Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 27

Siddharth Institute of Engineering and Technology

Department of Computer Science and Engineering


Academic Year 2020-21

Project Final Review

Project Title : A NOVEL METHOD OF FACE DETECTION AND RECOGNITION


USING OPENCV AND HAAR FEATURE BASED CASCADE
Batch Details :

Sno Reg No: Name Internal Guide


1. 17F61A05A7 D.ROHITH
DR.B.GEETHAVANI,ph.D,
2. 17F61A05A1 K.RAMYA SREE HOD & Professor
3. 17F61A05A8 P.RUPESH
4. 17F61A0599 N.RAJENDRA
OBJECTIVE
• A face recognition program is a script for verifying a person
and identifying him or her with a video or picture from a
source

• Face detection and picture or video recognition is a popular


subject of research on biometrics. Face recognition in a real-
time setting has an exciting area and a rapidly growing
challenge
OBJECTIVE

• It is generally compared to biometrics like fingerprints and


eye reconnaissance systems, and is used in security systems

• Here we built a camera-based real-time face recognition


system and set an algorithm by developing program on
OpenCV, Haar Cascade and Python.

• This project advanced capabilities such as facial detection,


face tracking, facial recognition and a range of ready-to-use
methods of artificial intelligence (AI).
ABSTRACT
• Face recognition, as one of the most successful applications of image analysis,
has recently gained significant attention. It is due to availability of feasible
technologies, including mobile solutions. 

• Research in automatic face recognition has been conducted since the 1960s, but
the problem is still largely unsolved. Last decade has provided significant
progress in this area owing to advances in face modelling and analysis
techniques.

• Although systems have been developed for face detection and tracking, reliable
face recognition still offers a great challenge to computer vision and pattern
recognition researchers.
ABSTRACT
• There are several reasons for recent increased interest in face
recognition, including rising public concern for security, the
need for identity verification in the digital world, face analysis
and modelling techniques in multimedia data management and
computer entertainment.
 
• In this project, we have implement face recognition processing,
including major components such as face detection and open
CV ,harr cascade . All of these major components points out the
technical challenges of building a face recognition system. 
Literature Survey

Sno Title of the Paper Year of publication Author Comments


1. A Face Recognition Approach 2020 Xuhang Lian This paper makes us
Based on Computer Vision understand the
application platform
of face recognition
based on Open CV
2. Face Detection and 2019 Gurlove singh, Learnt about image
Recognition System using Amitkumar goel processing and
Digital Image Processing cascading

3. Face Detection and 2018 Maliha Khan , Understood the


Recognition Using OpenCV Sudeshna comparison of
Chakraborty, different algorithms
Rani Astya , for facial recognition
Shaveta Khepra
Inferences from Literature
Survey
• How the concept of face recognition works.

• Internal concept of open cv

• what are the different types of methods existing to recognize


facial features.

• Techniques used to read data within an image from various


related methodologies.
System Architecture
System Architecture
Existing System
• The existing system presents an approach where artificial neural networks are
used to solve nonlinear problem. To recognise human faces, a non‐convergent
neural network is suggested. A radial basis function neural network integrated
with a non‐negative matrix factorisation to recognise faces is presented in 2016.

• Moreover, for face and speech verifications, utilise a momentum back


propagation neural network. Non‐negative sparse coding method to learning
facial features using different distance metrics and normalised cross‐correlation
for face recognition is applied .

• It has elements of both neural networks and statistical approaches and


replenishes methods for recognising face images with partial distortion and
occlusion.
Existing System

Disadvantages :
• Efficiency is less when compared to the latest
model.
• Difficult to evaluate the project.
• Unfortunately, this approach like other
statistical‐based methods, is inaccurate to
model classes given only a single or a small
number of training samples
Proposed Methodology
• For facial recognition so many different types of
methodologies are used but this open CV methodology is the
most recent and is generally preferred because of more
accuracy when compared to the previous methodologies

• OpenCV is the most popular library for computer vision.


Originally written in C/C++, it now provides bindings for
Python.

