Real Time Face Detection Systems

1

Hi all !!

Have you guys every used any of these image filters before? Maybe snapchat, maybe facebook messenger? And many moreBut have you ever wondered how they work that too so fast and efficient?

Real Time Face Detection Systems Using Viola Johns Algorithm-Sreerag SreenathSec AFinal Year B.Tech ECEJanuary 24 , 2017

Good evening Sir and my dear friends Today I will be taking the seminar of the topic Real time Face detection systems, My name is Sreerag Sreenath, Final year Btech bearing the roll number 134153So first lets get to the basics.

Face Detection3Basic idea: slide a window across image and evaluate a face model at every location of a given image

Tell how is it different from face recognition

OverviewRobust very high Detection Rate (True-Positive Rate) & very low False-Positive Rate always.Real Time For practical applications at least 2 frames per second must be processed.Face Detection not recognition. The goal is to distinguish faces from non-faces (face detection is the first step in the identification process)

4

So how does the algo work?5

Problems..?How to define a feature?-- Edge Detection to Haar featuresHow to calculate area fast?-- Integral Image6

Steps in Voila Jones Face Detection Algorithm7

Basic Introduction to edge detectionOutput image(right) has high intensity at pixels where the convolution kernel pixel pattern matched perfectly with the input image8

Haar Features9

Haar features are similar to these convolution kernels which are used to detect the presence of that feature in the given image.Each feature results in a single value which is calculated by subtracting the sum of pixels under white rectangle from the sum of pixels under black

Haar Features10

Viola Jones algorithm uses a 24x24 window as the base window size to start evaluating these features in any given image.If we consider all the possible parameters of the haars features like position, scale and type we will end up calculating about 160,000+ features in this window.

Integral Window11

In an integral image the value at pixel(x,y) is the sum of pixels above and to the left of (x,y)Integral image allows for the calculation of sum of all pixels inside any given rectangle using only four values at the Conner of the rectangle.

Adaboost12

As stated previously there can be 160,000+ feature values within a detector at 24x24 base resolution which needs to be calculated. But it is to be understood that only few set of features will be useful among all these features to identify a face .

Adaboost13

As Adaboost is a machine learning algorithm which helps in finding the best among all these 160,000+ features. After these features are found, a weighted combination of all these features in used in evaluating and deciding any given window or not. Their accuracy can also be low more than 50 percent (better than random guessing) These best features are called as weak classifiers. Adaboost constructs a strong classifier as a linear combination of these weak classifiers

Cascading14

The basic principle of the Viola-Jones face detection algorithm is to scan the detector many times through the same image each time with a new size.Even if an image should contain one or more faces it is obvious that an excessive large amount of the evaluated sub-window would still be negatives (non-faces).So the algorithm should concentrate on discarding non-faces quickly and spend more time on the probable face regionsHence a single strong classifier formed out of linear combination of all best features is not a good to evaluate on each window because of computational cost

Cascading15

Therefore a cascade classifiers is used which is composed of stages each containing a strong classifiers. So all the features are grouped into several stages where each stage has certain number of features.The job of each stage is used to determine wheatear a given sub-window is defiantly not a face or may be a face. A given sub window is immediately discarded as not a face if it fails in any of the stage

Image Classification Process Video16

Now the training to an XML file17

Haars Cascade File18

Face Detection Test19

Sample detected Images20

Further Improved Algorithms21

There have been a lot of research and development in object detection algorithms since then.Feature Point detection, Bag-of-Words models,Histogram-of-oriented gradients (HOG), Deformable Parts Models,Exemplar models,etc. are some modern techniques that have been used to great success.Deep learning(convolutional neural networks) is the absolute state-of-the-art technique for object detection and has produced great strides in the field.There are a lot of great papers and cutting-edge research. For example, consider Facebook'sDeepFaceface recognition algorithm, DeepFace had produced a face recognition accuracy of 97.35% on the Labelled Faces in the Wild dataset, which is quite near human-level performance (97.53%)! So yes, modern and state-of-the-art algorithms hold a lot of promise.

Thank You22