Skip to main content

Facial Landmarks Detection with DLIB Library

By
This week, my friend from my country started to do intership at University of Liverpool with me. Her name is Maksude Tuğçe Zile. We will work on a Project that involves measuring angles and distances between spesific landmarks in facial images. We will prefer to Python programming languages because my final Project was about opencv with python. We will try to place a point spesific landmarks in human's faces.(for instance we want to detect eye right outer and eye right inner etc. ) I am going to show how to detect eyes and eyebrows with opencv using dlib library.

What is Facial Landmark Detection ?

 Facial Landmark Detection is a computer vision topic and it deals with the problem of detecting distinctive features in human faces automatically.
  • Tip of the nose
  • Corners of the eyes
  • Corners of the eyebrows
  • Corners of the mouth
  • Eye pupils
The detected landmarks are used in several different applications.

 How to install Dlib ?

 Dlib is a modern C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.

We will use python programming language on Windows. To compile Dlib on Windows could be difficult. I have used steps shown as follow:

Step 1: Install Visual Studio 2015
Step 2: Install CMake v3.8.2
Step 3: Install Anaconda 3
Step 4: Download Dlib
Step 5: Build Dlib library
Step 6: Build Dlib examples
Step 7: Install Dlib’s Python modüle

For more details, you can visit this tutorial.

Comments

Post a Comment

Popular posts from this blog

New Method to Take an Correctly Images

By
To take a correct images are very important to get  good results.We have tested a lot of photos. We couldn't get correct result some photos to detect types of eyes. So, most important thing, it must be straight face pose when you take a photo. We are trying to avoid to take a picture with wrong angle.
1 comment
Read more

First Day in University of Liverpool

By
The morning of my first day at University of Liverpool. It wasn`t very hard to find this university, because my place that I stay is very near. I was so excited to meet Dr. Waleed. He supported me to come here. Firstly, He introduced me the university. Then we went to laboratories that I will work in. He introduced me other students, Joel,Elisha & Matt. They are very kindly and friendly. This lab a bit larger than my home university`s labs. There are a lot of electronic components that I can use. I would like to study here. I may be do master, why not? This lab has excellent dedicates  facilities for researcher. I`m going to work on image processing to track fish actions. I will try to develop smart app with my team. I hope it will be perfect experience for me.  This week will be good opportunity to get used to here and getting know other students.
Post a Comment
Read more

Creating a Database for Wide-Close-Normal Eyes

By
In this stage, we are trying to classify different eyes shapes. The most important thing in this classification is distance between of two eyes. For example, if the space between two eyes is smaller than the width of one eye, this is close set eye or if vice versa, this is wide set eye. For normal set eyes, we specified a tolerance value and tested over approx. a hundred images. Then, we classified these images which called wide-close- normal eyes. In next stage, we will try in our program each image and make a histogram to get a correct result for classification. For instance this is close set eyes. Normal Set Eyes Wide Set Eyes Close Set Eyes
Post a Comment
Read more