28-10-2016, 11:34 AM
[attachment=74088]
Abstract— Face Recognition is a very active research
area specializing on how to recognize faces within images
or videos. Face recognition compliments Face Detection.
Face Detection is the process of finding a 'face' within
images or videos and Face Recognition is the process of
matching the detected 'face' to one of many the faces
known to the file system. Our goal was to create a
portable low cost system using the advanced
communication technologies like GPS and GSM. An
intelligent portable human recognition and identification
system is proposed in this project using an ARM 7 based
microcontroller and opencv based machine. The system
consists of two parts. Unit 1 consists of portable system
with BSD Linux including opencv library, usb and serial
port to perform the image processing part . Initially using
an usb camera interface continuous images are captured
and these images are processed with help of Opencv and
compared with existing database. If the current images
are matching with any of the existing images the system
generates command to the unit 2.The unit 2 will perform
the location identification using GPS and forward the
necessary information about the identified person using
GSM/GPRS to concern authorities.
INTRODUCTION
Generally this face recognition is a big challenge as
there is a chance of high uncertainty due to the external
lighting conditions, so we are taking the advantage of
gray scale images and PCA (Principle Component
Analysis), which are less effected to the external
environment changes
And mainly a prior step of this face recognition
involves face detection which is also a big challenge.
For this we are taking the help of pre-designed
cascades whose detection of objects is satisfactory [5].
With the increasing threat of terrorist, the advanced
video surveillance system has to be put into use. The
advanced video surveillance system needs to analyze
the behaviors of people in order to prevent the
occurrence of the potential dangerous case. In recent
years, the development of human detection and
tracking system has been going forwards for several
years, many real time systems have been developed.
Face based applications such as face recognition and
video surveillance systems have been more popular in
computer vision during past several years.
Functions mainly aimed at real time computer vision,
developed by Intel in 1999 and now supported by
Willow Garage [1]. So, for the easy development of
these entire image processing algorithms on a microcontroller,
we are taking the help of OpenCV (Open
Source Computer Vision Library) which is a library of
programming .It is free for use under the open source
BSD license [2][5]. It focuses mainly on real-time
image processing. As OPENCV can support all the
Image and Signal processing algorithms and which can
be ported onto the Linux platform very easily. The
major applications of this OPENCV include 2D & 3D
feature extractions, Ego motion estimation, Facial
recognition system, Gesture recognition, Human
computer interaction, Mobile robotics [6].
The first part of this project is to use a camera for
detecting image or face, face recognisation is the
important part of this project will be done using Open
CV . The image capture is converted into digital data
and transfers to the microcontroller for further process.
The image capture will be assigned with a unique ID
which will be compared with the IDs predefine in the
database, if the ID matches with predefine one then the
information such as particular name assigned to the ID,
location of the person and time when the person is
detected is send as a SMS to the predefine number in
the code. If not matches then it will give ―INVALID
ID‖.
This paper has 6 sections with introduction &
conclusion. part II of this work describes literature survey, partIII describes Methodology of work
partIV hardware implementation partV software
implementation partVI implementation of human face
recognition.
II. LITERATURE SURVEY
The research proposes the design of human
recognition system that improves speed of the theft
identification by OpenCV library and GPS and GSM
and LPC2148. Inigo R.M., Application of machine
vision to traffic monitoring andControl[1], Wang Lei,
Jiang Bing, Chen Wenjian, Design of onboard
navigation system based on ARM platform,
Microprocessors[2] The main advantage of this kind
architecture is its detection speed a cascade detector
can detect faces almost in real time. Every node is a
classifier which determines one image block contains
faces or by several ―features‖. So, how to choose those
features is the key point. XIE Yonghua, LIU Chuancai,
YANG Jinyu(2008). ―The algorithm based on DDCT
and TCSVD of human-face feature extraction and
recognition[3].
To speed up the system to meet the real-time ability,
we choose the cascade detector method to be part of
work bases, which has been proved to be the nearly
fastest method of all. A cascade face detector uses a
sequence of node classifiers to distinguish faces from
non-faces. The proposed face detection method is
based on a cascade of simple classifiers to handle each
part of one integral image. Xusheng Tang, Zongying
Ou, Tieming Su,Pengfei Zhao, ―Cascade AdaBoost
Classifiers with StagFeaturesOptimization for Cellular
Phone Embedded Face Detection System[10] Zhu Yu
Lian Fuzzy Within-Class matrix Principal Component
Analysis And Its Application To Face Recognition[13].
