Shulou(Shulou.com)06/02 Report--

This article introduces the knowledge of "how to use Python to achieve face recognition function". In the operation of actual cases, many people will encounter such a dilemma, so let the editor lead you to learn how to deal with these situations. I hope you can read it carefully and be able to achieve something!

With the stunning performance of alphago last year, AI has once again become the darling of technology companies. AI involves many fields, and face recognition in image recognition is one of the interesting branches. Baidu's BFR,Face++ open platform, Hanwang, iFLYTEK and so on all provide face recognition API. For old code farmers, write a short piece of code to see how many people there are in a picture. It's not classy, it's just fun, and it only takes 7 lines of code.

Import cv2face_patterns = cv2.CascadeClassifier ('/ usr/local/opt/opencv3/share/OpenCV/haarcascades/haarcascade_frontalface_default.xml') sample_image = cv2.imread ('/ Users/abel/201612.jpg') 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, y), (0,255,0) 2) cv2.imwrite ('/ Users/abel/201612_detected.png', sample_image) Line 1 introduces OpenCV

Open source is great, it broadens our horizons and doesn't have to repeat the wheels. Instead of using PIL, combined with a specific algorithm, OpenCV (http://opencv.org)) is used directly. OpenCV is a cross-platform computer vision library based on BSD license, which can be run on Linux, Windows and Mac OS operating systems. It is lightweight and efficient. It is written in C Universe + and provides interfaces such as Python, Ruby, MATLAB, etc., and implements many general algorithms in image processing and computer vision.

Line 2 loads the classifier cv2.CascadeClassifier

CascadeClassifier is a cascade classifier for face detection in Opencv, which encapsulates the target detection mechanism, that is, sliding window mechanism + cascade classifier. The data structure includes two main parts: Data and FeatureEvaluator. What is stored in Data is the classifier data loaded from the trained xml file, while in FeatureEvaluator it is about the loading, storage and calculation of features. The training file used here is haarcascadefrontalfacedefault.xml, which is provided by default in OpenCV. As for the specific principle of Haar,LBP, you can refer to the relevant documents of opencv, simply, it can be understood as the feature data of human face.

Line 3 loads the target picture imread

Face recognition system is generally divided into: face image acquisition, face image preprocessing, face image feature extraction and matching and recognition. For the sake of simplicity, read in between the pictures, this is a group photo of the closed-door meeting in Beijing last year.

Line 4 Multi-scale Detection detectMultiScale

Call the detectMultiScale function in CascadeClassifier for multi-scale detection, and the single-scale method detectSingleScale will be called in multi-scale detection. Parameter description:

ScaleFactor is the scaling factor of the image

MinNeighbors is the number of neighbors that should be reserved for each cascade rectangle, which can be understood as how many faces there are around a person.

MinSize is the size of the detection window

These parameters can be adjusted for the picture, and the processing result returns a list of rectangular objects of the human face.

Lines 5 and 6 draw a box for each face

Read the list of rectangular objects of the face in a loop, get the coordinates and width and height of the rectangle of the face, and then draw the rectangle in the original picture, calling the rectangle method of OpenCV, in which the color of the rectangle is adjustable.

Line 7 holds the results of the test

When everything is ready, call imwrite to save the tested results to the specified location. The result is as follows:

The mystery is not these seven lines of code, but the related implementation in OpenCV. OpenCV's Chinese website is also a good place to learn and experience.

So, seven lines of code is just a gimmick, and the real core is OpenCV. Then, there are some pits when you install the OpenCV environment, so make a special note.

OpenCV environment based on Mac

It is recommended to use Brew installation. If brew is not installed, execute the following command first:

$/ usr/bin/ruby-e "$(curl-fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"

Then, specify the target warehouse $brew tap homebrew/science

Install OpenCV3 $brew install opencv3

The installation speed depends on the network. After installation, you need to bind the Python development environment. There are many native methods:

1) add the environment variable to add the site-packages of opencv to the PYTHONPATH

2) use ln soft connection to link cv2.so to site-packages in python environment

3) cp cv2.so directly to the site-packages directory of the python environment

It is more simple to execute the following command:

Echo / usr/local/opt/opencv3/lib/python2.7/site-packages > > / usr/local/lib/python2.7/site-packages/opencv3.pth mkdir-p / Users/hecom/.local/lib/python2.7/site-packages echo 'import site; site.addsitedir ("/ usr/local/lib/python2.7/site-packages")' > / Users/hecom/.local/lib/python2.7/site-packages/homebrew.pth for obsessive-compulsive disorder

You can fully install various plug-ins of opencv, such as QT plug-ins, video plug-ins, etc.:

Brew install opencv3-- with-contrib-- with-cuda-- with-ffmpeg-- with-tbb-- with-qt5

You may encounter many pits, such as Error: You must 'brew link texi2html' before homebrew/science/opencv3 can be installed

When you execute $brew link texi2html, you will encounter another error: Error: Cowardly refusing to 'sudo brew link' You can use brew with sudo, but only if the brew executable is owned by root. However, this is both not recommended and completely unsupported so do so atyour own risk

Indicates that there is a problem with the permission of brew, which needs to be solved: $sudo chown root:wheel 'which brew'

Source installation of OpenCV3 on Ubuntu

To install on Ubantu, you need to do some preparatory activities.

$aptitude-f install$ sudo apt-get update

Then install the compilation environment: $sudo apt-get install build-essential

Install the dependent library $sudo apt-get install cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev and install the python dependency and other dependent libraries $sudo apt-get install python-dev python-numpy libtbb2 libtbb-dev libjpeg-dev libpng-dev libtiff-dev libjasper-dev libdc1394-22-dev

Get the opencv source code git clone https://github.com/Itseez/opencv.git

You can finally compile and install:

$cd opencv$cmake-D CMAKE_INSTALL_PREFIX=/home/opencv/build-D CMAKE_BUILD_TYPE=RELEASE..

Finally, install python-opencv:

$sudo apt-get install python-opencv

Simple Verification of Python Environment for OpenCV

One line of code verifies that the Python environment for OpenCV is successful:

$python-c "import cv2; print dir (cv2)"

If you output a lot of dictionaries of cv2's properties and function names, it is successful; otherwise, you need to continue to fill in the hole.

This is the end of the content of "how to use Python to achieve face recognition". Thank you for reading. If you want to know more about the industry, you can follow the website, the editor will output more high-quality practical articles for you!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.