Real-Time Face Recognition Using Python And OpenCV

Aquib Javed Khan is a freelance technical writer. His interests include computer vision and mechatronic systems


A real time face recognition system is capable of identifying or verifying a person from a video frame. To recognize the face in a frame, first you need to detect whether the face is present in the frame. If it is present, mark it as a region of interest (ROI), extract the ROI and process it for facial recognition.

Real time face recognition software

This project is divided into two parts: creating a database, and training and testing.

Creating a database

Take pictures of the person for face recognition after running script. It automatically creates Train folder in Database folder containing the face to be recognised. You can change the name from Train to the person’s name.

While creating the database, the face images must have different expressions, which is why a 0.38-second delay is given in the code for creating the data set. In this example, we take about 45 pictures/images and extract the face, convert it into grayscale and save it to the database folder with its name.

Training and testing

Training and face recognition is done next. code does everything. The algorithm used here is Local Binary Patterns Histograms (LBPH).

Screenshot of Haar features | real time face recognition
Fig. 1: Screenshot of Haar features

Face detection is the process of finding or locating one or more human faces in a frame or image. Haar-like feature algorithm by Viola and Jones is used for face detection. In Haar features, all human faces share some common properties. These regularities may be matched using Haar features, as shown in Fig. 1.

Two properties common to human faces are:

  1. The eye region is darker than the upper cheeks.
  2. The nose bridge region is brighter than the eyes.

Composition of two properties forming matchable facial features are:

  1. Location and size including eyes, mouth and bridge of nose.
  2. Value for oriented gradients of pixel intensities.

For example, the difference in brightness between white and black rectangles over a specific area is given by:

Value = Σ (pixels in black area)- Σ (pixels in white area)

The above-mentioned four features matched by Haar algorithm are compared in the image of a face shown on the left of Fig. 1.

Testing procedure

Install OpenCV and Python on Ubuntu 16.04

The project was tested on Ubuntu 16.04 using OpenCV 2.4.10. The following shell script installs all dependencies required for OpenCV and also install OpenCV 2.4.10.

$ sh ./

After installing OpenCV, check it in the terminal using import command, as shown in Fig. 2.

Checking OpenCV using import command
Fig. 2: Checking OpenCV using import command
Creating the database
Fig. 3: Creating the database

1. Create the database and run the recogniser script, as given below (also shown in Fig. 3). Make at least two data sets in the database.

$ python person_name

2. Run the recogniser script, as given below:

$ python

This will start the training, and the camera will open up, as shown in Fig. 4. Accuracy depends on the number of data sets as well as the quality and lighting conditions.

 Screenshot of real time face recognition
Fig. 4: Screenshot of face detection

OpenCV 2.4.10.

OpenCV provides the following three face recognisers:

  1. Eigenface recogniser
  2. Fisherface recogniser
  3. LBPH face recogniser

In this project, LBPH face recognition is used, which is createLBPHFaceRecognizer( ) function.

LBP works on gray-scale images. For every pixel in a gray-scale image, a neighbourhood is selected around the current pixel and LBP value is calculated for the pixel using the neighbourhood.

After calculating LBP value of the current pixel, the corresponding pixel location is updated in the LBP mask (it is of same height and width as input image.) with LBP value calculated, as shown in Fig. 5.

Screenshot of a LBPH face recogniser
Fig. 5: Screenshot of a LBPH face recogniser

In the image, there are eight neighbouring pixels. If the current pixel value is greater than or equal to the neighbouring pixel value, the corresponding bit in the binary array is set to 1. But if the current pixel value is less than the neighbouring pixel value, the corresponding bit in the binary array is set to 0.

Download source code

Interested in face detection projects? Check out face recognition using Raspberry Pi.

This article was first published on 21 July 2017 and was updated on 29 May 2019.


  1. Hi, I’ve downloaded the source code and am able to create a database from file. But, am getting an issue while running file. My webcam is getting started! Can you please help me out here?

    • python abc
      Traceback (most recent call last):
      File “”, line 2, in
      import cv2, sys, numpy, os, time
      File “C:\Python27\lib\site-packages\cv2\”, line 2, in from . import cv2
      ImportError: DLL load failed: The specified module could not be found.

  2. i’m getting this error :
    fn_name = sys.argv[1] #name of the person
    IndexError: list index out of range

    please tell me solution????

  3. Hello Aquib,
    I need a custom development related to face recognition and I´m not a programmer. How can we be in touch?

  4. Hello aquib,
    Initially webcam wasn’t showing up but i changes argv to [0] then webcam showed up. but after that it is not capturing the images of mine.
    How to do that ?

