See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/323390774

Face detection and Recognition: A review

Conference Paper · February 2018

CITATIONS READS
0 3,394

3 authors, including:

Harjeet Singh
Punjab Technical University
30 PUBLICATIONS   19 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

M.Tech Research View project

PhD Research View project

All content following this page was uploaded by Harjeet Singh on 07 March 2018.

The user has requested enhancement of the downloaded file.

ISBN No. 978-81-924893-3-9 6th International Conference on Advancements in Engineering & Technology (ICAET-2018), Feb. 23-24, 2018, Sangrur

Face detection and Recognition: A review

Akanksha Jashanpreet Kaur Harjeet Singh
Student, B.Tech (ECE) Student, B.Tech (ECE) Assistant Prof., ECE
BHSBIET,Lehragaga BHSBIET,Lehragaga BHSBIET,Lehragaga

Abstract holistic approach. In this approach both local and whole

face is used as the input to
Face Detection is one of the type of biometric technique face detection system.
which refers to the detection of face automatically by In this paper, implementation of the face recognition
computerized systems by taking a look at face. It is a algorithm to detect and recognize faces accurately is on the
popular feature used in biometrics, digital cameras and MATLAB.
social tagging. Face detection and recognition has gained
more research attentions in last few years. In this paper we Face detection
studied different approach of face detection and implement The problem of face recognition is all about face detection.
it on the MATLAB software. Face detection is further classified as face detection in
images and real-time face detection. In this project we will
Keywords: Face Detection, Face Recognition, Biometrics, attempt to detect faces in still images by using image
Face Identification. invariants. To do this it would be useful to study the grey-
scale intensity distribution of an average human face. The
Introduction following 'average human face was constructed from a
sample of human faces. A suitably scaled color map has
Face detection and recognition becomes the most been used to highlight grayscale intensity differences.
biometrics authentication techniques from the past few The grey-scale differences, which are invariant across all
years. Face recognition is the process of using the face the sample faces are strikingly apparent. The eye-eyebrow
properties in the biometric systems. Face recognition area seem to always contain dark intensity (low) gray-
system has two main tasks: verification and identification. levels while nose forehead and cheeks contain bright
Face identification means a 1:N problem that compares a intensity (high) grey levels. After a great deal of
query face image against all image templates in a face experimentation, the researcher found that the following
database. We perform face recognition, an extremely areas of the human face were suitable for a face detection
complex visual task, almost instantaneously and our own system based on image invariants and a deformable
recognition ability is far more robust than any computer's template.
can hope to be. We can recognize a familiar individual
under very adverse lighting conditions, from varying angles
or view points. 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 past. 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. Theinput 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. Figure 1: Scaler Colourmap
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 easier the
task of face recognition.
 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
138
ISBN No. 978-81-924893-3-9 6th International Conference on Advancements in Engineering & Technology (ICAET-2018), Feb. 23-24, 2018, Sangrur

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 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 Figure 4: Whole face, eyes, nose and mouth regions which
It involves computation of a set of geometrical features could be used in a template matching strategy.
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 Algorithm for face Recognition
features of known individuals. A suitable metric such as Adding the image to the database
Euclidean distance (finding the closest vector) can be used 1. Get the image.
to find the closest match. 2. Get the FaceDetector object.
The advantage of using geometrical features as a basis for 3. Apply the FaceDetector object to the image to
face recognition is that recognition is possible even at very extract the features of detectedface.
low resolutions and with noisy images (images with many 4. Add the image to the database.
disorderly pixel intensities). Although the face cannot be
viewed in detail Comparing the input image with the database of images
its overall geometrical configuration can be extracted for 1. Get the image.
face recognition. The technique's main disadvantage is that 2. Get the FaceDetector object.
automated extraction of the facial geometrical features is 3. Apply the FaceDetector object to image and
very hard. 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.

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

for face recognition

139
ISBN No. 978-81-924893-3-9 6th International Conference on Advancements in Engineering & Technology (ICAET-2018), Feb. 23-24, 2018, Sangrur

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
2. Then we tested for two images, one of same Pearson Education Society.
person and one of different and the results were 2. 2. Digital Image Processing - by Keenneth R.
Castleman, Pearson Education Society.
3. 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.cascad
eobjectdetector 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
The image of same person is recognized correctly Pattern Analysis and Machine Intelligence,
and class is detected. 15(10):1042-1052
9. https://in.mathworks.com
3. For second test face, the results are 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.

For this image, it shows that the person is not registered in

the database.

140

View publication stats