The first alpha version of OpenCV was released to the
public at the IEEE Conference on Computer Vision
and Pattern Recognition in 2000, and five betas were
released between 2001 and 2005. The first 1.0 version
was released in 2006. In mid 2008, OpenCV obtained
corporate support from Willow Garage, and is now
again under active development. A version 1.1 "prerelease"
was released in October 2008.
III. METHODOLOGY OF WORK
This embedded system is based on human-face
recognition system. The S3C3400 chip is used as the
core of this embedded system which is combined with
the technologies of human-face recognition and GSM
wireless communication. The new system contained
the function of human-face recognition and take
advantage of the present one. Face detection is to find
faces in one image by the trained cascade classifiers
[14]. Every node determines whether there are faces in
the image according the data in classifiers‟ data file
which is the outcome of training process. As a result,
face detection process is a pure calculation process,
and most of the results of face detection research
papers are obtained by detecting images on personal
computer platform.The main functions are shown as
follows:
A. Human-face recognition: The owners’ face
information is used as the standards recognition. It
must verify the feature of the human face before using
vehicle.
B. Message alarming: When someone try to thieve
the vehicle, the message can be send to the owners’
mobile phone as soon as possible without any noise.
C. GPS: The GPS system is designed such that at any
point, a GPS module on earth has a clear view of at
least four satellites.
D. GSM: GSM digitizes and compress data then sends
it down a channel with two other streams of our user
data,each in its own time slot.
IV. IMPLEMENTATION
The design of whole system shown in Fig.1 consisted
of two part which are hardware and software. The
hardware are Designed by the rules of embedded
system, and the steps of software consisted of three
parts.
DESIGN OF HARDWARE:
The LPC2148 chip is used as the core of whole
hardware which operates around 1.2V internal,
1.8V/2.5V/3.3V memory, 3.3V external I/O
microprocessor with 512KB of flash memory and
40KB of SRAM. Furthermore, the modules of LCD,
USB camera, GPS, GSM are connected with the
LPC2148 main chip. There are several modules
consisted of the system as follows:
LPC2148:
Based on ARM7TDMI CPU with Real-time
emulation.LPC2148 is developed by the PHILIPS, is
designed to provide hand-held devices and general
applications with low-power, and high-performance
microcontroller solution. Due to their tiny size and low
power consumption, LPC2148 are ideal for
applications where miniaturization is a key
requirement, such as access control and point-of-sale.
Serial communications interfaces ranging from a USB
2.0 Full-speed device, multiple UARTs, SPI, SSP to
I2C-bus and on-chip SRAM of 8 kB up to 40 kB, make
these devices very well suited for communication
gateways and protocol converters, soft modems, voice
recognition and low end imaging, providing both large
buffer size and high processing power. Various 32-bit
timers, single or dual 10-bit ADC(s), 10-bit DAC,
PWM channels and 45 fast GPIO lines with up to nine
edge or level sensitive external interrupt pins make
these microcontrollers suitable for industrial control
and medical systems
.
Hex Keyboard module: It can be used for controlling
recognition method and inputting passwords.
Alarming module: SIM300 alarming module is based
on GSM technology implement which can call the
police without any sound and send message to owner.
USB module: The function of ZCD301P USB acquires
the human-face information.
SRAM and FLASH: The 16-bit 29LV160BB-7OREC
of FLASH chip and the 32-bit HY57V561620CT-6 of
SRAM chip are connected with the main chip. Their
functions are storing the running code, the information
of human-face and the algorithm.
Embedded control platform should control those
Processes below:
1) Obtain images from camera by USB;
2) Detect faces in images;
3) Get and handle the data from GPS module;
4) Send messages by GSM module;
5) Control IIC interface;
GPS MODULE:
Nowadays the most widely used positioning system is
the Global Positioning System of America (GPS),
which is a system consisting 24 satellites whose
searching area embrace the globe [1]. It can ensure that
more than 4satellites will be observed at one time, no
matter what time it is or where you are, thus making
sure that they can collect the longitude and latitude of
the view point, and furthermore realizing the function
of navigation, Positioning and time service [1].
