Professional Documents
Culture Documents
Real Time Embedded Face Recognition Using Arm7: B.koteswar Rao, P., MA - Wajeed
Real Time Embedded Face Recognition Using Arm7: B.koteswar Rao, P., MA - Wajeed
Real Time Embedded Face Recognition Using Arm7: B.koteswar Rao, P., MA - Wajeed
biological recognition market. Therefore, it is very in consumer applications. Their aim is to design and
important for the research of face recognition build a face recognition system that is robust for
technology. This project, which is based on ARM7 natural consumer environments and can be executed
and windows operating system, is a portable device on low-cost hardware.FA007 is an embedded facial
and meets the Requirements. In the last years, recognition system with the latest version of leading
different problems in face image analysis, such as “Dual Sensor™” Algorithm Ver 3.0, which applied
face detection, burr recognition [1] and facial for high level access control application. Its classic
expression recognition [5] have received very much slope and industrial design is good for market like
attention in computer vision research. Government, Civil ID. It is also good for commercial
market like Enterprise, Bank, and building
The problem is more interesting from the viewpoints automation and so on.
of basic research aiming to efficient descriptors for
facial images and of applications such as surveillance Chin-Shu Chang; Teh-Lu Liao; Po-Yun
and human-computer interaction [2].A key issue in Hsu; Kuo-Kuang Chen proposed human face
face analysis are finding efficient de-scriptors for face recognition system using modified PCA algorithm
appearance. Given the low inter-person variation in\ and ARM platform [27]. They used the human face
face images, ideal descriptors should be very as the main subject for authentication.
discriminative. Still, they should be robust to
Because the ARM system provides strong
different perturbations and changes such as
computation ability, various interfaces such as
illumination and pose changes, aging of the subjects,
camera, mass storage, etc. Their study includes
etc. for displaying the image of output for
recognizer algorithm-Principal Component Analysis
convenient and for more user options purpose code is
(PCA) is completely accomplished on the ARM
written in matlab as front end.
system. Finally, an ARM-based human face
recognition platform is implemented in this
Because Matlab is a high performance language for
study.Vikram kulkarni, k.Laxminarashima rao
technical computing It integrates computation
proposed Embedded car security system on face
visualization and programming in an easy to use
detection [28].
environment. And processing of image and
recognition of image is done by using ARM In this proposal embedded car security system, FDS
processor that runs at backend. This paper is (Face Detection System) is used to detect the face of
organized as follows. In section II we overview about the driver and compare it with the predefined face. In
some of the prior face recognition related research case any theft to car information is sent to the owner
that led to our research. In section III we present the through MMS. So now owner can obtain the image
details of our face recognition system and in section of the thief in his mobile as well as he can trace the
IV about the results and followed by experiment location through GPS.
analysis and conclusion.
II.RELATED WORK
The location of the car as well as its speed can be
In this section, we briefly describe some other displayed to the owner through SMS. So by using
techniques for face recognition. Fei zuo, with this system, owner can identify the thief image as
Eindhoven [26] proposed Real-time embedded face well as the location of the car.
recognition for smart home in which he proposed a
near real-time face recognition system for embedding
III. IMPLEMENTATION
III.1Methodology of main Algorithm Here, kY (i,j) is the code value of pixel (i; j) of image
B and w( ) is a user-defined function giving the
In this process first the facial image is divided into penalty to include for a pixel at the given spatial
local regions and texture descriptors are extracted
distance from the nearest matching code in A. Next
from each region independently. The descriptors are
then concatenated to form a global description of the process is to check for the similarity between images
face. See Fig 2 for an example of a facial image according to the distance among the images. The
divided into rectangular regions of size 3x3 . process of calculating the distance is called kernel
IV.SYSTEM TEST
V. EXPERIMENT ANALYSIS
ARM 7 processor the required output whether match Feature and Adaboost [J]. Journal of Optoelectronics
found or not found is shown in Fig 5. y Laser, 2006, 17(8):0993-0998.
Mr.MA.Wajeed,
Mr. Rama Krishna B.Tech(EC),M.T
P. received his ech(DECS) Gold
medalist, ISTE
B.Tech Degree in
MEMBER is
Electronics and currently working
communication as an Assistant
Professor, in
engineering in 2008
Department of
and M.Tech degree in DIGITAL ELECTRONICS Electronics &
AND COMMUNICATION SYSTEMS in 2011 Communication ,
from JNTU, Hyderabad, and A.P-India. He is in SARADA INSTITUTE OF TECHNOLOGY &
SCIENCES, Khammam, A.P, India. He was
currently working as an Assistant Professor in the
received a GOLD MEDAL in B.Tech (ECE). And
Department of ECE in LAQSHYA INSTITUTE OF Pursuing M.Tech belongs to Digital Electronics
TECHNOLOGY AND SCIENCE, Khammam, and &Communication systems .His research interests on
digital circuits, embedded systems &Electro magnetic
A.P-India. His research
and transmission lines and signals and systems. He
interests on digital circuits, IMAGE PROCESSING had 2 years of Teaching Experience in academic as
and Communication Systems .He had 3 years of well as competitive exams (GATE).
Teaching experience and also A LIFE MEMBER OF
INDIAN SOCIETY FOR TECHNICAL
EDUCATION