目录
一.基于LibSVM得到决策函数
1.下载Libsvm
地址：https://www.csie.ntu.edu.tw/~cjlin/libsvm/.
2.解压后导入
1.下载好的zip文件解压得到下方的文件
2.在idea中新建java文件，引入解压后得到得Java文件内容
3.准备需要实验的数据
1.打开libsvm文件下的windows文件里面的svm-toy程序
2.点击run
4.进行训练
1.新建Main的class的类用于训练
2.输入以下代码：
import java.io.IOException;
public class Main {
public static void main(String[] args) throws IOException {
// write your code here
//存放数据以及保存模型文件路径
String filepath = "D:\\32\\";
/**
* -s 设置svm类型：默认值为0
* 0– C-SVC
* 1 – v-SVC
* 2 – one-class-SVM
* 3 –ε-SVR
* 4 – n - SVR
*
* -t 设置核函数类型，默认值为2
* 0 --线性核
* 1 --多项式核
* 2 -- RBF核
* 3 -- sigmoid核
*
* -d degree:设置多项式核中degree的值，默认为3
*
* -c cost：设置C-SVC、ε-SVR、n - SVR中从惩罚系数C，默认值为1；
*/
String[] arg = {"-s","0","-c","10","-t","0",filepath+"data.txt",filepath+"line.txt"};
System.out.println("----------------线性-----------------");
//训练函数
svm_train.main(arg);
arg[5]="1";
arg[7]=filepath+"poly.txt";//输出文件路径
System.out.println("---------------多项式-----------------");
svm_train.main(arg);
arg[5]="2";
arg[7]=filepath+"RBF.txt";
System.out.println("---------------高斯核-----------------");
svm_train.main(arg);
}
}
3.点击运行，得到结果
5.输出文件
data.txt训练数据
line.txt线性模型
poly多项式模型
RBF高斯核模型
1.线性模型
2.多项式模型
3.高斯核模型
6.决策函数
根据公式f(x)=wT*x+b以及模型数据可以求得最终的决策函数。wT为向量的转置矩阵,即为模型数据中的SV
b为偏置常数，即为数据模型中的rho.
二.人脸识别数据集的建立
1.人脸数据采集
import numpy as np
import cv2
import dlib
import os
import sys
import random
# 存储位置
output_dir = 'C:/Users/DELL/face'
size = 64
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# 改变图片的亮度与对比度
def relight(img, light=1, bias=0):
w = img.shape[1]
h = img.shape[0]
#image = []
for i in range(0,w):
for j in range(0,h):
for c in range(3):
tmp = int(img[j,i,c]*light + bias)
if tmp > 255:
tmp = 255
elif tmp < 0:
tmp = 0
img[j,i,c] = tmp
return img
#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()
# 打开摄像头 参数为输入流，可以为摄像头或视频文件
camera = cv2.VideoCapture(0)
#camera = cv2.VideoCapture('C:/Users/CUNGU/Videos/Captures/wang.mp4')
ok = True
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor('D:/27/shape_predictor_68_face_landmarks.dat')
index=1
while ok:
if (index <= 20):#存储20张人脸特征图像
print('Being processed picture %s' % index)
# 从摄像头读取照片
success, img = camera.read()
# 转为灰度图片
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 使用detector进行人脸检测
dets = detector(gray_img, 1)
for i, d in enumerate(dets):
x1 = d.top() if d.top() > 0 else 0
y1 = d.bottom() if d.bottom() > 0 else 0
x2 = d.left() if d.left() > 0 else 0
y2 = d.right() if d.right() > 0 else 0
face = img[x1:y1,x2:y2]
face = cv2.resize(face, (size,size))
cv2.imwrite(output_dir+'/'+str(index)+'.jpg', face)
img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
rects = detector(img_gray, 0)
for i in range(len(rects)):
landmarks = np.matrix([[p.x, p.y] for p in predictor(img,rects[i]).parts()])
for idx, point in enumerate(landmarks):
# 68点的坐标
pos = point[0, 0], point[0, 1]
print(idx,pos)
if (index <= 20):
file = open('D:/27/'+str(index)+'.txt', 'a')
s=str(pos)
s = s.replace("(", "")
s = s.replace(")", "")
s = s.replace(",","")
file.write(s+'\n')
# 利用cv2.circle给每个特征点画一个圈，共68个
cv2.circle(img, pos, 2, color=(0, 255, 0))
