An Effective Approach in Face Recognition Using Image Processing Concepts

International Journal of Application or Innovation in Engineering & Management (IJAIEM)
Web Site: www.ijaiem.org Email: editor@ijaiem.org, editorijaiem@gmail.com Volume 2, Issue 8, August 2013 ISSN 2319 - 4847
An Effective Approach in Face Recognition using Image Processing Concepts

K. Ganapathi Babu1, M.A.Rama Prasad2
2 1 Pursuing M.Tech in CSE at VLITS,Vadlamudi Guntur Dist., A.P., India Asst.Prof, Department of CSE, VLITS,Vadlamudi Guntur Dist., A.P., India
Abstract
Image processing plays a vital role in aspects of all science and technology. In this image processing concepts have great importance in application oriented research and projects. In this face recognition related concepts like authentication, security etc has keen importance. In this we discuss various forms of face recognition using Image processing concepts.
Keywords: face recognition, Image processing, feature extraction
1. INTRODUCTION
When In this face recognition[1] concept we discuss various face recognition techniques and various image processing concepts[8]. In this we discuss different approaches in face recognition and various concepts used in face recognition. In this discus about good approaches in face recognition. In this Eigen faces, discrete cosine transform, filtering, classification ,feature extraction for face recognition. In this we take data sets and apply similarity and classification and then eigen faces calculation and filters and wavelet transforms for face recognition in an effective way.
2.BACKGROUND WORK
Feature extraction[4]: When the input data to an algorithm is too large to be processed and it is suspected to be notoriously redundant then the input data will be transformed into a reduced representation set of features. Transforming the input data into the set of features is called feature extraction. If the features extracted are carefully chosen it is expected that the features set will extract the relevant information from the input data in order to perform the desired task using this reduced representation instead of the full size input. Image processing[8]: image processing is which the input is an image, such as a photo or video the output of image processing possibly will either be an image or a set of characteristics or parameters connected to the image. Image processing regularly refers to digital image processing, except optical and analog image processing also are likely. Pattern recognition[9]: pattern recognition is the task of a label to a given input value. An illustration of pattern recognition is classification[4], which attempts to allot each input value to one of. but, pattern recognition is a additional common problem that encompasses other types of output as well. Other illustration are regression[8], which assigns a real-valued output to each input; succession labeling, which assigns a class to each member of a sequence of values and parsing, which assigns a parse tree to an input sentence, telling the syntactic structure of the sentence. Face recognition: A facial recognition system[9] is a computer application for mechanically identifying or confirming a person from a digital image or a video frame from a video source. One of the behavior to do this is by comparing selected facial features from the image and a facial database. It is classically used in security systems and can be compared to other biometrics such as fingerprint or eye iris recognition systems. Dynamic link matching[4]: Dynamic link matching is a neuronal model for face recognition. It employs wavelet transformations to encode incoming image data. Bunch graph matching is an algorithm stand on many ideas found in dynamic link matching MSL[4]: Multilinear subspace learning (MSL) plans to study a precise little part of a large space of multidimensional objects having a picky desired property. It is a dimensionality reduction approach for decision a low-dimensional representation
Volume 2, Issue 8, August 2013
Page 215

with certain favorite characteristics of high-dimensional tensor data in the course of direct mapping , without going through vectorization[2].The term tensor in MSL refers to multidimensional arrays. illustrations of tensor data include images(2D/3D), video sequences (3D/4D), and hyper spectral cubes(3D/4D). The mapping from a highdimensional tensor space to a low-dimensional tensor space or vector space is named as multilinear projection. HMM[4]: A hidden Markov model (HMM) is a statistical Markov model in which the system individual modeled is assumed to be a Markov process with unobserved states. A HMM can be considered the simplest dynamic Bayesian network[4]. The mathematics behind the HMM was developed by L. E. Baum Elastic matching[4]: Elastic matching is one of the pattern recognition techniques[9] in computer science. Elastic matching (EM) is also known as deformable template, flexible matching, or nonlinear template matching. Elastic matching can be defined as an optimization problem of two-dimensional warping specifying corresponding pixels between subjected images. LDA[8]: Linear discriminant analysis (LDA) and the associated Fisher's linear discriminant are methods worn in statistics, pattern recognition and machine learning to find a linear combination of features which characterizes or separates two or more classes of objects or events. The resulting combination may be used as a linear classifier, or, more frequently, for dimensionality reduction[3] before later classification. PCA[4]: Principal component analysis (PCA) is a mathematical procedure that uses orthogonal transformation to alter a set of observations of maybe correlated variables into a set of values of linearly uncorrelated variables called principal components. The number of principal components is fewer than or equal to the number of original variables. This transformation is defined in such a way that the first principal component has the largest possible and each succeeding component in turn has the highest variance possible under the constraint that it be orthogonal to the previous components. Principal components are guaranteed to be independent if the data set is jointly normally distributed. PCA is sensitive to the relative scaling of the original variables. ICA[5]: independent component analysis (ICA) is a computational method for separating a multivariate signal into additive subcomponents by pretentious that the subcomponents are non-Gaussian signals and that they are all statistically independent of each other. ICA is a special case of blind source separation.
3.RELATED WORK
Eigen values &eigen vectors[8]: An eigenvector of a square matrix is a non-zero vector that, when the matrix is multiplied by , yields a constant multiple of , the multiplier being commonly denoted by . That is: The number is called the eigenvalue of corresponding to
Eigen face[4]: Eigenfaces are a set of eigenvectors used in the computer vision problem of human face recognition. The loom of using eigenfaces for recognition was developed by Sirovich and Kirby (1987) and used by Matthew Turk and Alex Pentland in face classification. It is considered the first flourishing example of facial recognition technology.These eigenvectors are derived from the covariance matrix of the probability distribution of the high-dimensional vector space of likely faces of human beings. DCT: A discrete cosine transform (DCT)[8] expresses a finite series of data points in terms of a sum of cosine functions oscillating at different frequencies. DCTs are significant to numerous applications in science and engineering, from lossy compression of audio and images to spectral methods for the numerical solution of partial differential equations. The use of cosine rather than sine functions is critical in these applications: for compression, it turns out that cosine functions are much more efficient whereas for differential equations the cosines state a particular option of boundary conditions. LSA[4]:
Page 216

