本文介绍MTFL人脸数据库的预处理方法，包括图像resize、坐标缩放、属性编码及图像翻转增强，适用于人脸特征点定位、性别、微笑、眼镜和姿态的多任务学习。
数据集下载链接：
http://mmlab.ie.cuhk.edu.hk/projects/TCDCN.html
github地址：
https://github.com/Mimsyy/Deep-learning-MTFL
Multi-Task Facial Landmark (MTFL人脸数据库)，这个数据库包括了12,995张人脸图片，每张图片都被做了一些标注。包括
（1）5个人脸特征点，包括左眼、右眼、鼻子、左嘴角、右嘴角。
（2）标记性别、微笑、眼镜、姿态。
标记数据格式
数据库被分成两个部分：training和tesing，标记的信息全部存放在txt文件中（traning和testing文件）。
文件中的每一行为一张人脸图片的标记信息，他的格式如下：
image path x1...x5,y1..y5 gender smile wearing glasses head pose
--x1...x5,y1...y5: 标记了左眼、右眼、鼻子、左嘴角、右嘴角的坐标位置。
--gender: 1代表男, 2代表女
--smile: 1代表微笑, 2代表不微笑。
--glasses: 1代表戴眼镜, 2代表没戴眼镜。
--head pose: 1 for left profile，2 for left, 3 for frontal, 4 for right, 5 for right profile
对数据预处理文件的解读
-
from PIL
import Image
-
import os
-
import numpy
as np
-
#数据集存放地址
-
folder = os.path.abspath(os.path.join(
"./", os.pardir)+
"/MTFL") +
"/"
-
#最终要将图全部resize成这个大小150*150
-
finalSize =
150
-
counter =
0
-
infoFiles = [
"training.txt",
"testing.txt"]
-
validation_counter =
0
-
#建立一个validation.txt文件用于存放验证数据信息
-
val_file = open(folder +
"validation.txt",
"a")
-
#"training.txt", "testing.txt"中的信息进行处理
-
for idx
in range(len(infoFiles)):
-
info = infoFiles[idx]
-
#当idx=0时读取training.txt，当idx=1时读取testing.txt
-
f = open(folder+info,
"r")
-
#打开一个新的文件，用于写入信息
-
fnew = open(
"tmp",
'a')
-
#当读取training.txt信息时，创建aug_training.txt文件
-
if idx ==
0:
-
fnew_augmented = open(folder+
"aug_"+info,
'a')
-
lines = f.readlines()
-
for line
in lines:
-
line = line.strip(
"\n ").split(
" ")
-
#获取到图片名称
-
imgName = line[
0].replace(
"\\",
"/")
-
if imgName ==
"":
-
break
-
#打开图片，读取图片的宽高
-
img = Image.open(folder+imgName, mode=
'r')
-
originalWidth = img.width
-
originalHeight = img.height
-
if (originalWidth != originalHeight):
-
# Skip non-square images，若高宽不一致则跳过
-
img.close()
-
continue
-
-
# Resize and check RGB，将图片resize到150*150
-
if(originalWidth != finalSize):
-
img = img.resize((finalSize, finalSize), Image.ANTIALIAS)
# Image.ANTIALIAS代表高质量
-
-
# Check if img is RGB or greyscale，若图片不是彩色图，则跳过
-
pixels = list(img.getdata())
-
width, height = img.size
-
pixelsArray = np.asarray([pixels[i * width:(i +
1) * width]
for i
in range(height)])
-
if len(pixelsArray.shape) !=
3:
-
# img is greyscale, skip it
-
img.close()
-
continue
-
-
coords = []
-
# 图片的缩放比例，若大小没有被调整该系数为1，若图像大小调整，同比缩放坐标数据，记录在coords中line[i][1]-line[i][10]
-
# 对应x1,x2,x3,x4,x5,y1,y2,y3,y4,y5: 标记了左眼、右眼、鼻子、左嘴角、右嘴角的坐标位置
-
coordsScaleFactor = float(finalSize) / float(originalWidth)
-
for i
in range(
1,
11):
-
coords.append(float(line[i])*coordsScaleFactor)
-
#属性gender,smile,glasses,head pose分别对应每行line[i][11]-line[i][14]
-
attributes = np.array([int(line[i])
for i
in range(
11,
15)])
-
-
#对testing.txt进行读取，生成1000个用于验证的图片信息于validation.txt中
-
if(idx ==
1
and validation_counter <=
1000):
-
#line[i][0]
-
val_file.write(imgName)
-
#写入特征点信息
-
for coord
in coords:
-
val_file.write(
" " + str(coord))
-
#写入属性信息
-
for attribute
in attributes:
-
val_file.write(
" " + str(attribute -
1))
# Subtract 1 for better indexing
-
val_file.write(
"\n")
-
validation_counter +=
1
-
# '''
-
# --gender: 1代表男, 2代表女
-
# --smile: 1代表微笑, 2代表不微笑。
-
# --glasses: 1代表戴眼镜, 2代表没戴眼镜。
-
# --head pose: 1 for left profile，2 for left, 3 for frontal, 4 for right, 5 for right profile
-
# attribute - 1:是为了使索引从0开始，方便训练
-
# '''
-
#剩下的写入fnew中用于训练
-
else:
-
# Write resized img to file
-
fnew.write(imgName)
-
for coord
in coords:
-
fnew.write(
" " + str(coord))
-
for attribute
in attributes:
-
fnew.write(
" " + str(attribute -
1))
# Subtract 1 for better indexing
-
fnew.write(
"\n")
-
-
# Mirror the image if it's not part of test data
-
if idx ==
0:
-
# Get the new img name,生成翻转图像的名称./MTFL/lfw_5590/Aaron_Eckhart_0001.jpg-->./MTFL/lfw_5590/Aaron_Eckhart_0001_transl.jpg
-
splitName = imgName.split(
'.')
