def elasticMatching(charTemplates,symbolToRec,weights,amp,alt):
costCoord=[]
costLP=[]
costtAngle=[]
costtAD=[]
costliS=[]
costaA=[]
costqE=[]
costrSL=[]
costcog=[]
coststyle=[]
reference=[]
cost=[]
for character in charTemplates:
#Nomes si tenen el mateix nombre de traces ho decideix
if character[-1:]=='1':
tNum=1
elif character[-1:]=='2':
tNum=2
elif character[-1:]=='3':
tNum=3
if tNum==symbolToRec.tE.shape[0]:
adaptedSymbol=spp.altArcLengthResampling([symbolToRec],charTemplates[character].tE)[0]
adaptedSymbol.computeFeatures()
#Busca el cost de cada feature
costCoord.append(sum([math.sqrt(((charTemplates[character].Coord[i,0]-adaptedSymbol.Coord[i,0])**2)+((charTemplates[character].Coord[i,1]-adaptedSymbol.Coord[i,1])**2)) for i in range(adaptedSymbol.Coord.shape[0])]))
costLP.append(sum([abs(charTemplates[character].LP[i]-adaptedSymbol.LP[i]) for i in range(adaptedSymbol.LP.shape[0])]))
costtAngle.append(sum([abs(charTemplates[character].turningAngle[i]-adaptedSymbol.turningAngle[i]) for i in range(adaptedSymbol.turningAngle.shape[0])]))
costtAD.append(sum([abs(charTemplates[character].turningAngleDifference[i]-adaptedSymbol.turningAngleDifference[i]) for i in range(adaptedSymbol.turningAngleDifference.shape[0])]))
if adaptedSymbol.liS.shape[0]!=len(charTemplates[character].liS):
costliS.append(spp.lcomp(adaptedSymbol.Coord,adaptedSymbol.Coord.shape[0]))
else:
costliS.append(sum([abs(charTemplates[character].liS[i]-adaptedSymbol.liS[i]) for i in range(adaptedSymbol.liS.shape[0])]))
if adaptedSymbol.accAngle.shape[0]!=len(charTemplates[character].accAngle):
costaA.append(adaptedSymbol.tE.shape[0]*2*math.pi)
else:
costaA.append(sum([abs(charTemplates[character].accAngle[i]-adaptedSymbol.accAngle[i]) for i in range(adaptedSymbol.accAngle.shape[0])]))
if adaptedSymbol.quadraticError.shape[0]!=len(charTemplates[character].quadraticError):
costqE.append(math.sqrt(8)*adaptedSymbol.tE.shape[0])
else:
costqE.append(sum([abs(charTemplates[character].quadraticError[i]-adaptedSymbol.quadraticError[i]) for i in range(adaptedSymbol.quadraticError.shape[0])]))
if adaptedSymbol.relStrokeLength.shape[0]!=len(charTemplates[character].relStrokeLength):
costrSL.append(1)
else:
costrSL.append(sum([abs(charTemplates[character].relStrokeLength[i]-adaptedSymbol.relStrokeLength[i]) for i in range(adaptedSymbol.relStrokeLength.shape[0])]))
if adaptedSymbol.coG.shape[0]!=len(charTemplates[character].coG):
costcog.append(adaptedSymbol.tE.shape[0]*math.sqrt(8))
else:
costcog.append(sum([math.sqrt(((charTemplates[character].coG[i][0]-adaptedSymbol.coG[i][0])**2)+((charTemplates[character].coG[i][1]-adaptedSymbol.coG[i][1])**2)) for i in range(adaptedSymbol.coG.shape[0])]))
if charTemplates[character].Style==adaptedSymbol.Style:
coststyle.append(0)
else:
coststyle.append(1)
reference.append(character)
cost.append(0)
allThisCost={}
kindsOfCost={'Coord':costCoord,'LP':costLP,'turningAngle':costtAngle,'turningAngleDifference':costtAD,'liS':costliS,'accAngle':costaA,'quadraticError':costqE,'relStrokeLength':costrSL,'coG':costcog,'Style':coststyle}
probByCost={}
fiProb={}
#Segons el cost busca una probabilitat i la pondera
for kind in kindsOfCost:
allThisCost[kind]=np.nansum(kindsOfCost[kind])
probByCost[kind]=[allThisCost[kind]/float(ch) for ch in kindsOfCost[kind]]
totProb=np.nansum(probByCost[kind])
fiProb[kind]=[ch/float(totProb) for ch in probByCost[kind]]
probPonderada=[np.nansum([weights[kind]*fiProb[kind][i] for kind in fiProb]) for i in range(len(cost))]
while charTemplates[reference[np.argmax(probPonderada)]].tE.shape[0]!=adaptedSymbol.tE.shape[0]:
del reference[np.argmax(probPonderada)]
del probPonderada[np.argmax(probPonderada)]
