This project was aimed at face detection and recognition. We used HOG face detector for face detection and CNN for recognition. This application provides plastic and accurate opportunities for adding new faces. You can add one face by a line of code or select folder with named images for adding to database. Then you need just to call one function on desired image to get your image with selected and signed faces. Also, you can turn on selecting with rectangle unknown faces.

The application is written with Python 3.5. We used OpenCV, dlib and scikit-learn modules. It is easy to integrate our application in your system.

The main advantage of our application is high accuracy and flexibility. Let’s look on few examples.

First, we need to create new database by adding new faces, I gathered images of few people in one folder with file names as names of people on photo:

Face Detection and Recognition (1)

After that we start adding process which takes 7 second for my notebook. And now we able to recognize this people on different images! Now take few images of this people in different time of their lives and see result. For example, Steve Jobs and Steve Wozniak in youth:

Face Detection and Recognition (2) Face Detection and Recognition (3)

Moreover, we can try to process different photos of other people in our database:

Face Detection and Recognition (4) Face Detection and Recognition (5)

We can also turn on signing of unknown faces:

Face Detection and Recognition (6)

Face Detection and Recognition (7)

Languages: Python


“Of all the frictional resistances, the one that most retards human movement is ignorance, what Buddha called ‘the greatest evil in the world.’ The friction which results from ignorance … can be reduced only by the spread of knowledge and the unification of the heterogeneous elements of humanity. No effort could be better spent.”

Nikola Tesla