def get_data():
List = []
facelist = os.listdir('./datasets/original/face/') #
for i in range(len(facelist)):
location = './datasets/original/face/' + facelist[i]
im = Image.open(location).convert('L') #读取图片，将全部图片转成大小为24*24的灰度图
array = np.array(im).astype(float)
array = imresize(
array, (24, 24)) # Convert between PIL image and NumPy ndarray
#im2 = Image.fromarray(array) # Convert between PIL image and NumPy ndarray
npdfeature = NPDFeature(array) #处理数据集数据，提取NPD特征。
feature = npdfeature.extract()
List.append(feature)
nonfacelist = os.listdir('./datasets/original/nonface/') #
for i in range(len(nonfacelist)):
location = './datasets/original/nonface/' + nonfacelist[i]
im = Image.open(location).convert('L') #读取图片，将全部图片转成大小为24*24的灰度图
array = np.array(im).astype(float)
array = imresize(
array, (24, 24)) # Convert between PIL image and NumPy ndarray
#im2 = Image.fromarray(array) # Convert between PIL image and NumPy ndarray
npdfeature = NPDFeature(array) #处理数据集数据，提取NPD特征。
feature = npdfeature.extract()
List.append(feature)
file = open('feature.txt', 'wb') # 用pickle库中的dump()函数将预处理后的特征数据保存到缓存中
pickle.dump(List, file)
file.close()
def mk_dataset():
face_dir = "/Users/zoushuai/Python/lab/datasets/original/face"
nonface_dir = "/Users/zoushuai/Python/lab/datasets/original/nonface"
face_list = resize_image(face_dir)
nonface_list = resize_image(nonface_dir)
train_set = face_list[0:250]
train_set.extend(
nonface_list[0:250]) # trainset contains 250 faces and 250 nonfaces
train_set = np.array(train_set)
validate_set = face_list[250:500]
validate_set.extend(nonface_list[250:500]
) # validateset contains 250 faces and 250 nonfaces
validate_set = np.array(validate_set)
train_img2feature_list = []
validate_img2feature_list = []
for i in range(500):
npdFeature_train = NPDFeature(train_set[i])
train_img2feature_list.append(npdFeature_train.extract())
npdFeature_validate = NPDFeature(validate_set[i])
validate_img2feature_list.append(npdFeature_validate.extract())
train_img2feature_list = np.array(train_img2feature_list)
validate_img2feature_list = np.array(validate_img2feature_list)
AdaBoostClassifier.save(train_img2feature_list, 'train')
AdaBoostClassifier.save(validate_img2feature_list, 'validate')
def getFeature(Path, savePath):
for file in os.listdir(Path):
file_abs_path = os.path.join(Path, file)
if os.path.isdir(file_abs_path):
getFeature(file_abs_path, savePath)
if os.path.isfile(file_abs_path):
if os.path.exists(file_abs_path):
#using NPDFeature class to get feature
im = np.array(Image.open(file_abs_path))
#print("image.shape = ", im.shape)
#print("**8*************======", im)
npdf = NPDFeature(im)
pic_features = npdf.extract()
print("pic_features", pic_features.shape)
#to get path for saving features as files
parent_path_name = os.path.dirname(file_abs_path).split("/")[-1]
save_path = os.path.join(savePath, parent_path_name)
save_path = os.path.join(save_path, os.path.splitext(file)[0])
if not os.path.exists(save_path):
#dump to file
output = open(save_path, "wb")
PROROCOL = 0
pickle.dump(pic_features, output, PROROCOL)
def readimg():
currentpath1='./datasets/original/face/face_'
currentpath2='./datasets/original/nonface/nonface_'
for i in range(0,500):
img_face = mpimg.imread(currentpath1+"{:0>3d}".format(i)+".jpg")
img_face_=rgb2gray(img_face)
f=NPDFeature(img_face_)
feature_=f.extract()
feature.append(feature_)
label.append(1)
for i in range(0,500):
img_nonface=mpimg.imread(currentpath2+"{:0>3d}".format(i)+".jpg")
img_nonface_=rgb2gray(img_nonface)
f=NPDFeature(img_nonface_)
feature_=f.extract()
feature.append(feature_)
label.append(-1)
def extract_to_list(path_from):
result = []
