Docstoc

A Survey Paper on Biometric Pattern Recognition

Document Sample
A Survey Paper on Biometric Pattern Recognition Powered By Docstoc
					Int. J. Tech. 2011; Vol. 1: Issue 1, Pg 49-52




ISSN       2231-3907 (Print)                    2231-3915 (Online)      www.enggresearch.net

RESEARCH ARTICLE
A Survey Paper on Biometric Pattern Recognition

Anita Bara and Anurag Shrivastava

Shree Shankaracharya College of Engineering and Technology, Bhilai (CG) India
*Corresponding Author E-mail: monacyril2000@gmail.com


ABSTRACT:
This paper focus about biometric face recognition with different methodologies and comparison between them. Now a
day’s face recognition is play very crucial role in recent technology like mostly companies are adopting the biometric
identification for login but when images are degraded than the performance of our system is reduced. This paper gives
some idea about steps by steps face recognition algorithm how face is recognized but when quality of an image is
degrade due to some noise or any external reason than matching process will not give accurate result for this reason we
adopt some restoration and enhancement techniques like retinex theory for degrade image to improve quality for
better performance in next part of my work.

KEYWORDS: Face detection, classification, pattern recognition, Biometric, PCA, LDA.


1. INTRODUCTION:                                                     A machine vision system captures images via a camera and
Pattern recognition is the scientific discipline whose goal is       analyzes them to produce descriptions of what is imaged[2].
the classification of objects into a number of categories or         A typical application of a machine vision system is in the
classes [5]. Depending on the application, these objects can         manufacturing industry, either for automated visual
be images or signal waveforms or any type of                         inspection or for automation in the assembly line. For
measurements that need to be classified. We will refer to            example, in inspection, manufactured objects on a moving
these objects using the generic term patterns. Pattern               conveyor may pass the inspection station, where the camera
recognition has a long history, but before the 1960s it was          stands, and it has to be ascertained whether there is a defect.
mostly the output of theoretical research in the area of             Thus, images have to be analyzed online, and a pattern
statistics [6]. As with everything else, the advent of               recognition system has to classify the objects into the
computers increased the demand for practical applications            “defect” or “non defect” class[7]. After that, an action has
of pattern recognition, which in turn set new demands for            to be taken, such as to reject the offending parts. In an
further theoretical developments. As our society evolves             assembly line, different objects must be located and
from the industrial to its postindustrial phase, automation in       “recognized,” that is, classified in one of a number of
industrial production and the need for information handling          classes known a priori. Examples are the “screwdriver
and retrieval are becoming increasingly important[8]. This           class,” the “German key class,” and so forth in a tools’
trend has pushed pattern recognition to the high edge of             manufacturing unit. Then a robot arm can move the objects
today’s engineering applications and research. Pattern               in the right place. Character (letter or number) recognition
recognition is an integral part of most machine intelligence         is another important area of pattern recognition, with major
systems built for decision making. Machine vision is an              implications in automation and information handling.
area in which pattern recognition is of importance.                  Optical character recognition (OCR) systems are already
                                                                     commercially available and more or less familiar to all of
                                                                     us, the light sensitive detector, light-intensity variation is
                                                                     translated into “numbers” and an image array is formed. In
                                                                     the sequel, a series of image processing techniques are
                                                                     applied leading to line and character segmentation.
                                                                     Computer-aided diagnosis is another important application
Received on 11.03.2011     Accepted on 12.04.2011                    of pattern recognition, aiming at assisting doctors in making
© EnggResearch.net All Right Reserved                                diagnostic decisions. The final diagnosis is, of course, made
Int. J. Tech. 1(1): Jan.-June. 2011; Page 49-52                      by the doctor. Computer-assisted diagnosis has been
                                                                     applied to and is of interest for a variety of medical data

