []
genTags[character[:-1]].append(
[character, len(tagClassification[character])])
for onlySym in genTags:
