def scanImgOverScale(self, image):
from config import DETECT_START #1
from config import DETECT_END #2
from config import DETECT_STEP #0.2
from config import ADABOOST_CACHE_FILE #"./model/adaboost_classifier.cache"
from config import ADABOOST_LIMIT #150
model = getCachedAdaBoost(filename = ADABOOST_CACHE_FILE + str(0), limit = ADABOOST_LIMIT)
rectangles = []
for scale in numpy.arange(DETECT_START , DETECT_END, DETECT_STEP):
rectangles += self.scanImgAtScale(model, image, scale)
return self.optimalRectangle(rectangles)
def scanImgOverScale(self, image):
from config import DETECT_START
from config import DETECT_END
from config import DETECT_STEP
from config import ADABOOST_CACHE_FILE
from config import ADABOOST_LIMIT
model = getCachedAdaBoost(filename = ADABOOST_CACHE_FILE + str(0), limit = ADABOOST_LIMIT)
rectangles = []
for scale in numpy.arange(DETECT_START , DETECT_END, DETECT_STEP):
rectangles += self.scanImgAtScale(model, image, scale)
return self.optimalRectangle(rectangles)
def scanImgOverScale(self, image):
from config import DETECT_START
from config import DETECT_END
from config import DETECT_STEP
from config import ADABOOST_CACHE_FILE
from config import ADABOOST_LIMIT
model = getCachedAdaBoost(filename=ADABOOST_CACHE_FILE + str(0),
limit=ADABOOST_LIMIT)
rectangles = []
for scale in numpy.arange(DETECT_START, DETECT_END, DETECT_STEP):
rectangles += self.scanImgAtScale(model, image, scale)
return self.optimalRectangle(rectangles)
def train(self):
raise ("Unfinished")
detection_rate = 0
from config import EXPECTED_FPR_PRE_LAYYER
from config import EXPECTED_FPR
from config import LABEL_NEGATIVE
cur_fpr = 1.0
mat = self._mat
label = self._label
for i in xrange(self.limit):
if cur_fpr < EXPECTED_FPR:
break
else:
cache_filename = ADABOOST_CACHE_FILE + str(i)
if os.path.isfile(cache_filename):
self.strong_classifier[i] = getCachedAdaBoost(
mat=self._mat,
label=self._label,
filename=cache_filename,
limit=ADABOOST_LIMIT)
else:
self.strong_classifier[i] = AdaBoost(mat,
label,
limit=ADABOOST_LIMIT)
output, fpr = self.strong_classifier[i].train()
cur_fpr *= fpr
fp_num = fpr * numpy.count_nonzero(label == LABEL_NEGATIVE)
self.strong_classifier[i].saveModel(cache_filename)
mat, label = self.updateTrainingDate(mat, output, fp_num)
self.classifierNum += 1
def train(self):
raise ("Unfinished")
detection_rate = 0
from config import EXPECTED_FPR_PRE_LAYYER
from config import EXPECTED_FPR
from config import LABEL_NEGATIVE
cur_fpr = 1.0
mat = self._mat
label = self._label
for i in xrange(self.limit):
if cur_fpr < EXPECTED_FPR:
break
else:
cache_filename = ADABOOST_CACHE_FILE + str(i)
if os.path.isfile(cache_filename):
self.strong_classifier[i] = getCachedAdaBoost(mat = self._mat,
label = self._label,
filename= cache_filename,
limit = ADABOOST_LIMIT)
else:
self.strong_classifier[i] = AdaBoost(mat, label, limit = ADABOOST_LIMIT)
output, fpr = self.strong_classifier[i].train()
cur_fpr *= fpr
fp_num = fpr * numpy.count_nonzero(label == LABEL_NEGATIVE)
self.strong_classifier[i].saveModel(cache_filename)
mat, label = self.updateTrainingDate(mat, output, fp_num)
self.classifierNum += 1
from mapReduce import reduce
map(Face, nonFace)
_mat = reduce()
mat = _mat
featureNum, sampleNum = _mat.shape
assert sampleNum == (POSITIVE_SAMPLE + NEGATIVE_SAMPLE)
assert featureNum == FEATURE_NUM
Label_Face = [+1 for i in xrange(POSITIVE_SAMPLE)]
Label_NonFace = [-1 for i in xrange(NEGATIVE_SAMPLE)]
label = numpy.array(Label_Face + Label_NonFace)
cache_filename = ADABOOST_CACHE_FILE + str(0)
if os.path.isfile(cache_filename):
model = getCachedAdaBoost(mat = _mat,
label = label,
filename= cache_filename,
limit = ADABOOST_LIMIT)
else:
model = AdaBoost(mat, label, limit = ADABOOST_LIMIT)
model.train()
model.saveModel(cache_filename)
print model
import numpy
face = ImageSet(TEST_FACE, sampleNum=100)
nonFace = ImageSet(TEST_NONFACE, sampleNum=100)
tot_samples = face.sampleNum + nonFace.sampleNum
haar = Feature(TRAINING_IMG_WIDTH, TRAINING_IMG_HEIGHT)
mat = numpy.zeros((haar.featuresNum, tot_samples))
for i in range(face.sampleNum):
featureVec = haar.calFeatureForImg(face.images[i])
for j in range(haar.featuresNum):
mat[j][i] = featureVec[j]
for i in range(nonFace.sampleNum):
featureVec = haar.calFeatureForImg(nonFace.images[i])
for j in range(haar.featuresNum):
mat[j][i + face.sampleNum] = featureVec[j]
model = getCachedAdaBoost(filename=ADABOOST_CACHE_FILE + str(0), limit=10)
output = model.prediction(mat, th=0)
detectionRate = numpy.count_nonzero(output[0:100] == LABEL_POSITIVE) * 1. / 100
print(output)
nonFace = ImageSet(TEST_NONFACE, sampleNum = 100)
tot_samples = face.sampleNum + nonFace.sampleNum
haar = Feature(TRAINING_IMG_WIDTH, TRAINING_IMG_HEIGHT)
mat = numpy.zeros((haar.featuresNum, tot_samples))
for i in xrange(face.sampleNum):
featureVec = haar.calFeatureForImg(face.images[i])
for j in xrange(haar.featuresNum):
mat[j][i ] = featureVec[j]
for i in xrange(nonFace.sampleNum):
featureVec = haar.calFeatureForImg(nonFace.images[i])
for j in xrange(haar.featuresNum):
mat[j][i + face.sampleNum] = featureVec[j]
model = getCachedAdaBoost(filename = ADABOOST_CACHE_FILE + str(0), limit = 10)
output = model.prediction(mat, th=0)
detectionRate = numpy.count_nonzero(output[0:100] == LABEL_POSITIVE) * 1./ 100
print output