etiqBelongs=reference[np.argmax(probPonderada)]
#Casos especials amb bounding box petita
if (symbolToRec.bBox[1]-symbolToRec.bBox[0])<0.0125*amp and (symbolToRec.bBox[3]-symbolToRec.bBox[2])<0.017*alt:
etiqBelongs='.1'
elif ((symbolToRec.bBox[1]-symbolToRec.bBox[0])>0.0125*amp and (symbolToRec.bBox[3]-symbolToRec.bBox[2])<0.017*alt):
etiqBelongs='-1'
elif (symbolToRec.bBox[1]-symbolToRec.bBox[0])<0.0125*amp and (symbolToRec.bBox[3]-symbolToRec.bBox[2])>0.017*alt:
if symbolToRec.tE.shape[0]==1:
etiqBelongs='11'
elif symbolToRec.tE.shape[0]==2:
if abs(symbolToRec.Coord[0,1]-symbolToRec.Coord[symbolToRec.tE[0],1])*(symbolToRec.bBox[3]-symbolToRec.bBox[2])<0.017*alt and abs(symbolToRec.Coord[symbolToRec.tE[0]+1,1]-symbolToRec.Coord[symbolToRec.tE[1],1])*(symbolToRec.bBox[3]-symbolToRec.bBox[2])<0.017*alt:
etiqBelongs='\ldots2'
elif (abs(symbolToRec.Coord[0,1]-symbolToRec.Coord[symbolToRec.tE[0],1])*(symbolToRec.bBox[3]-symbolToRec.bBox[2])>0.017*alt and abs(symbolToRec.Coord[symbolToRec.tE[0]+1,1]-symbolToRec.Coord[symbolToRec.tE[1],1])*(symbolToRec.bBox[3]-symbolToRec.bBox[2])<0.017*alt) or (abs(symbolToRec.Coord[0,1]-symbolToRec.Coord[symbolToRec.tE[0],1])*(symbolToRec.bBox[3]-symbolToRec.bBox[2])<0.017*alt and abs(symbolToRec.Coord[symbolToRec.tE[0]+1,1]-symbolToRec.Coord[symbolToRec.tE[1],1])*(symbolToRec.bBox[3]-symbolToRec.bBox[2])>0.017*alt):
if symbolToRec.coG[0,1]<symbolToRec.coG[1,1]:
etiqBelongs='i2'
else:
etiqBelongs='!2'
else:
etiqBelongs='\ldots3'
if (symbolToRec.bBox[1]-symbolToRec.bBox[0])>(symbolToRec.bBox[3]-symbolToRec.bBox[2])*8:
etiqBelongs='-1'
return etiqBelongs
def templateGenerator():
symboldB, tagClassification = dB.readCROHMEdB([
'trainData/CROHME_training', 'trainData/trainData_v2',
'trainData/TrainINKML'
])
option = 3
counta = 0
tagAverages = {}
#Opcio 1: S'adapten els simbols de la base de dades amb el minim nombre de traces trobat
if option == 1:
for character in tagClassification:
counta += 1
print character, ':', len(tagClassification[character])
numStrokes = [
len(tagClassification[character][i].tE)
for i in range(len(tagClassification[character]))
]
nStrokesTemp = min(numStrokes)
tagClassification[character] = spp.strokeReduction(
tagClassification[character], nStrokesTemp, True)
eachStroke = np.asarray([
int(
sum([
tagClassification[character][i].tE[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character]))
for j in range(nStrokesTemp)
])
tagClassification[character] = spp.altArcLengthResampling(
tagClassification[character], eachStroke)
average = np.zeros([len(tagClassification[character][0].Coord), 2],
np.float64)
for example in tagClassification[character]:
average = np.array([[(average[i, 0] + example.Coord[i, 0]),
(average[i, 1] + example.Coord[i, 1])]
for i in range(example.Coord.shape[0])],
np.float64)
average = np.array([[
average[i, 0] / len(tagClassification[character]),
average[i, 1] / len(tagClassification[character])
] for i in range(example.Coord.shape[0])], np.float64)
tagAverages[character] = average
plt.figure(counta)
for j in range(nStrokesTemp):
if j == 0:
ini = -1
else:
ini = int(eachStroke[j - 1])
plt.plot(average[range(ini + 1,
int(eachStroke[j]) + 1), 0],
-average[range(ini + 1,
int(eachStroke[j]) + 1), 1], 'r')
#Opcio 2: S'adapten els simbols de la base de dades amb el maxim nombre de traces trobat
elif option == 2:
for character in tagClassification:
counta += 1
print character, ':', len(tagClassification[character])
numStrokes = [
len(tagClassification[character][i].tE)
for i in range(len(tagClassification[character]))
]
nStrokesTemp = int(round(sum(numStrokes) / float(len(numStrokes))))
