Face Detection and Recognition - A Review

Face Detection and Recognition: A review
Harjeet Singh, Assistant Prof., (ECE) BHSBIET,Lehragaga

Akanksha, Student, B.Tech (ECE) BHSBIET,Lehragaga
Jashanpreet Kaur, Student, B.Tech (ECE) BHSBIET,Lehragaga
Abstract
Face Detection is one of the types of biometric technique which refers to the detection of face
automatically by computerized systems by taking a look at face. It is a popular feature used in
biometrics, digital cameras and social tagging. Face detection and recognition has gained more
research attentions in last few years. In this paper we studied different approach of face
detection and implement it on the MATLAB software.
Keywords: Face Detection, Face Recognition, Biometrics, Face Identification.
Introduction
Face detection and recognition becomes the most biometrics authentication techniques from
the past few years. Face recognition is the process of using the face properties in the biometric
systems. Face recognition system has two main tasks: verification and identification. Face
identification means a 1:N problem that compares a query face image against all image
templates in a face database. We perform face recognition, an extremely complex visual task,
almost instantaneously and our own recognition ability is far more robust than any computers
can hope to be. We can recognize a familiar individual under very adverse lighting conditions,
from varying angles or viewpoints. Scaling differences (a face being near or far away), different
backgrounds do not affect our ability to recognize faces and we can even recognize individuals
with just a fraction of their face visible or even after several years have passed. Furthermore,
we are able to recognize the faces of several thousand individuals whom we have met during
our lifetime. In the Face recognition process, the input image is compared with the database.
The input image is also called as probe and the database is called as gallery. Then it gives a
match report and then the classification is done to identify the sub-population to which new
observations belong.
There are basically three approaches for face recognition:
 Feature base approach: In feature-based approach the local features like nose, eyes are
segmented and it can be used as input data in face detection to make the task of face
recognition easier.
 Holistic approach: In holistic approach the whole face taken as the input in the face
detection system to perform face recognition.
 Hybrid approach: Hybrid approach is combination of feature based and holistic
approach. In this approach both local and whole face is used as the input to face
detection system.
In this paper, implementation of the face recognition algorithm to detect and recognize faces
accurately is on the MATLAB.
Face detection
The problem of face recognition is all about face detection. Face detection is further
classified as face detection in images and real-time face detection. In this project we will
attempt to detect faces in still images by using image invariants. To do this it would be useful to
study the greyscale intensity distribution of an average human face. The following average
human face was constructed from a sample of human faces. A suitably scaled color map has
been used to highlight grayscale intensity differences.
The grey-scale differences, which are invariant across all the sample faces are strikingly
apparent. The eye-eyebrow area seems to always contain dark intensity (low) gray levels while
nose forehead and cheeks contain bright intensity (high) grey levels. After a great deal of
experimentation, the researcher found that the following areas of the human face were
suitable for a face detection system based on image invariants and a deformable template.
Figure 1: Scalar Colourmap
Figure 2: Scaled colourmap (negative)
The above facial area performs well as a basis for a face template, probably because of
the clear divisions of the bright intensity invariant area by the dark intensity invariant regions.
Once this pixel area is located by the face detection system, any particular area required can be
segmented based on the proportions of the average human face.
Face recognition
Human face recognition can be divided into two strategies: geometrical features and template
matching.
a) Face recognition using geometrical features

It involves computation of a set of geometrical features such as nose width and length,
mouth position and chin shape, etc. from the picture of the face we want to recognize. This set
of features is then matched with the features of known individuals. A suitable metric such as
Euclidean distance (finding the closest vector) can be used to find the closest match.
The advantage of using geometrical features as a basis for face recognition is that
recognition is possible even at very low resolutions and with noisy images (images with many
disorderly pixel intensities). Although the face cannot be viewed in detail its overall geometrical
configuration can be extracted for face recognition. The technique's main disadvantage is that
automated extraction of the facial geometrical features is very hard.
Figure 3: Geometrical features (white) which could be used

for face recognition.
b) Face recognition using template matching

This is similar the template matching technique used in face detection, except here we
are not trying to classify an image as a 'face' or 'non-face' but are trying to recognize a face. The
basis of the template matching strategy is to extract whole facial regions (matrix of pixels) and
compare these with the stored images of known individuals. Once again Euclidean distance can
be used to find the closest match.
Figure 4: Whole face, eyes, nose and mouth regions which

could be used in a template matching strategy.
Algorithm for face Recognition

Adding the image to the database
1. Get the image.
2. Get the FaceDetector object.
3. Apply the FaceDetector object to the image to extract the features of detected face.
4. Add the image to the database.
Comparing the input image with the database of images
1. Get the image.
2. Get the FaceDetector object.
3. Apply the FaceDetector object to image and extract the features.
4. Compare the image with the database.
RESULTS
Two images are used for testing and the results are as follows.
1. Firstly, we added the image to the database.
2. Then we tested for two images, one of same person and one of different and the results
were the image of same person is recognized correctly and class is detected.
3. For second test face, the results are:
For this image, it shows that the person is not registered in the database.
Conclusion
The facial expression recognition system contributes a resilient face recognition model based
on the mapping of behavioral characteristics with the physiological biometric characteristics.
The physiological characteristics of the human face with relevance to various expressions such
as happiness, sadness, fear, anger, surprise and disgust are associated with geometrical
structures which restored as base matching template for the recognition system. Experimental
analysis and study show that the hierarchical security structures are effective in geometric
shape identification for physiological traits.
References
1. Digital Image Processing using MATLAB - by Rafael C. Gonzalez, Richard E. Woods and Steven
L. Eddins Pearson Education Society.
2. Digital Image Processing - by Keenneth R. Castleman, Pearson Education Society.
3. Riddhi Patel, Shruti B. Yagnik (Nov 2013) : A Literature Survey on Face Recognition
Techniques
(IJCTT) – volume 5 number 4.
4. Raunil Singh Kiran Gupta (april 2015) : Face Detection and Recognition – A Review, SSRG-
IJCSE.
5. Vision.CascadeObjectDetector system
https://in.mathworks.com/help/vision/ref/vision.cascadeobjectdetector systemobject.html
6. Viola – Jones object detection framework.
https://en.wikipedia.org/wiki/Viola–Jones_object_detection_framework.
7. Beymer, D. and Poggio, T. (1995) Face Recognition From One Example View, A.I. Memo No.
1536, C.B.C.L. Paper No. 121. MIT.
8. Brunelli, R. and Poggio, T. (1993), Face Recognition: Features versus Templates. IEEE
Transactions on Pattern Analysis and Machine Intelligence, 15(10):1042-1052
9. https://in.mathworks.com
10. Saber, E. and Tekalp, A., (1996). Face Detection and Facial Feature Extraction Using Color,
Shape and Symmetry Based Cost Functions, International Conference on Pattern Recognition.

Face Detection and Recognition - A Review

Uploaded by

Copyright:

Available Formats

Face Detection and Recognition - A Review

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Face Detection and Recognition - A Review

Uploaded by

Copyright:

Available Formats

Face Detection and Recognition: A review

Harjeet Singh, Assistant Prof., (ECE) BHSBIET,Lehragaga

Keywords: Face Detection, Face Recognition, Biometrics, Face Identification.

Figure 2: Scaled colourmap (negative)

a) Face recognition using geometrical features

Figure 3: Geometrical features (white) which could be used

b) Face recognition using template matching

Figure 4: Whole face, eyes, nose and mouth regions which

Algorithm for face Recognition

You might also like