    • The reply from author Aquib Javed Khan.
      “argv[0] has nothing to do with webcam, cap=VideoCapture(0) instead of 0 put 1 for external webcam”

  5. Hi Aquib,
    i have follow your instruction and the code was worked for create database, but when i used “python” I got an error like this

    Traceback (most recent call last):
    File “”, line 29, in
    model = cv2.face.createFisherFaceRecognizer()
    AttributeError: ‘module’ object has no attribute ‘createFisherFaceRecognizer’

    how to solve this problem?

  6. Please help.

    OpenCV Error: Bad argument (Empty training data was given. You’ll need more than one sample to learn a model.) in train, file /io/opencv_contrib/modules/face/src/fisher_faces.cpp, line 71
    Traceback (most recent call last):
    File “”, line 30, in
    model.train(images, lables)
    cv2.error: /io/opencv_contrib/modules/face/src/fisher_faces.cpp:71: error: (-5) Empty training data was given. You’ll need more than one sample to learn a model. in function train

  7. The seems to be incomplete code. Camera is not opening. I only get “Training….” and then it closes. For att_faces I had to download it myself. 🙁

    • The author Aquib Javed Khan replies: It’s not necessary to download but if some one is starting first time and need to download. You need to give more than two samples during training. Probably you are training on one sample only. There is no problem in the program. You may read the article again to understand the training process.

  8. face integration with eyeglasses.
    i have this idea about helping someone finding the right type of fit and shape of eyeglass/frames on their face as i am an optometrist.. can anyone help me on this? i believe with new technologies, it is email [email protected]

  9. sir,
    i am new to python.I have recently downloaded the source code .getting some indentation errors, can you please solve error for me.
    below is the code where i am getting errors
    please send me a reply

    if faces:
    face_i = faces[0]
    (x, y, w, h) = [v * size for v in face_i]
    face = gray[y:y + h, x:x + w]
    face_resize = cv2.resize(face, (im_width, im_height))
    pin=sorted([int(n[:n.find(‘.’)]) for n in os.listdir(path)
    if n[0]!=’.’ ]+[0])[-1] + 1
    cv2.imwrite(‘%s/%s.png’ % (path, pin), face_resize)
    cv2.rectangle(im, (x, y), (x + w, y + h), (0, 255, 0), 3)
    cv2.putText(im, fn_name, (x – 10, y – 10), cv2.FONT_HERSHEY_PLAIN,1,(0, 255, 0))
    count += 1

  10. if you are getting indentation error then download notepad++ in your system. Then open this file with notepad++ and replace all tabs(Arrows) with space(dots). This worked for this.

  11. Please help me sir,
    After adding the images to database and while running the the program stopped after printing “Training…”. Where can I find the remaining program to recognize the face. In your output, that “””This will start the training, and the camera will open up, as shown”‘” but it does not happen.

    Thanks in Advance.

  12. I m getting error like Traceback (most recent call last):
    File “”, line 24, in
    mini = cv2.resize (gray (gray.shape[0] / int(size), gray.shape[1] / int(size)))
    TypeError: ‘numpy.ndarray’ object is not callable

    please help me to solve this error

  13. thank you for the information very useful, but I have a little problem when running the application error as follows

    Traceback (most recent call last):
    File “.\”, line 31, in
    model = cv2.face.createFisherFaceRecognizer()
    AttributeError: module ‘cv2.cv2’ has no attribute ‘face’

    what should I do so the application can run thank you

  14. File “”, line 25, in
    mini = cv2.resize(gray, (gray.shape[1] / size, gray.shape[0] / size))
    TypeError: integer argument expected, got float

    • While resizing grayscale image it should not be a float vaules to be resized.

  15. I got this Error please Help ?

    ———————–Taking pictures———————-
    ——————–Give some expressions———————
    Traceback (most recent call last):
    File “/data/user/0/ru.iiec.pydroid3/files/accomp_files/iiec_run/”, line 31, in
    File “/data/user/0/ru.iiec.pydroid3/files/accomp_files/iiec_run/”, line 30, in start
    exec(open(mainpyfile).read(), __main__.__dict__)
    File “”, line 22, in
    cv2.error: OpenCV(4.3.0) /data/data/ru.iiec.pydroid3/app_HOME/opencv/opencv-python-master/opencv/modules/imgproc/src/color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function ‘cvtColor’

    [Program finished]

  16. File “”, line 37
    TabError: inconsistent use of tabs and spaces in indentation

  17. File “”, line 19
    images.append(cv2.imread(path, 0))
    TabError: inconsistent use of tabs and spaces in indentation

  18. Hello, i have downloaded this file but im getting a few issues on executing create_database.
    faces = haar_cascade.detectMultiScale(mini)
    Syntax error invalid syntax

  19. This type of error occurs because Python doesn’t know what to do when it encounters wrong indentation.
    So type the code again by maintaining proper indentation.


Please enter your comment!
Please enter your name here