for f in os.listdir(path_from):
i = Image.open(path_from + "/" + f)
im_array = np.array(i)
npd = NPDFeature(im_array)
features = npd.extract()
result.append(features)
return result
def trainX():
#构建人脸数据
dir_name = 'datasets/original/face/face_'
im_list = []
for i in range(0, 100):
i = str(i).zfill(3)
im = Image.open(dir_name + i + '.jpg').convert('L')
im = im.resize((24, 24))
im = array(im)
im_list.append(im)
# im_list
#提取特征
NF = NPDFeature(im_list[0])
feature = NF.extract()
f_list = feature
for i in range(1, 100):
NF = NPDFeature(im_list[i])
feature = NF.extract()
f_list = append(f_list, feature)
f_list = f_list.reshape(100, 165600)
#构建非人脸数据
dir_name = 'datasets/original/nonface/nonface_'
imn_list = []
for i in range(0, 50):
i = str(i).zfill(3)
im = Image.open(dir_name + i + '.jpg').convert('L')
im = im.resize((24, 24))
im = array(im)
imn_list.append(im)
# imn_list
#调用NPDFeatureclass提取特征
NF = NPDFeature(imn_list[0])
feature = NF.extract()
fn_list = feature
print(feature.shape)
for i in range(1, 50):
NF = NPDFeature(imn_list[i])
feature = NF.extract()
fn_list = append(fn_list, feature)
fn_list = fn_list.reshape(50, 165600)
#将数据合并成训练集
X = concatenate((f_list, fn_list), axis=0)
return X
def get_npdArray_from_diskImg(pathDir):
list = []
file_names = os.listdir(pathDir)
for file_name in file_names:
img = Image.open('%s%s' % (pathDir, file_name))
img = img.resize((24, 24))
img = np.array(img.convert('L'))
npdFeature = NPDFeature(img)
npdArray = npdFeature.extract()
list.append(npdArray)
faces_npdArray = np.array(list)
return faces_npdArray
def testX():
dir_name = 'datasets/original/face/face_'
im_list_test = []
for i in range(100, 150):
i = str(i).zfill(3)
im = Image.open(dir_name + i + '.jpg').convert('L')
im = im.resize((24, 24))
im = array(im)
im_list_test.append(im)
# im_list_test
#提取特征
NF = NPDFeature(im_list_test[0])
feature = NF.extract()
f_list_test = feature
for i in range(1, 50):
NF = NPDFeature(im_list_test[i])
feature = NF.extract()
f_list_test = append(f_list_test, feature)
f_list_test = f_list_test.reshape(50, 165600)
#构建测试集的非人脸特征
dir_name = 'datasets/original/nonface/nonface_'
imn_list_test = []
for i in range(50, 75):
i = str(i).zfill(3)
im = Image.open(dir_name + i + '.jpg').convert('L')
im = im.resize((24, 24))
im = array(im)
imn_list_test.append(im)
imn_list_test
#提取特征
NF = NPDFeature(imn_list_test[0])
feature = NF.extract()
fn_list_test = feature
for i in range(1, 25):
NF = NPDFeature(imn_list_test[i])
feature = NF.extract()
fn_list_test = append(fn_list_test, feature)
fn_list_test = fn_list_test.reshape(25, 165600)
X_test = concatenate((f_list_test, fn_list_test), axis=0)
return X_test
def preprocess_image():
os.makedirs("datasets\\features")
# preprocess face images
for i in range(500):
# set the fetch address
fetch_address = "datasets\\original\\face\\face_%03d.jpg" % i
# read jpg file
# im = matplotlib.image.imread(fetch_address)
# transform to the 24*24 gray image
# xi = transform_image(im)
# create a NPDFeature class
xi = Image.open(fetch_address).convert('L').resize((24, 24))
xi = np.array(xi)
npd = NPDFeature(xi)
# extract feature
feature = npd.extract()
# set the filename
filename = "datasets\\features\\face%03d.pickle" % i
# save the feature in pickle file
save_data(filename, feature)
# preprocess nonface images
for i in range(500):
# set the fetch address
fetch_address = "datasets\\original\\nonface\\nonface_%03d.jpg" % i
# read jpg file
# im = matplotlib.image.imread(fetch_address)
# transform to the 24*24 gray image
# xi = transform_image(im)
# create a NPDFeature class
xi = Image.open(fetch_address).convert('L').resize((24, 24))
xi = np.array(xi)
