CASME2图片的对齐与裁剪
import os
import cv2
import numpy as np
import math
from collections import defaultdict
from PIL import Image,ImageDraw
from matplotlib.pyplot import imshow, show, grid
from datetime import datetime
import face_recognition
def del_file(filepath):
"""
del_file()该函数的主要功能：删除某一目录下的所有文件或文件夹
:param filepath: 路径
:return:
"""
del_list = os.listdir(filepath)
for f in del_list:
file_path = os.path.join(filepath, f)
if os.path.isfile(file_path):
os.remove(file_path)
def visualize_landmark(image_array, landmarks):
""" plot landmarks on image
:param image_array: numpy array of a single image
:param landmarks: dict of landmarks for facial parts as keys and tuple of coordinates as values
:return: plots of images with landmarks on
"""
origin_img = Image.fromarray(image_array)
draw = ImageDraw.Draw(origin_img)
for facial_feature in landmarks.keys():
draw.point(landmarks[facial_feature])
imshow(origin_img)
return origin_img
def circle_landmark(img_cv2,landmarks):
coordinate_landmark = []
idx = 0
for facial_feature in landmarks.keys():
a = landmarks[facial_feature]
for p in a:
coordinate_landmark.append(p)
cv2.circle(img_cv2, p, 3, color=(0, 255, 0))
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(img_cv2, str(idx + 1), p, font, 0.3, (0, 0, 255), 1, cv2.LINE_AA)
idx += 1
def align_face(image_array, landmarks):
""" align faces according to eyes position
:param image_array: numpy array of a single image
:param landmarks: dict of landmarks for facial parts as keys and tuple of coordinates as values
:return:
rotated_img: numpy array of aligned image
eye_center: tuple of coordinates for eye center
angle: degrees of rotation
"""
left_eye = landmarks['left_eye']
right_eye = landmarks['right_eye']
left_eye_center = np.mean(left_eye, axis=0)
right_eye_center = np.mean(right_eye, axis=0)
dy = right_eye_center[1] - left_eye_center[1]
dx = right_eye_center[0] - left_eye_center[0]
angle = math.atan2(dy, dx) * 180. / math.pi
eye_center = ((left_eye_center[0] + right_eye_center[0]) // 2,
(left_eye_center[1] + right_eye_center[1]) // 2)
# at the eye_center, rotate the image by the angle
rotate_matrix = cv2.getRotationMatrix2D(eye_center, angle, scale=1)
rotated_img = cv2.warpAffine(image_array, rotate_matrix, (image_array.shape[1], image_array.shape[0]))
return rotated_img, eye_center, angle
def rotate(origin, point, angle, row):
""" rotate coordinates in image coordinate system
:param origin: tuple of coordinates,the rotation center
:param point: tuple of coordinates, points to rotate
:param angle: degrees of rotation
:param row: row size of the image
:return: rotated coordinates of point
"""
x1, y1 = point
x2, y2 = origin
y1 = row - y1
y2 = row - y2
angle = math.radians(angle)
x = x2 + math.cos(angle) * (x1 - x2) - math.sin(angle) * (y1 - y2)
y = y2 + math.sin(angle) * (x1 - x2) + math.cos(angle) * (y1 - y2)
y = row - y
return int(x), int(y)
def rotate_landmarks(landmarks, eye_center, angle, row):
""" rotate landmarks to fit the aligned face
:param landmarks: dict of landmarks for facial parts as keys and tuple of coordinates as values
:param eye_center: tuple of coordinates for eye center
:param angle: degrees of rotation
:param row: row size of the image
:return: rotated_landmarks with the same structure with landmarks, but different values
"""
rotated_landmarks = defaultdict(list)
for facial_feature in landmarks.keys():
for landmark in landmarks[facial_feature]:
rotated_landmark = rotate(origin=eye_center, point=landmark, angle=angle, row=row)
rotated_landmarks[facial_feature].append(rotated_landmark)
return rotated_landmarks
def corp_face(image_array, size, landmarks):
""" crop face according to eye,mouth and chin position
:param image_array: numpy array of a single image
:param size: single int value, size for w and h after crop
:param landmarks: dict of landmarks for facial parts as keys and tuple of coordinates as values
:return:
cropped_img: numpy array of cropped image
left, top: left and top coordinates of cropping
"""
x_min = np.min(landmarks['chin'], axis=0)[0]
x_max = np.max(landmarks['chin'], axis=0)[0]
x_center = (x_max - x_min) / 2 + x_min
left, right = (x_center - size / 2, x_center + size / 2)
eye_landmark = landmarks['left_eye'] + landmarks['right_eye']
eye_center = np.mean(eye_landmark, axis=0).astype("int")
lip_landmark = landmarks['top_lip'] + landmarks['bottom+lip']
lip_center = np.mean(lip_landmark, axis=0).astype("int")
mid_part = lip_center[1] - eye_center[1]
top, bottom = eye_center[1] - (size - mid_part) / 2, lip_center[1] + (size - mid_part) / 2
pil_img = Image.fromarray(image_array)
left, top, right, bottom = [int(i) for i in [left, top, right, bottom]]
cropped_img = pil_img.crop((left, top, right, bottom))