                                                                49
Int. J. Tech. 2011; Vol. 1: Issue 1, Pg 49-52


,such as X-rays, computed tomographic images, ultrasound          measured cues that characterize a music piece, such as the
images,         electrocardiograms          (ECGs),        and    music meter, the music tempo, and the location of certain
electroencephalograms (EEGs). The need for a computer-            repeated patterns and many applications of pattern
aided diagnosis stems from the fact that medical data are         recognition like figure print recognition, iris recognition, etc
often not easily interpretable, and the interpretation can        [2]. In below figures the percentage of pattern recognitions
depend very much on the skill of the doctor. Let us take for      application given
example X-ray mammography for the detection of breast
cancer[9]. Although mammography is currently the best
method for detecting breast cancer, 10 to 30% of women
who have the disease and undergo mammography have
negative mammograms. In approximately two thirds of
these cases with false results the radiologist failed to detect
the cancer, which was evident retrospectively. This may be
due to poor image quality, eye fatigue of the radiologist, or
the subtle nature of the findings. The percentage of correct
classifications improves at a second reading by another
radiologist. Thus, one can aim to develop a pattern
recognition system in order to assist radiologists with a
“second” opinion. Increasing confidence in the diagnosis
based on mammograms would, in turn, decrease the number
of patients with suspected breast cancer who have to
undergo surgical breast biopsy, with its associated
complications [1].Data mining and knowledge discovery in
databases is another key application area of pattern
recognition. Data mining is of intense interest in a wide
range of applications such as medicine and biology, market
and financial analysis, business management, science
exploration, image and music retrieval [3]. Its popularity
stems from the fact that in the age of information and
knowledge society there is an ever increasing demand for
retrieving information and turning it into knowledge.
Moreover, this information exists in huge amounts of data
in various forms including, text, images, audio and video,
stored in different places distributed all over the world [7].
The traditional way of searching information in databases
was the description-based model where object retrieval was
based on keyword description and subsequent word
matching. However, this type of searching presupposes that
a manual annotation of the stored information has
previously been performed by a human [6]. This is a very
time-consuming job and, although feasible when the size of
the stored information is limited, it is not possible when the    2: Biometric recognition: Personal recognition based on
amount of the available information becomes large[5].             “who you are or what you do” as opposed to “what you
Moreover, the task of manual annotation becomes                   know” (password) o“ what you have” (ID card)
problematic when the stored information is widely
distributed and shared by a heterogeneous “mixture” of
sites and users. Content-based retrieval systems are
becoming more and more popular where information is
sought based on “similarity” between an object, which is
presented into the system, and objects stored in sites all
over the world [6]. In a content-based image retrieval CBIR
(system) an image is presented to an input device
(e.g.,scanner). The system returns “similar” images based
on a measured“ signature,” which can encode, for example,
information related to color, texture and shape [4]. In a
music content-based retrieval system, an example (i.e., an
extract from a music piece), is presented to a microphone
input device and the system returns “similar” music pieces.
In this case, similarity is based on certain (automatically)

                                                              50
Int. J. Tech. 2011; Vol. 1: Issue 1, Pg 49-52


                                                                 done using the simple Euclidean distance equation. The
                                                                 PCA usually became a benchmark method to the others and
                                                                 it is extensively used in many research papers (Duan et al.,
                                                                 2008; Mong et al., 2009).

                                                                 3: Review of Biometrics Face Recognition algorithm




                                                                 PCA: The Eigen face algorithm uses the Principal
                                                                 Component Analysis (PCA) for dimensionality reduction to
                                                                 find the vectors which best account for the distribution of
                                                                 face images within the entire image space. These vectors
                                                                 define the subspace of face images and the subspace is
                                                                 called face space. All faces in the training set are projected
Face recognition is a subject in pattern recognition study for   onto the face space to find a set of weights that describes
machine learning applications. Although, other biometrics        the contribution of each vector in the face space. To identify
system such as fingerprint, iris and others reported to be       a test image, it requires the projection of the test image onto
more accurate, the research in face recognition has              the face space to obtain the corresponding set of weights[
significantly increase for the past 20 years because of its      8]. By comparing the weights of the test image with the set
non-intrusive characteristic (Angle et al., 2005)[3].            of weights of the faces in the training set, the face in the test
Furthermore, face recognition systems require minimal            image can be identified.
participation from users in order to perform identification
tasks. Despite of these advantages, to build a face              ICA: Independent Component Analysis (ICA) is similar to
recognition system is not an easy task. Several constraints      PCA except that the distribution of the components is
that usually confront researchers are varying poses, lighting    designed to be non-Gaussian. Maximizing non-Gaussianity
conditions and facial expressions.                               promotes statistical independence. Figure 11 presents the
                                                                 different feature extraction properties between PCA and
There are certain techniques used in face recognition study      ICA. Bartlett et al. [8] provided two architectures based on
(Zhao et al., 2000). One of it is the statistical pattern        Independent Component Analysis, statistically independent
method which has been extensively adopted in many face           basis images and a factorial code representation, for the face
recognition commercial products (Jain et al., 2000)[5]. A        recognition task. The ICA separates the high-order
statistical method is defined as a method which analyzes a       moments of the input in addition to the second-order
pattern data with D dimensional input vector. The                moments utilized in PCA. Both the architectures lead to a
representation of the input data are usually the pre-            similar performance.
processed by reducing the dimensionality, extract the
relevant information from the data and remove noise before       LDA: Both PCA and ICA construct the face space without
the recognition task is performed [7]. One of the earliest       using the face class (category) information. The whole face
statistical methods is by Turk and Pentland , who has            training data is taken as a whole. In LDA the goal is to find
proposed the eigenfaces or also known as Principal               an efficient or interesting way to represent the face vector
Component Analysis (PCA) method. The classification is           space. But exploiting the class information can be helpful to