GPS technique has been widely used both in military
equipments and civil devices in recent years [1]. We
choose Jupiter TU30 GPS module to offer the location
of the system in time. TU30 has a UART (Universal
Asynchronous Receiver/Transmitter), which can be
used to communicate with many other embedded
devices. It is easy to get a serial of char from TU30 at
9600 bps. GPS modules have to evaluate weak antenna
signals from at least four satellites, in order to
determine a correct three-dimensional position. A time
signal is also often emitted in addition to longitude,
latitude and height.
28 satellites inclined at 55° to the equator orbit the
Earth every 11 hours and 58 minutes at a height of
20,180 km on 6 different orbital planes as shown in
Fig.2. Each one of these satellites has up to four atomic
clocks on board.
GSM MODULE:
GSM is the most widely used mobile technology
Using a simple Subscriber Identity Module (SIM) it
has taken the world of mobile communication to new
Heights[1]. To achieve important information of
system, one GSM module is added in to the system
I.CONCLUSION:
Generally this face recognition is a big challenge as
there is a chance of high uncertainty due to the external
lighting conditions, so we are taking the advantage of
gray scale images and PCA (Principle Component
Analysis), which are less effected to the external
environment changes. An intelligent portable human
recognition and identification system is proposed in
this project using an ARM 7 based microcontroller and
opencv based machine. The proposed face detection
method is based on a cascade of simple classifiers to
handle each part of one integral image. The design of
whole system consisted of two part which are hardware
and software.
As size and portability are the major unique
advantages of this OpenCV, it can replace all other
image and signal processing tools like MATLAB
which is of very huge size and which can’t be ported
onto any device. What’s more, the system contained
the second verifying methods which were inputting
owner’s password in order to make the other people
gain the permission of owner’s to use the vehicle. The
security features were enhanced largely for the stability
and liability of human-face recognition. This
technology FRS USING OPEN CV library provides
user to know more about the visitor besides a notice
which usually left from visitor. The system has
successfully implemented in the real time environment
with capability to capture the object that appears in
front of the camera. If another GPRS module is added
in, the image data could also sent to an information
server and sends the image through MMS.
Abstract— Face Recognition is a very active research
area specializing on how to recognize faces within images
or videos. Face recognition compliments Face Detection.
Face Detection is the process of finding a 'face' within
images or videos and Face Recognition is the process of
matching the detected 'face' to one of many the faces
known to the file system. Our goal was to create a
portable low cost system using the advanced
communication technologies like GPS and GSM. An
intelligent portable human recognition and identification
system is proposed in this project using an ARM 7 based
microcontroller and opencv based machine. The system
consists of two parts. Unit 1 consists of portable system
with BSD Linux including opencv library, usb and serial
port to perform the image processing part . Initially using
an usb camera interface continuous images are captured
and these images are processed with help of Opencv and
compared with existing database. If the current images
are matching with any of the existing images the system
generates command to the unit 2.The unit 2 will perform
the location identification using GPS and forward the
necessary information about the identified person using
GSM/GPRS to concern authorities.
INTRODUCTION
Generally this face recognition is a big challenge as
there is a chance of high uncertainty due to the external
lighting conditions, so we are taking the advantage of
gray scale images and PCA (Principle Component
Analysis), which are less effected to the external
environment changes
And mainly a prior step of this face recognition
involves face detection which is also a big challenge.
For this we are taking the help of pre-designed
cascades whose detection of objects is satisfactory [5].
With the increasing threat of terrorist, the advanced
video surveillance system has to be put into use. The
advanced video surveillance system needs to analyze
the behaviors of people in order to prevent the
occurrence of the potential dangerous case. In recent
years, the development of human detection and
tracking system has been going forwards for several
years, many real time systems have been developed.
Face based applications such as face recognition and
video surveillance systems have been more popular in
computer vision during past several years.
Functions mainly aimed at real time computer vision,
developed by Intel in 1999 and now supported by
Willow Garage [1]. So, for the easy development of
these entire image processing algorithms on a microcontroller,
we are taking the help of OpenCV (Open
Source Computer Vision Library) which is a library of
programming .It is free for use under the open source
BSD license [2][5]. It focuses mainly on real-time
image processing. As OPENCV can support all the
Image and Signal processing algorithms and which can
be ported onto the Linux platform very easily. The
major applications of this OPENCV include 2D & 3D
feature extractions, Ego motion estimation, Facial
recognition system, Gesture recognition, Human
computer interaction, Mobile robotics [6].
