Professional Documents
Culture Documents
Maurya Banda
(CE11B009)
(CE11B027)
N.B.Ravi Teja
(CE11B079)
Table of Contents
1 AIM....................................................................................................................................................................................... 3
2 INTRODUCTION ................................................................................................................................................................... 3
2.1 What is Face recognition system? .......................................................................................................................... 3
2.2 What is its significance? .................................................................................................................................. 3
2.3 What are the different applications with regard to security? .3
2.4 What are the disadvantages? 4
2.5 How does the FR Software work? 5
2.6 What happens inside the FRM? 7
3 WORKING MECHANISM ...................................................................................................................................................... 8
3.1 Door opening and closing ....................................................................................................................................... 8
3.2 Lighting System ........................................................................................................................................................ 9
3.3 BACNET Network....9
4 COMPONENTS REQUIRED ...10
5 SPECIFICATIONS OF AVAILABLE COMPONENTS 10
5.1 FRM Specifications.....10
5.2 Occupancy Sensor ...10
5.3Electric Bell 11
5.4 Electromagnetic Lock ...11
5.5 TCP/IP ..11
6 ALGORITHMS FOR VARIOUS CONNECTIONS ..11
6.1 Occupancy Sensor for lighting system ..11
6.2 FRM to EM lock: ( Communication : Analog)
6.3 FRM to Electric Bell 12
6.4 PC to HUB .12
6.5 FRM to PC ....12
6.6 Occupancy sensor to FRM ..12
6.7 Exit Button to FRM(Communication: Binary).12
6.8 Automated Attendance System .12
7 COST ANALYSIS OF COMPONENTS USED...12
7.1 Cost Estimation .... 12
7.2 Links for Costs ..12
8 REFERENCES...............14
2. Introduction
2.1. What is Face recognition system?
A facial recognition system is a computer application automatically identifying or verifying a person from
a digital image or a video frame from a video source. One of the ways to do this is by comparing selected facial
features from the image and a facial database. It is typically used in security systems and can be compared to
other biometrics such as fingerprint or eye iris recognition systems.
banks, social welfare and security, electronic commerce and security and defence fields. Various uses of face
recognition system in doors is discussed here.
Domestic Use
Face recognition system can be used as a security system for houses and residential buildings.
Specifically when a person tries to access the door it either allows the person through the door if the person is
an authorized user or it specifies the owner of the house regarding the use of the door by any anonymous
person. In some cases when the user tries to access the door by forcible means it activates an alarm so that the
neighbours or the security of house can respond.
Offices
Face recognition system has many uses in offices.
It can be used for saving important files and documents which can be used only by a specified personal.
It can be used for allowing only the staff and other people who were pre-specified in the database of the
face recognition system.
It can act as an automated security system during free hours of the office usually when the office is
vacant.
Banks
The main use of face recognition system in banks is to have protected lockers for saving money and
important documents of properties.
Military
Military of many nations use face recognition system as an additional security system for the access of
highly valuable, precarious, dangerous and sophisticated weapons and armaments. These systems not only
improve the security of individual buildings but also increases the security of the state and country as a whole.
to secretly collect the identities and associated personal information of any individual captured by the facial
recognition system.
Whatever might the propensity of disadvantages be in other fields, the face recognition system in the
security applications has been found very instrumental in automating the security operations in various walks of
industrial and domestic fields.
You can use the cascade object detector to track a face across successive video frames. However, when
the face tilts or the person turns their head, you may lose tracking. This limitation is due to the type of trained
classification model used for detection. To avoid this issue, and because performing face detection for every
video frame is computationally intensive, this example uses a simple facial feature for tracking.
Step 2: Identify Facial Features To Track
Once the face is located in the video, the next step is to identify a feature that will help you track the face. For
example, you can use the shape, texture, or color. Choose a feature that is unique to the object and remains
invariant even when the object moves.
In this example, you use skin tone as the feature to track. The skin tone provides a good deal of contrast
between the face and the background and does not change as the face rotates or moves.
% Get the skin tone information by extracting the Hue from the video frame
% converted to the HSV color space.
