python+opencv 做人臉識別
一.準備工作
對於Linux作業系統
1.安裝Python
2.安裝依賴庫，命令如下：
yum install cmake gcc gcc-c++ gtk2-devel gimp-develgimp-devel-tools gimp-help-browser zlib-devel libtiff-devel libjpeg-devellibpng-devel gstreamer-devel libavc1394-devel libraw1394-devel libdc1394-develjasper-devel jasper-utils swig python libtool nasm
3.安裝opencv
1、下載 http://sourceforge.net/projects/opencvlibrary/files/opencv-unix/2.4.9/opencv-2.4.9.zip/download
並解壓opencv2.49
2、安裝依賴的庫sudo apt-get install build-essential cmake libgtk2.0-dev pkg-config python-dev python-numpy libavcodec-dev libavformat-dev libswscale-dev
3、安裝opencv
cd opencv2.49
mkdir build
cd build
cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local ..
make
sudo make install
3、拷貝cv2.so （查詢其路徑的命令 find / -name cv2.so ）
cp /usr/local/lib/python2.7/site-packages/cv* /usr/local/lib/python2.7/site-packages/ #第二個路徑是根據你使用的Python的site-packages目錄位置決定的，如果你使用的是anaconda ，複製cv2.so 到anaconda下的site-packages下
二.python 程式如下
import cv2
import sys
path=sys.argv[1]
face_patterns = cv2.CascadeClassifier('/usr/local/opt/opencv3/share/OpenCV/haarcascades/haarcascade_frontalface_default.xml')
#haarcascade_frontalface_default.xml 檔案在你opencv下有，查找出來自己的路徑
sample_image = cv2.imread(path)
faces = face_patterns.detectMultiScale(sample_image,scaleFactor=1.1,minNeighbors=5,minSize=(100, 100))for (x, y, w, h) in faces:
cv2.rectangle(sample_image, (x, y), (x+w, y+h), (0, 255, 0), 2)
cv2.imwrite('/Users/abel/test.png', sample_image);
儲存為face-rg.py
$python face-rg.py /home/maicaijian/test_1.jpg #命令後面的路徑是圖片的路徑
執行效果如下：