• To get around this, OpenCV uses cascades


Proposed Methodology
• First, a classifier (namely a cascade of boosted classifiers
working with haar-like features) is trained with a few hundred
sample views of a particular object (i.e., a face or a car), called
positive examples, that are scaled to the same size (say,
20x20), and negative examples - arbitrary images of the same
size.

• The current algorithm uses the following Haar-like features:

• Haar-like features are the input to the basic classifiers, and are
calculated as described below
Proposed Methodology
Modules Descriptions
Open CV : This project was done with this fantastic “Open Source
Computer Vision Library”, the OpenCV. OpenCV is a cross-
platform library using which we can develop real-time computer
vision applications.
It mainly focuses on image processing, video capture and
analysis including features like face detection and object
detection.
• Computer Vision overlaps significantly with the following fields
• Image Processing − It focuses on image manipulation.
• Pattern Recognition − It explains various techniques to
classify patterns.
• Photogrammetry − It is concerned with obtaining accurate
measurements from images.
Modules Descriptions
• Numpy : NumPy is a library for the Python programming language,
adding support for large, multi-dimensional arrays and matrices,
along with a large collection of high-level mathematical functions
to operate on these arrays

• Haar classifier :A Haar classifier, or a Haar cascade classifier, is a


machine learning object detection program that identifies objects
in an image and video.

• Haar Cascade classifiers are an effective way for object detection.


Modules Descriptions
• This method was proposed by Paul Viola and Michael Jones in their
paper 
Rapid Object Detection using a Boosted Cascade of Simple Feature
s
 .

• Haar Cascade is a machine learning-based approach where a lot of


positive and negative images are used to train the classifier.

• Positive images – These images contain the images which we want


our classifier to identify.
• Negative Images – Images of everything else, which do not contain
the object we want to detect.
Modules Descriptions
Modules Descriptions
Modules Descriptions
Modules Descriptions
Modules Descriptions
Requirement specification
Software Requirements :
Python latest version (3.8),
Pycharm (recommended),
Numpy and Open CV version 2.7 ,
Windows operating system 7,8,10 (32 bit or 64 bit)
Hardware Requirements :
Processor - any Processor
camera - required
RAM - 2GB (min)
Hard Disk - 100GB(min)
Key Board - Standard Windows Keyboard
Mouse - required
Monitor - required
Conclusion
• In the last 20 years, facial recognition technology has come a
long way. Today we can check identity information
automatically with regard to safe transactions, tracking,
security purposes and buildings access control.

• Such systems normally work in controlled environments and


algorithms of recognition may manipulate environmental
constraints to achieve high accuracy of recognition. Yet face-
recognition technologies of next generation will be commonly
used in smart settings where computers and machines are
most likely supportive helpers.
References
•1] Learning OpenCV –Computer Vision with the OpenCV Library O’Reilly Publication. [2]
Learning OpenCV: Computer Vision with OpenCV Library, Kindle Edition.Gary Bradsk1 and
AndrianKehlar
•[3] M.A. Turk and A.P. Pentland, “Face Recognition Using Eigenfaces”, IEEE Conf. on
Computer Vision and Pattern Recognition, pp. 586-591, 1991.
•[4] “KyungnamKim” Face Recognition using Principle Component Analysis”
•[5] Codacus: https://youtu.be/1Jz24sVsLE4
•[6] G B Huang, H Lee, E L. Miller, “Learning hierarchical representation for Face
verification with convolution deep belief networks[C]”,Proceedings of International
Conference on Computer Vision and Pattern Recognition,pp.223-226,2012.
•[7] Computer Vision Papers, http://www.cvpapers.com
•[8] Learning OpenCV: Computer Vision with the OpenCV Library 1st Edition, Kindle Edition
•[9] OpenCV Homepage http://opencv.willowgarage.com
•[10] Recognition Homepage http://www.face-rec.org/algorithms.
•[11] Paul Viola, Matthew Jones Conference paper- IEEE Computer Society Conference on
Computer Vision and Pattern Recognition.“Rapid object detection using a boosted cascade
of simple features.
Queries ?
Thank you

You might also like