tagClassification[character] = spp.strokeReduction(
tagClassification[character], nStrokesTemp, True)
eachStroke = np.asarray([
int(
sum([
tagClassification[character][i].tE[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character]))
for j in range(nStrokesTemp)
])
tagClassification[character] = spp.altArcLengthResampling(
tagClassification[character], eachStroke)
average = np.zeros([len(tagClassification[character][0].Coord), 2],
np.float64)
for example in tagClassification[character]:
average = np.array([[(average[i, 0] + example.Coord[i, 0]),
(average[i, 1] + example.Coord[i, 1])]
for i in range(example.Coord.shape[0])],
np.float64)
average = np.array([[
average[i, 0] / len(tagClassification[character]),
average[i, 1] / len(tagClassification[character])
] for i in range(example.Coord.shape[0])], np.float64)
tagAverages[character] = average
#Opcio 3: Es separen els simbols segons el seu numero de traces
elif option == 3:
charList = [character for character in tagClassification]
for charInd in range(len(charList)):
numStrokes = [
len(tagClassification[charList[charInd]][i].tE)
for i in range(len(tagClassification[charList[charInd]]))
]
c = 0
typesByN = []
for n in numStrokes:
if n not in typesByN:
typesByN.append(n)
tagClassification[charList[charInd] + str(n)] = []
tagClassification[charList[charInd] + str(n)].append(
tagClassification[charList[charInd]][c])
c += 1
del tagClassification[charList[charInd]]
print tagClassification['-1'][0].LP
#Soroll de la dB
del tagClassification['\exists2'][1]
del tagClassification['\pi2']
del tagClassification['\\' + 'forall3']
del tagClassification['Y2']
del tagClassification['x2']
del tagClassification['Y3']
tagClassification['k1'] = [
tagClassification['k1'][valid] for valid in
[0, 1, 2, 3, 8, 12, 20, 24, 29, 30, 34, 35, 42, 43, 58, 59, 61]
]
tagClassification['\sum2'] = [
tagClassification['\sum2'][valid]
for valid in [1, 5, 13, 18, 24, 25, 28, 32, 35, 37, 38, 45, 61]
]
tagClassification[']2'] = [
tagClassification[']2'][valid] for valid in [3, 4]
]
tagClassification['[2'] = [
tagClassification['[2'][valid] for valid in [0, 8]
]
tagClassification['\\' + 'theta2'] = [
tagClassification['\\' + 'theta2'][valid] for valid in [
1, 2, 5, 7, 9, 12, 13, 28, 29, 31, 32, 34, 37, 39, 40, 41, 52,
61, 65, 66, 67, 69
]
]
tagClassification['\div3'] = [
tagClassification['\div3'][valid] for valid in [10, 24, 38]
]
tagClassification['\\' + 'tan3'] = [
tagClassification['\\' + 'tan3'][valid]
for valid in [0, 4, 5, 16, 22, 34, 41, 45, 50, 53, 72, 86, 144]
]
tagClassification['\lim3'] = [tagClassification['\lim3'][9]]
###
os.remove('results.txt')
report = open('results.txt', 'w')
for character in tagClassification:
#EachStroke fa referencia a com es reparteixen els grups en traces, segons la mitjana d'aquesta distribucio a la base de dades
eachStroke = np.asarray([
int(
sum([
tagClassification[character][i].tE[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character]))
for j in range(tagClassification[character][0].tE.shape[0])
])
tagClassification[character] = spp.altArcLengthResampling(
tagClassification[character], eachStroke)
counta += 1
print character, ':', len(tagClassification[character])
#Totes les features del template d'una etiqueta es calculen com la seva mitjana en els simbols d'aquesta etiqueta
average = np.zeros([len(tagClassification[character][0].Coord), 2],
np.float64)
for example in tagClassification[character]:
average = np.array([[(average[i, 0] + example.Coord[i, 0]),
(average[i, 1] + example.Coord[i, 1])]
for i in range(example.Coord.shape[0])],
np.float64)
average = np.array([[
average[i, 0] / len(tagClassification[character]),
average[i, 1] / len(tagClassification[character])
