Improving Office Security via Face Recognition
Volumn 4

Improving Office Security via Face Recognition

Mr. Nitin Thakre#1 ,  Mrs. Rupali Fulse*2 ,  Mrs. Bharati Raut#3

123Assistant Professor , Information Technology,

RTMNU, India.

1nitinthakre3400@gmail.com

2 pathatkarrupali@gmail.com

3 kamdebharati@rediffmail.com

Abstract—

This Automatic face recognition of people has become a challenging task now a days and is getting implemented in various fields due to its crucial application in different fields. A facial recognition system is a computer application for automatically identifying authorities a person from a digital image. Every day action or increasingly being handle electrically instead of a pen and paper or face to face. The technique uses an image based  approach towards uses face recognition technique for verification in office system. In this technique we can capture the image of the office entering person by using web cam, if the capturing image matches with our database  then person is authorized person otherwise the person will be unauthorized. The system will directly send the  capture image to the predefined email with a message  alert  to the cell phone.

Keywords—Bio-metric, face recognition, web cam,  face identification.

I. Introduction

    Face recognition or identification system is evolving as an attractive solution to address many needs for authentication of identity claims. This system merges together two systems; the biometric systems, which attempt to tie identity to individually distinctive features of the body; the shape, reflectance, pose, occlusion and illumination, and the more familiar functionality of visual surveillance systems. The contemporary biometric identification technology aims at strengthening the links between attributed and biographical identity and create a stable, accurate, and reliable identity group. It is surely difficult for individuals to falsify attributed and biographical identifiers, biometric identifiers such as an individual’s fingerprints, palm prints, irises, face, all are conceivably more secure because it is assumed that “the body never lies” or differently stated, that it is very difficult or impossible to falsify biometric characteristics. Remain rooted to this principle, many important challenges of a practical nature which are having utmost importance as far as security is concerned have been faced and solved using the powerful system of face recognition wherein it focuses on deciding on which bodily features to use, how to convert these features into usable representations, and, beyond these, how to store, retrieve, process, and govern the distribution of these representations.

Prior to recent advances in the information sciences and technologies, the practical challenges of biometric identification had been difficult to meet. For example, passport photographs are amenable to tampering and hence not reliable; fingerprints, though more reliable than photographs, were not amenable, as they are today, to automated processing and efficient dissemination. Security as well as other concerns has turned attention and resources toward the development of automatic biometric systems. An automated biometric system is essentially a pattern recognition system that operates by acquiring biometric data (a face image) from an individual, extracting certain features (defined as mathematical artifacts) from the acquired data, and comparing this feature set against the biometric template (or representation) of features already acquired in a database as shown in fig 2 and fig 3. Fig 1 [1] addresses the face recognition problem among the thousands or lakhs of images available.

Fig 1. Face recognition problem
Fig 2. Face recognition
Fig 3. Face authentication or verification

I.I Fundamentals of Digital Image Processing

Modern digital technology has made it possible to process multi-dimensional signals with systems that range from simple digital circuits to advanced parallel computers. The goal of this processing can be divided into three categories:

  • Image Processing: Image in image out, Example: Gamma Correction.
  • Image Analysis: Image in measurements out, Example:Histogram.
  • Image Understanding: Image in high-level description out.

Example: Detecting the number of faces in an image.

The following figure (Fig 4) shows the typical working of a face recognition system.

Fig 4. The working of a typical face recognition system.

