Learn practical skills, build real-world projects, and advance your career

Face Recognition

Face recognition is machine learning application, in which machine learns to identify the human face in the image.
As we know machine learning model need a lots of data, on which we need to train it. Hence to identify a human face in the image we will need lots of pictures with human faces and pictures without human faces. It requires lot time to train this type of model, hence we will use the already trained model, which is very accurate in detecting the faces. Hence we are going to use Face_Recognition package to identification of faces.

Objectives

To create a Face Recognition System we will need to achieve following objectives:

1. Requirement Analysis

In this step we need to list out the all required packages and tool for development of the system.

2. Feature Extraction

A image cantain lot of noisy data, so we need to remove those unnecessary data and need to extract the features which will be useful for detecting the faces.

3. Face Detection

To recognise the face in a picture we first need to check that is there any human face in the picture or not. and if the human face is in the picture then we need to locate the face in the picture.

4. Face Recognition

now, as we located the face in the picture we need to recognize that face. for that we need a database with persone names and there pictures. we will compare the face in the inputed picture and the face in the picture got from database.

Requirement Analysis

As our whole project is going to be in python so we will need some python packages.

  1. os - We will need the os library to access the device folders.
  2. OpenCV - To do operations on the picture
  3. Face_Recognition - For face detection and Recogition
  4. Matplotlib - To display the pictures
  5. skimage - to do feature extraction related tasks.

We will import these libraries differently for each step, so that we can understand which library we will need for which task.

!pip install opencv-python
Collecting opencv-python Downloading opencv_python-4.3.0.38-cp37-cp37m-manylinux2014_x86_64.whl (49.3 MB) |████████████████████████████████| 49.3 MB 3.2 MB/s eta 0:00:01 Requirement already satisfied: numpy>=1.14.5 in ./anaconda3/lib/python3.7/site-packages (from opencv-python) (1.18.1) Installing collected packages: opencv-python Successfully installed opencv-python-4.3.0.38
!pip install cmake
Collecting cmake Downloading cmake-3.18.0-py3-none-manylinux1_x86_64.whl (18.2 MB) |████████████████████████████████| 18.2 MB 2.0 MB/s eta 0:00:01 Installing collected packages: cmake Successfully installed cmake-3.18.0