] for i in range(example.Coord.shape[0])], np.float64)
tagAverages[character] = nsi.taggedSymbol(average, eachStroke,
character)
tagAverages[character].computeFeatures()
tagAverages[character].LP = [
np.nansum([
tagClassification[character][i].LP[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character])
for j in range(len(tagClassification[character][0].LP))
]
tagAverages[character].accAngle = [
np.nansum([
tagClassification[character][i].accAngle[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character])
for j in range(len(tagClassification[character][0].accAngle))
]
tagAverages[character].coG = [[
np.nansum([
tagClassification[character][i].coG[j][0]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character]),
np.nansum([
tagClassification[character][i].coG[j][1]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character])
] for j in range(len(tagClassification[character][0].coG))]
tagAverages[character].liS = [
np.nansum([
tagClassification[character][i].liS[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character])
for j in range(len(tagClassification[character][0].liS))
]
tagAverages[character].quadraticError = [
np.nansum([
tagClassification[character][i].quadraticError[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character]) for j in range(
len(tagClassification[character][0].quadraticError))
]
tagAverages[character].relStrokeLength = [
np.nansum([
tagClassification[character][i].relStrokeLength[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character]) for j in range(
len(tagClassification[character][0].relStrokeLength))
]
tagAverages[character].turningAngle = [
np.nansum([
tagClassification[character][i].turningAngle[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character]) for j in range(
len(tagClassification[character][0].turningAngle))
]
tagAverages[character].turningAngleDifference = [
np.nansum([
tagClassification[character][i].turningAngleDifference[j]
for i in range(len(tagClassification[character]))
]) / len(tagClassification[character]) for j in range(
len(tagClassification[character]
[0].turningAngleDifference))
]
styles = ['horizontal', 'vertical', 'diagonal', 'closed']
tagAverages[character].Style = styles[np.argmax(
[[
tagClassification[character][i].Style
for i in range(len(tagClassification[character]))
].count('horizontal'),
[
tagClassification[character][i].Style
for i in range(len(tagClassification[character]))
].count('vertical'),
[
tagClassification[character][i].Style
for i in range(len(tagClassification[character]))
].count('diagonal'),
[
tagClassification[character][i].Style
for i in range(len(tagClassification[character]))
].count('closed')])]
report.write('-----------------------------------------------\n')
report.write(character + ' |\n')
report.write('---------\n')
for i in range(len(tagClassification[character])):
report.write(
str(tagClassification[character][i].tE) + ' :\n')
for j in range(tagClassification[character][i].Coord.shape[0]):
report.write(
str(tagClassification[character][i].Coord[j]) + ', ')
report.write('\n')
report.write('average:\n ')
for j in range(average.shape[0]):
report.write(str(average[j]) + ', ')
report.write('\n')
#Guarda els resultats al sistema
if os.path.isfile('varSimbdB.txt'):
os.remove('varSimbdB.txt')
f = open('varSimbdB.txt', 'wb')
pickle.dump(symboldB, f)
f.close()
if os.path.isfile('varTagClass.txt'):
os.remove('varTagClass.txt')
f = open('varTagClass.txt', 'wb')
pickle.dump(tagClassification, f)
f.close()
if os.path.isfile('varAverages.txt'):
os.remove('varAverages.txt')
f = open('varAverages.txt', 'wb')
pickle.dump(tagAverages, f)
f.close()
report.close()