cropped_img = np.array(cropped_img)
return cropped_img, left, top
def corp_face_unsize(image_array, landmarks):
""" crop face according to eye,mouth and chin position
:param image_array: numpy array of a single image
:param landmarks: dict of landmarks for facial parts as keys and tuple of coordinates as values
:return:
cropped_img: numpy array of cropped image
"""
eye_landmark = np.concatenate([np.array(landmarks['left_eye']),
np.array(landmarks['right_eye'])])
eye_center = np.mean(eye_landmark, axis=0).astype("int")
lip_landmark = np.concatenate([np.array(landmarks['top_lip']),
np.array(landmarks['bottom_lip'])])
lip_center = np.mean(lip_landmark, axis=0).astype("int")
mid_part = lip_center[1] - eye_center[1]
top = eye_center[1] - mid_part
bottom = lip_center[1] + mid_part * 40 / 70
w = h = bottom - top
x_min = np.min(landmarks['chin'], axis=0)[0]
x_max = np.max(landmarks['chin'], axis=0)[0]
x_center = (x_max - x_min) / 2 + x_min
left, right = (x_center - w / 2, x_center + w / 2)
pil_img = Image.fromarray(image_array)
left, top, right, bottom = [int(i) for i in [left, top, right, bottom]]
cropped_img = pil_img.crop((left, top, right, bottom))
cropped_img = np.array(cropped_img)
return cropped_img, left, top
def transfer_landmark(landmarks, left, top):
"""transfer landmarks to fit the cropped face
:param landmarks: dict of landmarks for facial parts as keys and tuple of coordinates as values
:param left: left coordinates of cropping
:param top: top coordinates of cropping
:return: transferred_landmarks with the same structure with landmarks, but different values
"""
transferred_landmarks = defaultdict(list)
for facial_feature in landmarks.keys():
for landmark in landmarks[facial_feature]:
transferred_landmark = (landmark[0] - left, landmark[1] - top)
transferred_landmarks[facial_feature].append(transferred_landmark)
return transferred_landmarks
'''
写于2023年11月30日：对CASME2-RAW-video2jpg中的文件进行裁剪并且存到另一个文件夹中
'''
if __name__ == '__main__':
t1 = datetime.now()
image_root = 'D:/gyy_data/CASMEII/CASME2-RAW-video2jpg'
image_root_cropped = 'D:/gyy_data/CASMEII/CASME2-RAW-video2jpg_cropped'
sub_list = os.listdir(image_root)
for i in range(len(sub_list)):
sub_dir = os.path.join(image_root,sub_list[i])+'/'
sub_image_list = os.listdir(sub_dir)
sub_file_dir = os.path.join(image_root_cropped, sub_list[i]) + '/'
for j in range(len(sub_image_list)):
temp = sub_image_list[j]
jpg_dir_cropped = os.path.join(sub_file_dir,temp)+'/'
print(jpg_dir_cropped)
if not os.path.exists(jpg_dir_cropped):
os.makedirs(jpg_dir_cropped)
print("-----OK-----")
else:
print("文件夹已经存在！")
del_file(jpg_dir_cropped)
each_image_dir = os.path.join(sub_dir,sub_image_list[j])+'/'
print(each_image_dir)
root = os.listdir(each_image_dir)
for k in range(len(root)):
'''第一帧的路径'''
start_main = os.path.join(each_image_dir, root[0])
start_main_img_cv2 = cv2.imread(start_main)
start_main_img_cv2_PIL = Image.fromarray(cv2.cvtColor(start_main_img_cv2, cv2.COLOR_BGR2RGB))
start_main_img_cv2_PIL_array = np.array(start_main_img_cv2_PIL)
face_landmarks_list1 = face_recognition.face_landmarks(start_main_img_cv2_PIL_array, model="large")
face_landmarks_dict1 = face_landmarks_list1[0]
aligned_face1, eye_center1, angle1 = align_face(image_array=start_main_img_cv2_PIL_array,
landmarks=face_landmarks_dict1)
rotated_landmarks1 = rotate_landmarks(landmarks=face_landmarks_dict1,
eye_center=eye_center1, angle=angle1,
row=start_main_img_cv2_PIL_array.shape[0])
cropped_face1, left1, top1 = corp_face_unsize(image_array=aligned_face1,
landmarks=rotated_landmarks1)
'''图像路径'''
img_path = os.path.join(each_image_dir, root[k])
img_cv2 = cv2.imread(img_path)
img_cv2_PIL = Image.fromarray(cv2.cvtColor(img_cv2, cv2.COLOR_BGR2RGB))
img_cv2_PIL_array = np.array(img_cv2_PIL)
aligned_face, eye_center, angle = align_face(image_array=img_cv2_PIL_array,
landmarks=rotated_landmarks1)
rotated_landmarks = rotate_landmarks(landmarks=rotated_landmarks1,
eye_center=eye_center, angle=angle, row=img_cv2_PIL_array.shape[0])
cropped_face, left, top = corp_face_unsize(image_array=aligned_face,
landmarks=rotated_landmarks)
t_array, _, _ = align_face(image_array=cropped_face, landmarks=rotated_landmarks1)
t_PIL_cv2 = cv2.cvtColor(t_array, cv2.COLOR_RGB2BGR)
t_PIL_cv2_resize = cv2.resize(t_PIL_cv2, (224, 224))
print("Save into:", jpg_dir_cropped + root[k])
cv2.imwrite(jpg_dir_cropped + '/' + root[k], t_PIL_cv2_resize)
t2 = datetime.now()
print("Time cost = ", (t2 - t1))
print("SUCCEED !!!")
参考链接
- cv2 读取、显示、保存图片
- Py之face_alignment：face_alignment库的简介、安装、使用方法之详细攻略
- PIL，cv2读取类型及转换，以及PIL，numpy，tensor格式以及cuda，cpu的格式转换
- 【人脸】人脸检测与对齐python实现
- dlib实现脸部分割与人脸对齐
3466
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