II. Related work

In [1], Face and biometric Based Attendance and Security System using RFID and Arduino has been implemented For the implementation purpose we are using languages such as C, C++ along with python Whenever the employee enters the campus, he is required to swipe his/her issued Employee ID card from the company. The camera has to be placed near the entrance. When the employee swipes ID card number and ID number does not matches with the database then a voice based alert is issued through speaker & security is alerted. The warning alert message is also displayed on display devices. When the employee swipes ID card number and ID number matches with the database then his face photo captured from the camera is checked for face recognition or face matching with the already existing face photo of the employee from the company database. If the face matches with that present in the database then face matched message is displayed on screen and the employee is asked to enter his left hand thumb impression on finger print sensor. Once the finger print matches with that present in the database which has been tagged to the particular employee ID number then an audio based voice welcome greetings is played and also welcome message displayed on the display device. We should note that 85 finger print of valid employee trying to give attendance to his colleagues Employee ID will also trigger alarm as the finger print is tested first for valid finger print from the database & if found then its specifically tested for the tagged ID. Thus if employee tries to give proxy then also he gets caught. Its hardware implementation is Whenever an employee enters into the campus, near entry gate camera, display will ask for RFID tags (ID card) to be displayed or swiped on RFID reader. Once swiped his ID card number & other details are fetched from Arduino into PC database. From PC database his existing uploaded photo of the face is matched with his live face photo detected from the live video using web camera. Once it is established that the face matches with the one existing in database then employee will be allowed into the campus by opening entry gate. Then in the main gate he will be asked to authenticate his finger print. Once left hand thumb finger print also matches then Voice greeting heard via speaker which will welcome the employee. Employee attendance will be marked with entry time & date details.

Viola and Jones devised [6] an algorithm, called Haar Classifiers, to rapidly detect any object, including human faces, using Adaboost [2] classifier cascades that are based on Haar-like features and not pixels [4]. Open CV uses Viola Jones method published in 2001, to detect faces using 4 key concepts

  • Simple rectangular features called haar features
  • An integral image for rapid face detection
  • The adaboost machine learing method
  • A cascaded classifier to combine many classifiers efficiently [5].

III. Conclusion

In these modern times, office  security is the need of the hour for the development of market as a whole which in turn will help make our cities industries, so the concept of facial recognition to gain access of the office is an idea which is used to make our working area more secure. A facial recognition system is a system which captures facial images and verifies the a person using a store database. The human face assumes an essential part in our social association, passing on individuals’ character. Utilizing the human face as a key to security. Today, machines are able to automatically verify identity information for secure transactions, for surveillance and security tasks, and for access control to buildings. These applications usually work in controlled environments and recognition algorithms that can take advantage of the environmental constraints to obtain high recognition accuracy. However, next generation face recognition systems are going to have widespread application in smart environments, where computers and machines are more like helpful assistants. A major factor of that evolution is the use of neural networks in face recognition. A different filed of science that also is very fast becoming more and more efficient, popular and helpful to other applications.

REFERENCES

  1. https://www.iti.gr/iti/files/document/seminars/FR2.pdf
  2. Saleem Ulla Shariff, “Face and Bio-Metric Based Attendance and Security System using RFID and Arduino”, International Journal of Electrical Electronics & Computer Science Engineering Special Issue – NEWS 2016 | E-ISSN : 2348-2273 | P-ISSN : 2454-1222
  3. P. Viola and Michael J. Jones. “Robust real-time face detection”, International Journal of Computer Vision, 57(2):137-154, 2004.
  4. “Facial feature detection using haar classifiers” Phillip Ian Wilson Dr. John Fernandez Texas A&M University – Corpus Christi 6300 Ocean Dr. CI334, Corpus Christi, TX 78412 361-825-3622.
  5. http://www.cognotics.com/opencv/servo_2007_series/part_2/sidebar.html
  6. Prathamesh Timse **, Pranav Aggarwal ** , Prakhar Sinha ** ,Neel Vora **, “Face Recognition Based Door Lock System Using Opencv and C# with Remote Access and Security Features”, Int. Journal of Engineering Research and Applications ISSN : 2248-9622, Vol. 4, Issue 4( Version 6), April 2014, pp.52-57

Related posts

A Review on Algorithmic design for Eye & Face Recognition for Various Complaint using Matlab

admin

A Comparative Study of LEACH Protocol for Wireless Sensor Network

admin

Challenges & Opportunities for Automobile Vehicles in Smart Cities in India

admin

Leave a Comment