plt.show()
def elasticMatching(charTemplates, symbolToRec, weights, amp, alt):
costCoord = []
costLP = []
costtAngle = []
costtAD = []
costliS = []
costaA = []
costqE = []
costrSL = []
costcog = []
coststyle = []
reference = []
cost = []
for character in charTemplates:
#Nomes si tenen el mateix nombre de traces ho decideix
if character[-1:] == '1':
tNum = 1
elif character[-1:] == '2':
tNum = 2
elif character[-1:] == '3':
tNum = 3
if tNum == symbolToRec.tE.shape[0]:
adaptedSymbol = spp.altArcLengthResampling(
[symbolToRec], charTemplates[character].tE)[0]
adaptedSymbol.computeFeatures()
#Busca el cost de cada feature
costCoord.append(
sum([
math.sqrt(((charTemplates[character].Coord[i, 0] -
adaptedSymbol.Coord[i, 0])**2) +
((charTemplates[character].Coord[i, 1] -
adaptedSymbol.Coord[i, 1])**2))
for i in range(adaptedSymbol.Coord.shape[0])
]))
costLP.append(
sum([
abs(charTemplates[character].LP[i] - adaptedSymbol.LP[i])
for i in range(adaptedSymbol.LP.shape[0])
]))
costtAngle.append(
sum([
abs(charTemplates[character].turningAngle[i] -
adaptedSymbol.turningAngle[i])
for i in range(adaptedSymbol.turningAngle.shape[0])
]))
costtAD.append(
sum([
abs(charTemplates[character].turningAngleDifference[i] -
adaptedSymbol.turningAngleDifference[i]) for i in
range(adaptedSymbol.turningAngleDifference.shape[0])
]))
if adaptedSymbol.liS.shape[0] != len(charTemplates[character].liS):
costliS.append(
spp.lcomp(adaptedSymbol.Coord,
adaptedSymbol.Coord.shape[0]))
else:
costliS.append(
sum([
abs(charTemplates[character].liS[i] -
adaptedSymbol.liS[i])
for i in range(adaptedSymbol.liS.shape[0])
]))
if adaptedSymbol.accAngle.shape[0] != len(
charTemplates[character].accAngle):
costaA.append(adaptedSymbol.tE.shape[0] * 2 * math.pi)
else:
costaA.append(
sum([
abs(charTemplates[character].accAngle[i] -
adaptedSymbol.accAngle[i])
for i in range(adaptedSymbol.accAngle.shape[0])
]))
if adaptedSymbol.quadraticError.shape[0] != len(
charTemplates[character].quadraticError):
costqE.append(math.sqrt(8) * adaptedSymbol.tE.shape[0])
else:
costqE.append(
sum([
abs(charTemplates[character].quadraticError[i] -
adaptedSymbol.quadraticError[i])
for i in range(adaptedSymbol.quadraticError.shape[0])
]))
if adaptedSymbol.relStrokeLength.shape[0] != len(
charTemplates[character].relStrokeLength):
costrSL.append(1)
else:
costrSL.append(
sum([
abs(charTemplates[character].relStrokeLength[i] -
adaptedSymbol.relStrokeLength[i])
for i in range(adaptedSymbol.relStrokeLength.shape[0])
]))
if adaptedSymbol.coG.shape[0] != len(charTemplates[character].coG):
costcog.append(adaptedSymbol.tE.shape[0] * math.sqrt(8))
else:
costcog.append(
sum([
math.sqrt(((charTemplates[character].coG[i][0] -
adaptedSymbol.coG[i][0])**2) +
((charTemplates[character].coG[i][1] -
adaptedSymbol.coG[i][1])**2))
for i in range(adaptedSymbol.coG.shape[0])
]))
if charTemplates[character].Style == adaptedSymbol.Style:
coststyle.append(0)
else:
coststyle.append(1)
reference.append(character)
cost.append(0)
allThisCost = {}
kindsOfCost = {
'Coord': costCoord,
'LP': costLP,
'turningAngle': costtAngle,
'turningAngleDifference': costtAD,
'liS': costliS,
'accAngle': costaA,
'quadraticError': costqE,
'relStrokeLength': costrSL,
'coG': costcog,
'Style': coststyle
}
probByCost = {}
fiProb = {}
#Segons el cost busca una probabilitat i la pondera
for kind in kindsOfCost:
allThisCost[kind] = np.nansum(kindsOfCost[kind])
probByCost[kind] = [
allThisCost[kind] / float(ch) for ch in kindsOfCost[kind]
]
totProb = np.nansum(probByCost[kind])
fiProb[kind] = [ch / float(totProb) for ch in probByCost[kind]]
probPonderada = [
np.nansum([weights[kind] * fiProb[kind][i] for kind in fiProb])