                                                             51
Int. J. Tech. 2011; Vol. 1: Issue 1, Pg 49-52


the identification tasks. The Fisherface algorithm [10] is      5: Perform Analysis of Different Algorithms.
derived from the Fisher Linear Discriminant (FLD), which
uses class specific information. By defining different
classes with different statistics, the images in the learning
set are divided into the corresponding classes. Then,
techniques similar to those used in Eigenface algorithm are
applied. The Fisherface algorithm results in a higher
accuracy rate in independent component axes. Each axis is a
direction found by PCA or ICA. Note the PC axes are
orthogonal while the IC axes are not. If only 2 components
are allowed, ICA chooses a different subspace than PCA.
Bottom left: Distribution of the first PCA coordinate of the    6: CONCLUSION:
data. Bottom right: distribution of the first ICA coordinates   Image-based face recognition is still a very challenging
of the data [7]. For this example, ICA tends to extract more    topic after decades of exploration. A number of typical
intrinsic structure of the original data clusters.              algorithms are presented, being categorized into
                                                                appearance-based and model-based schemes. Sensitivity to
Model-based face recognition: The model-based face              variations in pose and different lighting conditions is still a
recognition scheme is aimed at constructing a model of the      challenging problem. Georghiades et al. extensively
human face, which is able to capture the facial variations.     explored the illumination change and synthesis for facial
The prior knowledge of human face is highly utilized to         analysis using appearance-based approaches to achieve an
design the model. For example, feature-based matching           illumination-invariant face recognition system.
derives distance and relative position features from the
placement of internal facial elements (e.g., eyes, etc.). By    7. REFERENCES:
localizing the corners of the eyes, nostrils, etc. in frontal   1.  R. Chellappa, C.L. Wilson, and S. Sirohey, “Human and machine
views, his system computed parameters for each face,                recognition of faces: A survey,” Proc. IEEE, vol. 83, pp. 705–
which were compared (using a Euclidean metric) against              740, 1995.
                                                                2. H. Wechsler, P. Phillips, V. Bruce, F. Soulie, and T. Huang, Face
the parameters of known faces. A more recent feature-based          Recognition: From Theory to Applications, Springer-Verlag,
system, based on elastic bunch graph matching, was                  1996.
developed by Wiskott et al. as an extension to their original   3. W. Zhao, R. Chellappa, A. Rosenfeld, and P.J. Phillips, “Face
graph matching system . By integrating both shape                   recognition: A literature survey,” CVL Technical Report,
                                                                    University of Maryland,2000
                                                                4. S. Gong, S.J. McKenna, and A. Psarrou, Dynamic Vision: from
                                                                    Images to Face Recognition, Imperial College Press and World
                                                                    Scientific Publishing, 2000.
4: Comparison between Appearance and Model based                5. Terence Sim and Takeo Kanade. Illuminating the face. Technical
Algorithm                                                           report, Robotics Institute, Carnegie Mellon University,
                                                                    September 2001.
                                                                6. E. Land and J. McCann. Lightness and retinex theory. Journal of
                                                                    the Optical Society of America, 61(1):1–11,
                                                                7. P. Perona and J. Malik. Scale-space and edge detection using
                                                                    anisotropic diffusion. IEEE Transactions on PAMI, 12(7):629–
                                                                    639, 1990.
                                                                8. T. Ojala, M. Pietikainen, and T. Maenpaa. Multiresolution gray-
                                                                    scale and rotation invariant texture classification with local binary
                                                                    patterns. IEEE Transactions on PAMI, 24(7):971–987, 2004.
                                                                9. G. Heusch, Y. Rodriguez, and S. Marcel. Local binary patterns as
                                                                    image preprocessing for face authentication. In IEEE
                                                                    International Conference on Automatic Face and Gesture
                                                                    Recognition, 2006.
                                                                10. Qian Tao and Raymond N. J. Veldhuis, “Biometric authentication
                                                                    for a mobile personal device”, Proceedings of the 1st
                                                                    International Workshop on Personalized Networks (Pernets2006),
                                                                    San Jose, July 2006.




                                                            52

				
DOCUMENT INFO
Shared By:
Tags:
Stats:
views:12
posted:10/11/2011
language:English
pages:4