def feature_extractor():
#Abrir arquivo que vai receber as features dos arquivos de imagens
file = "image_features_train_20_10_1_Novo4.arff"
text_file = open(file, "a")
trainPath = "C:/Python27/ARP/Dataset/train5"
dirList = os.listdir(trainPath)
edge = EdgeHistogramFeatureExtractor(20)
for dirName in dirList:
fileList = os.listdir(trainPath + '/' + dirName)
maxsize = len(fileList)
for i in range(0, maxsize):
#print fileList[i]
filePATH = (trainPath + '/' + dirName + '/' + fileList[i])
img = Image(filePATH)
#Feature - Edge histogram
edge_vecs = edge.extract(img)
edge_fields = edge.getFieldNames()
for y in range(0, edge.getNumFields()):
#print edge_fields[y], '=', edge_vecs[y]
text_file.write(str(edge_vecs[y]) + ",")
#Feature - Hue
hue = HueHistogramFeatureExtractor(10)
hue_vecs = hue.extract(img)
hue_fields = hue.getFieldNames()
for i in range(0, hue.getNumFields()):
# #print hue_fields[i], '=', hue_vecs[i]
text_file.write(str(hue_vecs[i]) + ",")
Morph1 = MorphologyFeatureExtractor()
Morph2 = Morph1.extract(img)
text_file.write(str(Morph2) + ",")
text_file.write(dirName + "\n")
text_file.close()
def morph():
mf = MorphologyFeatureExtractor()
mf.setThresholdOperation(myBinaryFunc)
a = np.array(mf.extract(watchman.imgbank[0]))
if len(watchman.imgbank) > 1:
b = np.array(mf.extract(watchman.imgbank[1]))
else:
b = np.array(mf.extract(watchman.imgbank[0]))
AandB = np.sum(np.square(a - b))
return AandB
def morph():
mf = MorphologyFeatureExtractor()
mf.setThresholdOperation(myBinaryFunc)
a = np.array(mf.extract(watchman.imgbank[0]))
if len(watchman.imgbank) > 1:
b = np.array(mf.extract(watchman.imgbank[1]))
else:
b = np.array(mf.extract(watchman.imgbank[0]))
AandB = np.sum(np.square(a-b))
return AandB
for i in range(0, hue.getNumFields()):
print hue_fields[i], '=', hue_vecs[i]
text_file.write(str(hue_vecs[i]) + ",")
#Feature - Haar
#haar = HaarLikeFeatureExtractor(fname='haar.txt')
#haar_vecs = haar.extract(img)
#haar_fields = haar.getFieldNames()
#for i in range(0, len(haar_fields)):
# print haar_fields[i], '=', haar_vecs[i]
# text_file.write(str(haar_vecs[i]) + ",")
text_file.write("revolver")
text_file.close()
"""
#Criando o header do arquivo ARFF de features
#var1 = gerador_Header()
#Gerando e gravando as features no arquivo ARFF
#var2 = feature_extractor()
"""
#classes = ['pistola_gray','revolver_gray',]
"""
img = Image('revolver.jpg')
feature = MorphologyFeatureExtractor()
array = feature.extract(img)
print (array)
#text_file.write("revolver")
#text_file.close()
from SimpleCV import *
from numpy import *
from SimpleCV.Display import Display, pg
from SimpleCV import MorphologyFeatureExtractor
#we pass this methods as our threshold operation
def thresholdOp(in_image):
return in_image.binarize(thresh=70).invert().dilate(2)
# extract only morphology
morph_extractor = MorphologyFeatureExtractor()
morph_extractor.setThresholdOperation(thresholdOp)
extractors = [morph_extractor]
#setup the paths to our data
nuts_path = "./data/nuts/"
bolts_path = "./data/bolts/"
path = [nuts_path, bolts_path]
classes = ['washer', 'bolt']
props = {
'KernelType': 'Linear', #default is a RBF Kernel
'SVMType': 'C', #default is C
'nu': None, # NU for SVM NU
'c': None, #C for SVM C - the slack variable
'degree': None, #degree for poly kernels - defaults to 3
'coef': None, #coef for Poly/Sigmoid defaults to 0
'gamma':
None, #kernel param for poly/rbf/sigma - default is 1/#samples
}
# flag if we need to train the SVM