for i in range(len(cost))
]
while charTemplates[reference[np.argmax(
probPonderada)]].tE.shape[0] != adaptedSymbol.tE.shape[0]:
del reference[np.argmax(probPonderada)]
del probPonderada[np.argmax(probPonderada)]
etiqBelongs = reference[np.argmax(probPonderada)]
#Casos especials amb bounding box petita
if (symbolToRec.bBox[1] - symbolToRec.bBox[0]) < 0.0125 * amp and (
symbolToRec.bBox[3] - symbolToRec.bBox[2]) < 0.017 * alt:
etiqBelongs = '.1'
elif ((symbolToRec.bBox[1] - symbolToRec.bBox[0]) > 0.0125 * amp
and (symbolToRec.bBox[3] - symbolToRec.bBox[2]) < 0.017 * alt):
etiqBelongs = '-1'
elif (symbolToRec.bBox[1] - symbolToRec.bBox[0]) < 0.0125 * amp and (
symbolToRec.bBox[3] - symbolToRec.bBox[2]) > 0.017 * alt:
if symbolToRec.tE.shape[0] == 1:
etiqBelongs = '11'
elif symbolToRec.tE.shape[0] == 2:
if abs(symbolToRec.Coord[0, 1] -
symbolToRec.Coord[symbolToRec.tE[0], 1]) * (
symbolToRec.bBox[3] -
symbolToRec.bBox[2]) < 0.017 * alt and abs(
symbolToRec.Coord[symbolToRec.tE[0] + 1, 1] -
symbolToRec.Coord[symbolToRec.tE[1], 1]) * (
symbolToRec.bBox[3] -
symbolToRec.bBox[2]) < 0.017 * alt:
etiqBelongs = '\ldots2'
elif (
abs(symbolToRec.Coord[0, 1] -
symbolToRec.Coord[symbolToRec.tE[0], 1]) *
(symbolToRec.bBox[3] - symbolToRec.bBox[2]) > 0.017 * alt
and abs(symbolToRec.Coord[symbolToRec.tE[0] + 1, 1] -
symbolToRec.Coord[symbolToRec.tE[1], 1]) *
(symbolToRec.bBox[3] - symbolToRec.bBox[2]) < 0.017 * alt) or (
abs(symbolToRec.Coord[0, 1] -
symbolToRec.Coord[symbolToRec.tE[0], 1]) *
(symbolToRec.bBox[3] - symbolToRec.bBox[2]) < 0.017 * alt
and abs(symbolToRec.Coord[symbolToRec.tE[0] + 1, 1] -
symbolToRec.Coord[symbolToRec.tE[1], 1]) *
(symbolToRec.bBox[3] - symbolToRec.bBox[2]) > 0.017 * alt):
if symbolToRec.coG[0, 1] < symbolToRec.coG[1, 1]:
etiqBelongs = 'i2'
else:
etiqBelongs = '!2'
else:
etiqBelongs = '\ldots3'
if (symbolToRec.bBox[1] - symbolToRec.bBox[0]) > (symbolToRec.bBox[3] -
symbolToRec.bBox[2]) * 8:
etiqBelongs = '-1'
return etiqBelongs
def templateGenerator():
symboldB,tagClassification=dB.readCROHMEdB(['trainData/CROHME_training','trainData/trainData_v2','trainData/TrainINKML'])
option=3
counta=0
tagAverages={}
#Opcio 1: S'adapten els simbols de la base de dades amb el minim nombre de traces trobat
if option==1:
for character in tagClassification:
counta+=1
print character,':',len(tagClassification[character])
numStrokes=[len(tagClassification[character][i].tE) for i in range(len(tagClassification[character]))]
nStrokesTemp=min(numStrokes)
tagClassification[character]=spp.strokeReduction(tagClassification[character],nStrokesTemp,True)
eachStroke=np.asarray([int(sum([tagClassification[character][i].tE[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character])) for j in range(nStrokesTemp)])
tagClassification[character]=spp.altArcLengthResampling(tagClassification[character],eachStroke)
average=np.zeros([len(tagClassification[character][0].Coord),2],np.float64)
for example in tagClassification[character]:
average=np.array([[(average[i,0]+example.Coord[i,0]),(average[i,1]+example.Coord[i,1])] for i in range(example.Coord.shape[0])],np.float64)
average=np.array([[average[i,0]/len(tagClassification[character]),average[i,1]/len(tagClassification[character])] for i in range(example.Coord.shape[0])],np.float64)
tagAverages[character]=average
plt.figure(counta)
for j in range(nStrokesTemp):
if j==0:
ini=-1
else:
ini=int(eachStroke[j-1])
plt.plot(average[range(ini+1,int(eachStroke[j])+1),0],-average[range(ini+1,int(eachStroke[j])+1),1],'r')
#Opcio 2: S'adapten els simbols de la base de dades amb el maxim nombre de traces trobat
elif option==2:
for character in tagClassification:
counta+=1
