Perform facial recognition with Python libraries MediaPipe, Dlib, and DeepFace. Explore face detection, analytics, and transformation effects, gaining crucial biometric software skills.

updated_FA.tar.gz

setup

Face Detection

Face Landmarking Using Dlib

Face Landmarking Using MediaPipe

Delaunay Triangulation of Facial Landmarks

Face Alignment

Age Prediction

Gender Prediction

Emotions Prediction

Race Prediction

Recognizing Eyes Color

Calculating Eyes Open Ratio

Detecting Eyeglasses

Recognizing Lips Color

Changing Lips Color

Detecting Skin Color

Swapping Faces

Swapping Eyes

Drawing Face Filter

Blurring Face

Cartooning Face

Face Encoding

Face Matching - Manhattan

Face Matching - Euclidean

Try Virtual Glasses

Change Background

Expand Face Features

Remove Background

Predict Beauty

Detect Face Shape

Condense Eyebrows

Drawing Eyeliners

Applying Blush

Detect Hair Color

Change Hair Color

Aging Faces

Auto-colorize Facial Photos

Calculate Face Golden Ratios

Add AR effects To Facial Photos

Face analysis technology is a rapidly growing biometric software discipline with wide-ranging applications in surveillance, forensics, game design, and social media. As with other machine learning domains, Python has several libraries for computer vision, image analysis, and pattern recognition that make it ideal for facial analysis.

This course is a hands-on introduction to facial recognition with three unique libraries—MediaPipe, Dlib, and DeepFace. You’ll start with face detection, landmarking, and face alignment before exploring common analytics like age, gender, and emotional prediction based on facial expressions. Next, you’ll identify common facial features before transforming them by adding blurring, sketching, and cartoon effects or swapping color palettes. You’ll finish by performing full makeover functions, manipulating cheeks, lips, eyes, and brows.

By the end of this course, you’ll have a strong foundation in popular facial recognition and manipulation libraries in Python.

Analyzing and Transforming Faces in Python

## Introduction ##

This lesson provides the steps needed to develop a utility that swaps specific facial components. For the sake of this lesson, we’ll emphasize the mechanism of swapping an eye between two face images.

This utility will enable you to try out different eye colors since you can swap your eye color with a different one.  Afterwards, you’ll be able to see the difference between your current eye color and the new eye.


## Dependencies ##

We’ll be using the following external Python libraries.

align-center

## Let’s code the utility!

Let’s take a look at the main function of this utility.

### The `swap_facial_component` function

The core function of this utility aims to illustrate the steps taken to swap one facial component (the eye component) in a chosen facial image (the destination image) and another one that has already been selected as a template (the swap image). Let’s learn about this function:

* **Line 6** initializes DLib detector and landmarks predictor.
* **Lines 9–10** load the swap image (source image).
* **Line 13** loads the destination image.
* **Line 18** gathers the list of face components and their respective indexes. The `FACIAL_LANDMARKS_IDXS` dictionary inside `face_utils` in the `imutils` library returns the mapping of the main facial regions like the mouth (points 48 to 68), the left eye (points 42 to 48), and so on.
* **Line 22** loops over the detected faces in the source image and, for each face that is detected, assigns an identifier to it. Then, its respective landmarks and the landmarks relative to the selected face component are grabbed. For the purpose of this lesson, we selected the left eye as a face component.
* **Lines 27–31** output a message that shows the face identifier and its location.
* **Lines 34–35** segment the detected face component into triangles using the Delaunay triangulation technique and draw the triangles generated.
* **Lines 37–40** output the segmented source image.
* **Line 44** loops over the detected faces in the destination image and, for each face detected, assigns an identifier to it. Then, its respective landmarks and the landmarks relative to the select face component are grabbed.
* **Lines 49–52** output a message showing the face identifier and its location.
Lines 54–55 invoke the function `swap_triangles`.
* **Lines 58–64** output the result.
The complete code of the function `swap_facial_component` is shown below:


# Introduction ##

This lesson provides the steps needed to develop a utility that swaps specific facial components. For the sake of this lesson, we’ll emphasize the mechanism of swapping an eye between two face images.

This utility will enable you to try out different eye colors since you can swap your eye color with a different one.  Afterwards, you’ll be able to see the difference between your current eye color and the new eye.


# Dependencies ##

We’ll be using the following external Python libraries.

# Let’s code the utility!

Let’s take a look at the main function of this utility.

## The `swap_facial_component` function

The core function of this utility aims to illustrate the steps taken to swap one facial component (the eye component) in a chosen facial image (the destination image) and another one that has already been selected as a template (the swap image). Let’s learn about this function:

* **Line 6** initializes DLib detector and landmarks predictor.
* **Lines 9–10** load the swap image (source image).
* **Line 13** loads the destination image.
* **Line 18** gathers the list of face components and their respective indexes. The `FACIAL_LANDMARKS_IDXS` dictionary inside `face_utils` in the `imutils` library returns the mapping of the main facial regions like the mouth (points 48 to 68), the left eye (points 42 to 48), and so on.
* **Line 22** loops over the detected faces in the source image and, for each face that is detected, assigns an identifier to it. Then, its respective landmarks and the landmarks relative to the selected face component are grabbed. For the purpose of this lesson, we selected the left eye as a face component.
* **Lines 27–31** output a message that shows the face identifier and its location.
* **Lines 34–35** segment the detected face component into triangles using the Delaunay triangulation technique and draw the triangles generated.
* **Lines 37–40** output the segmented source image.
* **Line 44** loops over the detected faces in the destination image and, for each face detected, assigns an identifier to it. Then, its respective landmarks and the landmarks relative to the select face component are grabbed.
* **Lines 49–52** output a message showing the face identifier and its location.
Lines 54–55 invoke the function `swap_triangles`.
* **Lines 58–64** output the result.
The complete code of the function `swap_facial_component` is shown below:


Learn how to swap the eyes between two face images.

Library	Version
`Dlib`	19.17.0
`opencv-python`	4.4.0.46
`imutils`	0.5.3
`filetype`	1.0.7

Introduction

Core Functions

Face Detection Using Dlib and DNN in OpenCV

Predictive Analytics

Manipulation Functions

Virtual Makeover Functions

Face Recognition

Conclusion

Appendices

Swap the Eyes

Introduction

Dependencies

Let’s code the utility!

The `swap_facial_component` function

Face Detection Using Dlib and DNN in OpenCV

Swap the Eyes

Introduction

Dependencies

Let’s code the utility!

The swap_facial_component function

The `swap_facial_component` function