[hueChannel,~,~] = rgb2hsv(videoFrame);
% Display the Hue Channel data and draw the bounding box around the face.
figure, imshow(hueChannel), title('Hue channel data');
rectangle('Position',bbox(1,:),'LineWidth',2,'EdgeColor',[1 1 0])
nose within the face region. The nose provides a more accurate
the skin tone because it does not contain any background
= vision.CascadeObjectDetector('Nose');
= imcrop(videoFrame,bbox(1,:));
= step(noseDetector,faceImage);
% The nose bounding box is defined relative to the cropped face image.
% Adjust the nose bounding box so that it is relative to the original video
% frame.
noseBBox(1,1:2) = noseBBox(1,1:2) + bbox(1,1:2);
% Create a tracker object.
tracker = vision.HistogramBasedTracker;
% Initialize the tracker histogram using the Hue channel pixels from the
% nose.
initializeObject(tracker, hueChannel, noseBBox(1,:));
% Create a video player object for displaying video frames.
videoInfo
= info(videoFileReader);
videoPlayer = vision.VideoPlayer('Position',[300 300 videoInfo.VideoSize+30]);
% Track the face over successive video frames until the video is finished.
while ~isDone(videoFileReader)
% Extract the next video frame
videoFrame = step(videoFileReader);
% RGB -> HSV
[hueChannel,~,~] = rgb2hsv(videoFrame);
2.6.
The FRM used in the present installation works on Viola Jones Face Detection Algorithm for which the
steps are discussed at length along with the code in the previous section. The hardware part of the FRM works
in the following mechanism. The functions of all the components that constitute the FRM are clearly mentioned
in the flowchart. Many commercially available machines follow a similar process. One such machine we
referenced for learning the mechanism is HF-FR701 which is a product by Chongquing Huifan Technology Co.,
Ltd.
3. Working Mechanism
Lighting System
Negative ID
Lock
Sensor
DOOR
Bell
USB
Key
Exit
Face Recognition
System
RS 230/485
PC
Attendance
TCP/IP
HUB
3.1.
8. If the persons face ID matches with the authorized, the FRM sends a binary signal to the
Electromagnetic lock and it opens.
9. If the persons face ID does not match with the authorized, the FRM sends a binary signal to the
security alarm and the security personnel of the building is cautioned.
10. After a person has moved in, the occupancy sensor sends a binary signal to the FRM and the
Electromagnetic Lock is actuated and the door is locked.
11. If the person wants to exit from the room, he presses the EXIT button which is wall mounted.
12. When the EXIT button is pressed a binary voltage signal is sent to the FRM, the Electromagnetic
Lock is actuated and the door opens.
13. After the person has moved out, the occupancy sensor again sends a binary signal to the FRM, and
the Electromagnetic Lock is actuated and the door is locked.
3.2.
Lighting System
The Face Recognition mechanism can be used for controlling the lighting inside the room and hence
it can help in energy saving.
1. When an authorized face ID is recognized, the occupancy of the room is increased by one.
2. Similarly when a person presses the EXIT button, the occupancy of the room is deducted by one
3. So whenever the occupancy of the room is zero, the FRM sends a binary signal to the lighting
system and the lights are turned off.
3.3.
BACNET Network
In a commercial building there can be multiple installations of the face recognition system.
The BACNET network is used for connecting all the routers, controllers , sensors and actuators to
a common HUB.
Each PC (Router)has a unique IP address
The FRMs(Controllers) have a unique Net ID
The sensors have a unique Instance ID
Router
FRM
Occupancy
sensor
HUB
Router
EM Lock
FRM
Door Bell
FRM
Occupancy
sensor
EM Lock
FRM
Door Bell
4. Components required:
Logs Capacity
Backup Battery
Communication
Access Control Interfaces
100,000
2000mAh
TCP/IP, RS232/485
3rd party electric lock, door sensor, alarm, wired bell and exit button
Power Supply
Verification Speed
Operating temperature
Operating Humidity
12V/3A
2 Seconds
0C-45C
20%-80%
5.5. TCP/IP
TCP/IP communication mode is used between the hub and the computer that checks the ID
created by the FR 701 and sees if it matches with the pre-existing database of IDs. TCP/IP provides end-to-end
connectivity specifying how data should be formatted, addressed, transmitted, routed and received at the
destination. This utilizes Cat5 cables.