The first part of this project is to use a camera for
detecting image or face, face recognisation is the
important part of this project will be done using Open
CV . The image capture is converted into digital data
and transfers to the microcontroller for further process.
The image capture will be assigned with a unique ID
which will be compared with the IDs predefine in the
database, if the ID matches with predefine one then the
information such as particular name assigned to the ID,
location of the person and time when the person is
detected is send as a SMS to the predefine number in
the code. If not matches then it will give ―INVALID
ID‖.
This paper has 6 sections with introduction &
conclusion. part II of this work describes literature survey, partIII describes Methodology of work
partIV hardware implementation partV software
implementation partVI implementation of human face
recognition.
II. LITERATURE SURVEY
The research proposes the design of human
recognition system that improves speed of the theft
identification by OpenCV library and GPS and GSM
and LPC2148. Inigo R.M., Application of machine
vision to traffic monitoring andControl[1], Wang Lei,
Jiang Bing, Chen Wenjian, Design of onboard
navigation system based on ARM platform,
Microprocessors[2] The main advantage of this kind
architecture is its detection speed a cascade detector
can detect faces almost in real time. Every node is a
classifier which determines one image block contains
faces or by several ―features‖. So, how to choose those
features is the key point. XIE Yonghua, LIU Chuancai,
YANG Jinyu(2008). ―The algorithm based on DDCT
and TCSVD of human-face feature extraction and
recognition[3].
To speed up the system to meet the real-time ability,
we choose the cascade detector method to be part of
work bases, which has been proved to be the nearly
fastest method of all. A cascade face detector uses a
sequence of node classifiers to distinguish faces from
non-faces. The proposed face detection method is
based on a cascade of simple classifiers to handle each
part of one integral image. Xusheng Tang, Zongying
Ou, Tieming Su,Pengfei Zhao, ―Cascade AdaBoost
Classifiers with StagFeaturesOptimization for Cellular
Phone Embedded Face Detection System[10] Zhu Yu
Lian Fuzzy Within-Class matrix Principal Component
Analysis And Its Application To Face Recognition[13].
The first alpha version of OpenCV was released to the
public at the IEEE Conference on Computer Vision
and Pattern Recognition in 2000, and five betas were
released between 2001 and 2005. The first 1.0 version
was released in 2006. In mid 2008, OpenCV obtained
corporate support from Willow Garage, and is now
again under active development. A version 1.1 "prerelease"
was released in October 2008.
III. METHODOLOGY OF WORK
This embedded system is based on human-face
recognition system. The S3C3400 chip is used as the
core of this embedded system which is combined with
the technologies of human-face recognition and GSM
wireless communication. The new system contained
the function of human-face recognition and take
advantage of the present one. Face detection is to find
faces in one image by the trained cascade classifiers
[14]. Every node determines whether there are faces in
the image according the data in classifiers‟ data file
which is the outcome of training process. As a result,
face detection process is a pure calculation process,
and most of the results of face detection research
papers are obtained by detecting images on personal
computer platform.The main functions are shown as
follows:
A. Human-face recognition: The owners’ face
information is used as the standards recognition. It
must verify the feature of the human face before using
vehicle.
B. Message alarming: When someone try to thieve
the vehicle, the message can be send to the owners’
mobile phone as soon as possible without any noise.
C. GPS: The GPS system is designed such that at any
point, a GPS module on earth has a clear view of at
least four satellites.
D. GSM: GSM digitizes and compress data then sends
it down a channel with two other streams of our user
data,each in its own time slot.
IV. IMPLEMENTATION
The design of whole system shown in Fig.1 consisted
of two part which are hardware and software. The
hardware are Designed by the rules of embedded
system, and the steps of software consisted of three
parts.
