import sys
import os
import cv2
import dlib
import PIL.Image as Image
def cut_all_face(input_dir, output_dir):
'''剪切所有的图片'''
# 使用dlib自带的frontal_face_detector作为我们的特征提取器
detector = dlib.get_frontal_face_detector()
output_dir = output_dir + r'\all'
if not os.path.exists(output_dir):
os.makedirs(output_dir)
index = 1
for path, dirnames, filenames in os.walk(input_dir):
for filename in filenames:
if filename.endswith('.jpg') or filename.endswith('.png'):
print('正在处理图片 %s' % index)
img_path = path + '/' + filename
# 从文件读取图片
img = cv2.imread(img_path)
img1 = Image.open(img_path)
# 转为灰度图片
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 使用detector进行人脸检测 dets为返回的结果
dets = detector(gray_img, 1)
# 使用enumerate 函数遍历序列中的元素以及它们的下标
# 下标i即为人脸序号
# left：人脸左边距离图片左边界的距离 ；right：人脸右边距离图片左边界的距离
# top：人脸上边距离图片上边界的距离 ；bottom：人脸下边距离图片上边界的距离
for i, d in enumerate(dets):
# print(i, d)
x1 = int(d.left()) if d.left() > 0 else 0
y1 = int(d.top()) if d.top() > 0 else 0
x2 = int(d.right()) if d.right() > 0 else 0
y2 = int(d.bottom()) if d.bottom() > 0 else 0
box = (x1 - 20, y1 - 20, x2 + 20, y2 + 20)
# print(box)
face = img1.crop(box)
# 调整图片的尺寸
face = face.resize((160, 160), Image.ANTIALIAS)
# 保存图片
face.save(output_dir + '\\' + str(index) + '.jpg', 'JPEG', quality=95)
index += 1
key = cv2.waitKey(30) & 0xff
if key == 27:
sys.exit(0)
return output_dir
def difference(hist1, hist2):
'''图片间的差异'''
sum1 = 0
for i in range(len(hist1)):
if hist1[i] == hist2[i]:
sum1 += 1
else:
sum1 += 1 - float(abs(hist1[i] - hist2[i])) / max(hist1[i], hist2[i])
return sum1 / len(hist1)
def similary_calculate(path1, path2):
'''图片处理'''
# 预处理
img1 = Image.open(path1).resize((256, 256)).convert('RGB')
img2 = Image.open(path2).resize((256, 256)).convert('RGB')
sum = 0
for i in range(4):
for j in range(4):
hist1 = img1.crop((i * 64, j * 64, i * 64 + 63, j * 64 + 63)).copy().histogram()
hist2 = img2.crop((i * 64, j * 64, i * 64 + 63, j * 64 + 63)).copy().histogram()
sum += difference(hist1, hist2)
# print difference(hist1, hist2)
return sum / 16
def face_discern(path_test, path_train):
'''根据图片间的相似度，筛选图片'''
for root_train, directors_train, files_train in os.walk(path_train):
j = 0
for filename in files_train:
file_path_train = os.path.join(root_train, filename)
j += 1
output_dir = r'C:\Users\Desktop\test' + '\\' + str(j)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
for root, directors, files in os.walk(path_test):
i = 0
for filename in files:
filepath = os.path.join(root, filename)
if filepath.endswith(".png") or filepath.endswith(".jpg"):
remember = similary_calculate(file_path_train, filepath)
if remember > 0.55:
print(filepath)
img = Image.open(filepath)
img.resize((160, 160), Image.ANTIALIAS)
img.save(output_dir + '\\' + str(i) + '.jpg', 'JPEG', quality=95)
i += 1
if __name__ == '__main__':
input_dir = r'C:\Users\Desktop\face'
output_dir = r'C:\Users\Desktop\test'
if not os.path.exists(output_dir):
os.makedirs(output_dir)
path_test = cut_all_face(input_dir=input_dir, output_dir=output_dir)
path_train = r'C:\Users\Desktop\train'
face_discern(path_test=path_test, path_train=path_train)
l = []
l.a