print character,':',len(tagClassification[character])
numStrokes=[len(tagClassification[character][i].tE) for i in range(len(tagClassification[character]))]
nStrokesTemp=int(round(sum(numStrokes)/float(len(numStrokes))))
tagClassification[character]=spp.strokeReduction(tagClassification[character],nStrokesTemp,True)
eachStroke=np.asarray([int(sum([tagClassification[character][i].tE[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character])) for j in range(nStrokesTemp)])
tagClassification[character]=spp.altArcLengthResampling(tagClassification[character],eachStroke)
average=np.zeros([len(tagClassification[character][0].Coord),2],np.float64)
for example in tagClassification[character]:
average=np.array([[(average[i,0]+example.Coord[i,0]),(average[i,1]+example.Coord[i,1])] for i in range(example.Coord.shape[0])],np.float64)
average=np.array([[average[i,0]/len(tagClassification[character]),average[i,1]/len(tagClassification[character])] for i in range(example.Coord.shape[0])],np.float64)
tagAverages[character]=average
#Opcio 3: Es separen els simbols segons el seu numero de traces
elif option==3:
charList=[character for character in tagClassification]
for charInd in range(len(charList)):
numStrokes=[len(tagClassification[charList[charInd]][i].tE) for i in range(len(tagClassification[charList[charInd]]))]
c=0
typesByN=[]
for n in numStrokes:
if n not in typesByN:
typesByN.append(n)
tagClassification[charList[charInd]+str(n)]=[]
tagClassification[charList[charInd]+str(n)].append(tagClassification[charList[charInd]][c])
c+=1
del tagClassification[charList[charInd]]
print tagClassification['-1'][0].LP
#Soroll de la dB
del tagClassification['\exists2'][1]
del tagClassification['\pi2']
del tagClassification['\\'+'forall3']
del tagClassification['Y2']
del tagClassification['x2']
del tagClassification['Y3']
tagClassification['k1']=[tagClassification['k1'][valid] for valid in [0,1,2,3,8,12,20,24,29,30,34,35,42,43,58,59,61]]
tagClassification['\sum2']=[tagClassification['\sum2'][valid] for valid in [1,5,13,18,24,25,28,32,35,37,38,45,61]]
tagClassification[']2']=[tagClassification[']2'][valid] for valid in [3,4]]
tagClassification['[2']=[tagClassification['[2'][valid] for valid in [0,8]]
tagClassification['\\'+'theta2']=[tagClassification['\\'+'theta2'][valid] for valid in [1,2,5,7,9,12,13,28,29,31,32,34,37,39,40,41,52,61,65,66,67,69]]
tagClassification['\div3']=[tagClassification['\div3'][valid] for valid in [10,24,38]]
tagClassification['\\'+'tan3']=[tagClassification['\\'+'tan3'][valid] for valid in [0,4,5,16,22,34,41,45,50,53,72,86,144]]
tagClassification['\lim3']=[tagClassification['\lim3'][9]]
###
os.remove('results.txt')
report=open('results.txt','w')
for character in tagClassification:
#EachStroke fa referencia a com es reparteixen els grups en traces, segons la mitjana d'aquesta distribucio a la base de dades
eachStroke=np.asarray([int(sum([tagClassification[character][i].tE[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character])) for j in range(tagClassification[character][0].tE.shape[0])])
tagClassification[character]=spp.altArcLengthResampling(tagClassification[character],eachStroke)
counta+=1
print character,':',len(tagClassification[character])
#Totes les features del template d'una etiqueta es calculen com la seva mitjana en els simbols d'aquesta etiqueta
average=np.zeros([len(tagClassification[character][0].Coord),2],np.float64)
for example in tagClassification[character]:
average=np.array([[(average[i,0]+example.Coord[i,0]),(average[i,1]+example.Coord[i,1])] for i in range(example.Coord.shape[0])],np.float64)