npd = NPDFeature(xi)
# extract feature
feature = npd.extract()
# set the filename
filename = "datasets\\features\\nonface%03d.pickle" % i
# save the feature in pickle file
save_data(filename, feature)
def get_feature(path):
features = numpy.array([])
files = os.listdir(path)
for k in range(len(files)):
im = Image.open(path + files[k])
image = numpy.ones(shape=(24, 24), dtype=int)
for i in range(24):
for j in range(24):
image[i][j] = im.getpixel((i, j))
NPDFeature1 = NPDFeature(image)
feature = NPDFeature1.extract()
features = numpy.concatenate((features, feature))
return features
def exact_nonface():
#处理nonface
i=0;
feature=[]
label=[]
while i<500:
img_wait_deal=np.array(Image.open("/home/kodgv/第三次实验/ML2017-lab-03/huidutu/non" + str(i) + ".jpg"))
NPD=NPDFeature(img_wait_deal)
label.append(-1)
feature.append(list(NPD.extract()))
i+=1
np.save("nonfeature.npy",np.array(feature))
np.save("nonlabel.npy",np.array(label).reshape(1,len(label)))
def Feature_extract():
#提取特征
face_path = '.\\datasets\\original\\face\\face_%03d.jpg'
faces_path = []
for i in range(500):
faces_path.append(face_path % i)
nonface_path = '.\\datasets\\original\\nonface\\nonface_%03d.jpg'
nonfaces_path = []
for i in range(500):
nonfaces_path.append(nonface_path % i)
train = np.zeros((1000, 165600))
for i in range(500):
img = Image.open(faces_path[i])
img = img.convert('L').resize((24, 24))
nf = NPDFeature(np.array(img))
train[i * 2] = nf.extract()
img = Image.open(nonfaces_path[i])
img = img.convert('L').resize((24, 24))
nf = NPDFeature(np.array(img))
train[i * 2 + 1] = nf.extract()
AdaBoostClassifier.save(train, 'train.txt')
def load_data():
face_path = u'C:/Users/47864/Desktop/Data/datasets/original/face'
nonface_path = u'C:/Users/47864/Desktop/Data/datasets/original/nonface'
face_image = os.listdir(face_path)
nonface_image = os.listdir(nonface_path)
num_face_image = len(face_image)
num_nonface_image = len(nonface_image)
dataset = []
for i in range(num_face_image):
img = Image.open(face_path + '/' + face_image[i])
img = img.convert('L')
img = img.resize((24, 24), Image.ANTIALIAS)
img = NPDFeature(np.array(img))
dataset.append(np.concatenate((img.extract(), np.array([1]))))
for i in range(num_nonface_image):
img = Image.open(nonface_path + '/' + nonface_image[i])
img = img.convert('L')
img = img.resize((24, 24), Image.ANTIALIAS)
img = NPDFeature(np.array(img))
dataset.append(np.concatenate((img.extract(), np.array([-1]))))
return dataset
def extract_fea(img_dirs, img_labels, store_name):
'''
预处理阶段，处理为24*24，灰度图
'''
fea_list = []
for i in range(len(img_dirs)):
temp_img = io.imread(img_dirs[i])
temp_gray_img = color.rgb2gray(temp_img)
temp_resized_img = transform.resize(temp_gray_img, (24, 24))
temp_resized_img = img_as_ubyte(temp_resized_img)
#提取特征
npd_fea = NPDFeature(temp_resized_img)
temp_fea = npd_fea.extract()
temp_label = img_labels[i]
fea_list.append((temp_fea, temp_label))
o_file = open(store_name, 'wb')
pickle.dump(fea_list, o_file, -1)
o_file.close()
def read_data():
X = []
y = []
for i in range(500):
path = get_i_face_image_path(i)
image = Image.open(path)
image = image.convert('L')
image = image.resize((16, 16))
X.append(image)
y.append(1)
for i in range(500):
path = get_i_nonface_image_path(i)
image = Image.open(path)
image = image.convert('L')
image = image.resize((16, 16))
X.append(image)
y.append(-1)
feature = []
for i in tqdm(range(len(X)), desc='pre_train', leave=True):
array_image = np.array(X[i])
fea = NPDFeature(array_image)
feature.append(fea.extract())
return feature, y
def extra_img_features():
for i in range(0, len(img)):
f = NPDFeature(img[i])
features = f.extract()
img_features.append(features)