DESIGN OF HARDWARE:
The LPC2148 chip is used as the core of whole
hardware which operates around 1.2V internal,
1.8V/2.5V/3.3V memory, 3.3V external I/O
microprocessor with 512KB of flash memory and
40KB of SRAM. Furthermore, the modules of LCD,
USB camera, GPS, GSM are connected with the
LPC2148 main chip. There are several modules
consisted of the system as follows:
LPC2148:
Based on ARM7TDMI CPU with Real-time
emulation.LPC2148 is developed by the PHILIPS, is
designed to provide hand-held devices and general
applications with low-power, and high-performance
microcontroller solution. Due to their tiny size and low
power consumption, LPC2148 are ideal for
applications where miniaturization is a key
requirement, such as access control and point-of-sale.
Serial communications interfaces ranging from a USB
2.0 Full-speed device, multiple UARTs, SPI, SSP to
I2C-bus and on-chip SRAM of 8 kB up to 40 kB, make
these devices very well suited for communication
gateways and protocol converters, soft modems, voice
recognition and low end imaging, providing both large
buffer size and high processing power. Various 32-bit
timers, single or dual 10-bit ADC(s), 10-bit DAC,
PWM channels and 45 fast GPIO lines with up to nine
edge or level sensitive external interrupt pins make
these microcontrollers suitable for industrial control
and medical systems
.
Hex Keyboard module: It can be used for controlling
recognition method and inputting passwords.
Alarming module: SIM300 alarming module is based
on GSM technology implement which can call the
police without any sound and send message to owner.
USB module: The function of ZCD301P USB acquires
the human-face information.
SRAM and FLASH: The 16-bit 29LV160BB-7OREC
of FLASH chip and the 32-bit HY57V561620CT-6 of
SRAM chip are connected with the main chip. Their
functions are storing the running code, the information
of human-face and the algorithm.
Embedded control platform should control those
Processes below:
1) Obtain images from camera by USB;
2) Detect faces in images;
3) Get and handle the data from GPS module;
4) Send messages by GSM module;
5) Control IIC interface;
GPS MODULE:
Nowadays the most widely used positioning system is
the Global Positioning System of America (GPS),
which is a system consisting 24 satellites whose
searching area embrace the globe [1]. It can ensure that
more than 4satellites will be observed at one time, no
matter what time it is or where you are, thus making
sure that they can collect the longitude and latitude of
the view point, and furthermore realizing the function
of navigation, Positioning and time service [1].
GPS technique has been widely used both in military
equipments and civil devices in recent years [1]. We
choose Jupiter TU30 GPS module to offer the location
of the system in time. TU30 has a UART (Universal
Asynchronous Receiver/Transmitter), which can be
used to communicate with many other embedded
devices. It is easy to get a serial of char from TU30 at
9600 bps. GPS modules have to evaluate weak antenna
signals from at least four satellites, in order to
determine a correct three-dimensional position. A time
signal is also often emitted in addition to longitude,
latitude and height.
28 satellites inclined at 55° to the equator orbit the
Earth every 11 hours and 58 minutes at a height of
20,180 km on 6 different orbital planes as shown in
Fig.2. Each one of these satellites has up to four atomic
clocks on board.
GSM MODULE:
GSM is the most widely used mobile technology
Using a simple Subscriber Identity Module (SIM) it
has taken the world of mobile communication to new
Heights[1]. To achieve important information of
system, one GSM module is added in to the system
I.CONCLUSION:
Generally this face recognition is a big challenge as
there is a chance of high uncertainty due to the external
lighting conditions, so we are taking the advantage of
gray scale images and PCA (Principle Component
Analysis), which are less effected to the external
environment changes. An intelligent portable human
recognition and identification system is proposed in
this project using an ARM 7 based microcontroller and
opencv based machine. The proposed face detection
method is based on a cascade of simple classifiers to
handle each part of one integral image. The design of
whole system consisted of two part which are hardware
and software.
As size and portability are the major unique
advantages of this OpenCV, it can replace all other
image and signal processing tools like MATLAB
which is of very huge size and which can’t be ported
onto any device. What’s more, the system contained
the second verifying methods which were inputting
owner’s password in order to make the other people
gain the permission of owner’s to use the vehicle. The
security features were enhanced largely for the stability
and liability of human-face recognition. This
technology FRS USING OPEN CV library provides
user to know more about the visitor besides a notice
which usually left from visitor. The system has
successfully implemented in the real time environment
with capability to capture the object that appears in
front of the camera. If another GPRS module is added
in, the image data could also sent to an information
server and sends the image through MMS.