average=np.array([[average[i,0]/len(tagClassification[character]),average[i,1]/len(tagClassification[character])] for i in range(example.Coord.shape[0])],np.float64)
tagAverages[character]=nsi.taggedSymbol(average,eachStroke,character)
tagAverages[character].computeFeatures()
tagAverages[character].LP=[np.nansum([tagClassification[character][i].LP[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character]) for j in range(len(tagClassification[character][0].LP))]
tagAverages[character].accAngle=[np.nansum([tagClassification[character][i].accAngle[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character]) for j in range(len(tagClassification[character][0].accAngle))]
tagAverages[character].coG=[[np.nansum([tagClassification[character][i].coG[j][0] for i in range(len(tagClassification[character]))])/len(tagClassification[character]),np.nansum([tagClassification[character][i].coG[j][1] for i in range(len(tagClassification[character]))])/len(tagClassification[character])] for j in range(len(tagClassification[character][0].coG))]
tagAverages[character].liS=[np.nansum([tagClassification[character][i].liS[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character]) for j in range(len(tagClassification[character][0].liS))]
tagAverages[character].quadraticError=[np.nansum([tagClassification[character][i].quadraticError[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character]) for j in range(len(tagClassification[character][0].quadraticError))]
tagAverages[character].relStrokeLength=[np.nansum([tagClassification[character][i].relStrokeLength[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character]) for j in range(len(tagClassification[character][0].relStrokeLength))]
tagAverages[character].turningAngle=[np.nansum([tagClassification[character][i].turningAngle[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character]) for j in range(len(tagClassification[character][0].turningAngle))]
tagAverages[character].turningAngleDifference=[np.nansum([tagClassification[character][i].turningAngleDifference[j] for i in range(len(tagClassification[character]))])/len(tagClassification[character]) for j in range(len(tagClassification[character][0].turningAngleDifference))]
styles=['horizontal','vertical','diagonal','closed']
tagAverages[character].Style=styles[np.argmax([[tagClassification[character][i].Style for i in range(len(tagClassification[character]))].count('horizontal'),[tagClassification[character][i].Style for i in range(len(tagClassification[character]))].count('vertical'),[tagClassification[character][i].Style for i in range(len(tagClassification[character]))].count('diagonal'),[tagClassification[character][i].Style for i in range(len(tagClassification[character]))].count('closed')])]
report.write('-----------------------------------------------\n')
report.write(character+' |\n')
report.write('---------\n')
for i in range(len(tagClassification[character])):
report.write(str(tagClassification[character][i].tE)+' :\n')
for j in range(tagClassification[character][i].Coord.shape[0]):
report.write(str(tagClassification[character][i].Coord[j])+', ')
report.write('\n')
report.write('average:\n ')
for j in range(average.shape[0]):
report.write(str(average[j])+', ')
report.write('\n')
#Guarda els resultats al sistema
if os.path.isfile('varSimbdB.txt'):
os.remove('varSimbdB.txt')
f = open('varSimbdB.txt','wb')
pickle.dump(symboldB,f)
f.close()
if os.path.isfile('varTagClass.txt'):
os.remove('varTagClass.txt')
f = open('varTagClass.txt','wb')
pickle.dump(tagClassification,f)
f.close()
if os.path.isfile('varAverages.txt'):
os.remove('varAverages.txt')
f = open('varAverages.txt','wb')
pickle.dump(tagAverages,f)
f.close()
report.close()
plt.show()