# 利用cv2.putText输出1-68
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(img, str(idx+1), pos, font, 0.2, (0, 0, 255), 1,cv2.LINE_AA)
cv2.imshow('video', img)
index += 1
if index == 20:
break
camera.release()
cv2.destroyAllWindows()
2.数据集的建立
# 从人脸图像文件中提取人脸特征存入 CSV
# Features extraction from images and save into features_all.csv
# return_128d_features() 获取某张图像的128D特征
# compute_the_mean() 计算128D特征均值
from cv2 import cv2 as cv2
import os
import dlib
from skimage import io
import csv
import numpy as np
# 要读取人脸图像文件的路径
path_images_from_camera ="D:/28/"
# Dlib 正向人脸检测器
detector = dlib.get_frontal_face_detector()
# Dlib 人脸预测器
predictor = dlib.shape_predictor("D:/27/shape_predictor_68_face_landmarks.dat")
# Dlib 人脸识别模型
# Face recognition model, the object maps human faces into 128D vectors
face_rec = dlib.face_recognition_model_v1("D:/27/dlib_face_recognition_resnet_model_v1.dat")
# 返回单张图像的 128D 特征
def return_128d_features(path_img):
img_rd = io.imread(path_img)
img_gray = cv2.cvtColor(img_rd, cv2.COLOR_BGR2RGB)
faces = detector(img_gray, 1)
print("%-40s %-20s" % ("检测到人脸的图像 / image with faces detected:", path_img), '\n')
# 因为有可能截下来的人脸再去检测，检测不出来人脸了
# 所以要确保是 检测到人脸的人脸图像 拿去算特征
if len(faces) != 0:
shape = predictor(img_gray, faces[0])
face_descriptor = face_rec.compute_face_descriptor(img_gray, shape)
else:
face_descriptor = 0
print("no face")
return face_descriptor
# 将文件夹中照片特征提取出来, 写入 CSV
def return_features_mean_personX(path_faces_personX):
features_list_personX = []
photos_list = os.listdir(path_faces_personX)
if photos_list:
for i in range(len(photos_list)):
# 调用return_128d_features()得到128d特征
print("%-40s %-20s" % ("正在读的人脸图像 / image to read:", path_faces_personX + "/" + photos_list[i]))
features_128d = return_128d_features(path_faces_personX + "/" + photos_list[i])
# print(features_128d)
# 遇到没有检测出人脸的图片跳过
if features_128d == 0:
i += 1
else:
features_list_personX.append(features_128d)
i1=str(i+1)
add="D:/29/face_feature"+i1+".csv"
print(add)
with open(add, "w", newline="") as csvfile:
writer1 = csv.writer(csvfile)
writer1.writerow(features_128d)
else:
print("文件夹内图像文件为空 / Warning: No images in " + path_faces_personX + '/', '\n')
# 计算 128D 特征的均值
# N x 128D -> 1 x 128D
if features_list_personX:
features_mean_personX = np.array(features_list_personX).mean(axis=0)
else:
features_mean_personX = '0'
return features_mean_personX
# 读取某人所有的人脸图像的数据
people = os.listdir(path_images_from_camera)
people.sort()
with open("D:/29/features2_all.csv", "w", newline="") as csvfile:
writer = csv.writer(csvfile)
for person in people:
print("##### " + person + " #####")
# Get the mean/average features of face/personX, it will be a list with a length of 128D
features_mean_personX = return_features_mean_personX(path_images_from_camera + person)
writer.writerow(features_mean_personX)
print("特征均值 / The mean of features:", list(features_mean_personX))
print('\n')
print("所有录入人脸数据存入 / Save all the features of faces registered into: D:/29/features_all2.csv")
三.总结
通过本次实验，我学习到了如何使用libSVM处理决策函数以及采集到本人脸信息的基本过程，并将把采集到的人脸信息后续运用到人脸识别中去。
四.参考文献
https://blog.csdn.net/qq_47281915/article/details/121307709?spm=1001.2014.3001.5501.