6.2.
Initialize occupancy =0
If Sensor = 1 => occupancy=occupancy+1
If Exit= 1 =>occupancy= occupancy -1 (When the exit switch is pressed from inside the room)
If (occupancy >1 ) Turn on the lights else Turn off the lights
6.3.
6.4. PC to HUB
1.
2.
3.
4.
6.5. FRM to PC
1. The Controller generates a digital output of the face id
2. These signals are transmitted via RS 232 cables
3. As the PC uses RS 485 input, a RS232/485 converter is used to convert the RS232 signals to RS
485
(A PC can use both RS 232 and RS 485 communication but RS 485 communication is preferred
as many controllers can be connected to the PC)
FRM (Exit=1)
2. The FRM recognizes the signal and actuates the Electromagnetic Lock
3. And also the occupancy measure of the room is reduced by 1 (Occupancy=Occupancy-1)
This system can be used for a board room or a meeting room to maintain a directory for the
attendance
1. The FRM recognizes the face and generates the face id.
ESTIMATED COST
Rs 280/-
Electromagnetic Lock
Rs 1950/-
HF-FR701
Rs 18600/-
Rs 3000/-
Rs 200/-
Rs 250/-
Electric Bell
Rs 250/-
Total
Rs 26080/-
Allowance (appx)
Rs 1000/-
Rs 27080/-
Rs 60/Rs 1500/-
http://www.ebay.com/bhp/usb-to-rs485-adapter
Electromagnetic Lock
http://www.ebay.com/sch/i.html?_trksid=p2053587.m570.l1313.TR0.TRC0.H0.XElectromagnetic+Lock+&_nkw=
Electromagnetic+Lock+&_sacat=0&_from=R40
http://www.alibaba.com/trade/search?fsb=y&IndexArea=product_en&CatId=&SearchText=hf-fr701
http://sigma-shop.com/product/129/uart-8-channel-relay-controller-with-clips-for-din-mount-rail-12vdc.html
http://www.ebay.com/sch/i.html?_odkw=USB+2.0+to+RS232+Serial+DB9+Pin+Male+Adapter+SKU%23622&_os
acat=0&_from=R40&_trksid=p2045573.m570.l1313.TR0.TRC0.H0.XUSB+2.0+to+RS232+Serial+DB9+Pin+Adapte
r+SKU%23622&_nkw=USB+2.0+to+RS232+Serial+DB9+Pin+Adapter+SKU%23622&_sacat=0
http://www.ebay.com/sch/i.html?_odkw=USB+2.0+to+RS232+Serial+DB9+Pin+Adapter+SKU%23622&_osacat=
0&_from=R40&_trksid=p2045573.m570.l1313.TR0.TRC0.H0.XRS232+to+RS485+Adapter+Converter+Card+acce
ss+control+Systems+&_nkw=RS232+to+RS485+Adapter+Converter+Card+access+control+Systems+&_sacat=0
200ft feet RS485 Signal Transmission Cable for Control CCTV PTZ Security camera
http://www.ebay.com/sch/i.html?_odkw=CAT+5+NETWORKING+LAN+PATCH+CORD+CABLE+1.5+METERs&_osa
cat=0&_from=R40&_trksid=p2045573.m570.l1313.TR0.TRC0.H0.X200ft+feet+RS485+Signal+Transmission+Cabl
e+for+Control+CCTV+PTZ+Security+camera&_nkw=200ft+feet+RS485+Signal+Transmission+Cable+for+Control
+CCTV+PTZ+Security+camera&_sacat=0
Electric bell
http://www.ebay.in/itm/electric-bell-kit-do-yourself-diy-science-activity-model-hobby-toy-gift/111303990398?pt=in_toys_games_school_stuff
8. References
www.wikipedia.org
http://www.alibaba.com/trade/search?fsb=y&IndexArea=product_en&CatId=&SearchText=hf-fr701
http://stackoverflow.com
http://www.mathworks.in
Research paper on Viola Jones Face detection algorithm