-
imgNameTransp = splitName[
0] +
'_transl.' + splitName[
1]
-
-
# Mirror the image and save it
-
#左右翻转图像，存图
-
imgTransp = img.copy().transpose(Image.FLIP_LEFT_RIGHT)
-
imgTransp.save(folder+imgNameTransp)
-
imgTransp.close()
-
#生成对应翻转图像特征点及属性特征
-
coordsTransp = [
0
for i
in range(
10)]
-
# Translate x-coords for eyes, nose, and mouth
-
coordsTransp[
0] =
150 - coords[
1]
#左眼睛x1
-
coordsTransp[
1] =
150 - coords[
0]
#右眼睛x2
-
coordsTransp[
2] =
150 - coords[
2]
#鼻子x3
-
coordsTransp[
3] =
150 - coords[
4]
#左嘴角X4
-
coordsTransp[
4] =
150 - coords[
3]
#右嘴角x5
-
# Translate y-coords for eyes, nose, and mouth
-
coordsTransp[
5] = coords[
6]
#左眼睛y1
-
coordsTransp[
6] = coords[
5]
#右眼睛y2
-
coordsTransp[
7] = coords[
7]
#鼻子y3
-
coordsTransp[
8] = coords[
9]
#左嘴角y4
-
coordsTransp[
9] = coords[
8]
#右嘴角y5
-
# Translate attributes 属性变换gender,smile,glasses,head pose
-
attributesTransp = np.array([int(line[i])
for i
in range(
11,
15)])
-
attributesTransp[
3] =
6 - attributesTransp[
3]
# Translate head：1 for left profile，2 for left, 3 for frontal, 4 for right, 5 for right profile
-
-
# Write resized old img to augmented file，写入原图的图像信息
-
fnew_augmented.write(imgName)
-
for coord
in coords:
-
fnew_augmented.write(
" " + str(coord))
-
for attribute
in attributes:
-
fnew_augmented.write(
" " + str(attribute -
1))
-
fnew_augmented.write(
"\n")
-
-
# Write mirrored img to augmented file，写入翻转后的图像信息
-
fnew_augmented.write(imgNameTransp)
-
for coord
in coordsTransp:
-
fnew_augmented.write(
" " + str(coord))
-
for attribute
in attributesTransp:
-
fnew_augmented.write(
" " + str(attribute -
1))
-
fnew_augmented.write(
"\n")
-
-
# Save resized img 存的都是resize到150*150的图片
-
img.save(folder+imgName)
-
img.close()
-
-
counter = counter +
1
-
if counter %
1000 ==
0:
-
print(counter,
"files processed")
-
#对"training.txt"/"testing.txt"中的每一行读完之后，就关闭该文件
-
f.close()
-
#对"training.txt"/"testing.txt"中的每一行数据进行操作完成，写入完毕后，就关闭该"tmp"文件
-
fnew.close()
-
#关闭aug_training.txt
-
if idx ==
0:
-
fnew_augmented.close()
-
#删除之前的"training.txt"/"testing.txt"
-
os.remove(folder+info)
-
#将tmp重命名为"training.txt"/"testing.txt"
-
os.rename(
"tmp",folder+info)
-
#都循环完毕后，关闭validation.txt
-
val_file.close()
扫一扫
1271
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