Latent semantic analysis (LSA) is a technique in natural language processing, in exacting in vectorial semantics, of analyzing relationships between a set of documents and the terms they enclose by producing a set of concepts related to the documents and terms. LSA assumes that words that are close in meaning will occur in similar pieces of text. A matrix containing word counts per paragraph is constructed from a large piece of text and a mathematical technique called singular value decomposition (SVD) is used to lessen the number of columns while preserving the likeness structure among rows. Words are then compared by taking the cosine of the angle between the two vectors produced by any two rows. Values close to 1 represent very similar words while values close to 0 represent very dissimilar words. Bhatta charyya distance[4] : In statistics, the Bhattacharyya distance measures the similarity of two discrete or continuous probability distributions. It is very much related to the Bhattacharyya coefficient which is a measure of the amount of overlap between two statistial samples or populations The coefficient can be used to determine the relative closeness of the two samples being measured. It is used to measure the separability of classes in classification and it is considered to be further reliable than the Mahalanobis distance[4], as the Mahalanobis distance is a particular case of the Bhattacharyya distance when the standard deviations of the two classes is the same. Therefore, when two classes have the similar means but different standard deviations, the Mahalanobis distance would tend to zero, however, the Bhattacharyya distance would grow depending on the difference between the standard deviations. Formula definition: For discrete probability distributions p and q over the same domain X, it is defined as: where: (1)
is the Bhattacharyya coefficient. For continuous probability distributions, the Bhattacharyya coefficient is defined as: In either case, and . doesnt obey the triangle inequality, but the Hellinger distance does obey the triangle inequality. In its simplest formulation, the Bhattacharyya distance between two classes under the normal distribution can be calculated [2] by extracting the mean and variances of two separate distributions or classes: (2) where: is the Bhattacharyya distance between p and q distributions or classes is the variance of the p-th distribution, is the mean of the p-th distribution, and are two different distributions.
4. EFFECTIVE WORK
Face recognition: 1. In this feature extraction features like face, eyes, nose, expressions. 2. Calculation based on Eigen faces by Eigen vector , Eigen values etc. 3. Calculation based on similarity measures for similarity by applying distance measures[6] 4. Classification for differentiating between the images. 5. Image processing concepts like discrete wavelet transform, etc. 6. Applying filters & image processing techniques. 7. Face recognition result of faces used for security, authentication.
Figure 1 Face recognition processing
Page 217

In this process of face recognition we perform many process and get result .In this we take our own images and then apply the eigen calculation in this eigen vector,eigen values ,eigen faces calculations [7]are done then similarity matching by using distance measure calculation like manhattan distance etc.then classification for differentiating between the images and wavelet transform and filters like gausian filters[6] and other image processing techniques like shadow removal brightness, contrast etc and then finally we recognize the faces. This process can be done reverse and in any order we get results of face recognition.
5. RESULTS
Comparison of various image processing face recognition concepts. Input image of a mean image for all face recognition using image processing concepts.
Figure 2 Input Mean images for Face recognition processing FaceRecognition using Eigenfaces. Utilizes the two dimensional global grayscale images representing distinctive characteristics
Figure 3 Face recognition processing using Eigen faces Face recognition using gaussian filters
Figure 4 Face recognition processing using Gaussian Filter In above image processing concepts of face recognition eigenfaces is the best for face recognition with good results.
REFERENCES
[1] X. Tang and X. Wang, Face Sketch Recognition, IEEE Trans. Circuits and Systems for Video Technology, vol. 14, no. 1, pp. 50-57, Jan. 2004.
Page 218

[2] L. Juwei, K. Plataniotis, and A. Venetsanopoulos, Face Recognition Using Kernel Direct Discriminant Analysis Algorithms, IEEE Trans. Neural Networks, vol. 14, no. 1, pp. 117-126, Jan. 2003. [3] K.I. Kim, K. Jung, and H.J. Kim, Face Recognition Using Kernel Principal Component Analysis, IEEE Signal Processing Letters, vol. 9, no. 2, pp. 40-42, Feb. 2002. [4] http://www.wikipedia.com [5] Y. Hu, A.S. Mian, and R. Owens, Sparse Approximated Nearest Points for Image Set Classification, Proc. IEEE Intl Conf. Computer Vision and Pattern Recognition, 2011. [6] J. Weng, C.H. Evans, and W.S. Hwang, An Incremental Learning Method for Face Recognition under Continuous Video Stream,Proc. IEEE Intl Conf. Automatic Face and Gesture Recognition, pp. 251-256, 2000. [7] X. Li, K. Fukui, and N. Zheng, Image-Set Based Face Recognition Using Boosted Global and Local Principal Angles, Proc. AsianConf. Computer Vision, pp. 323-332, 2009. [8] Digital Image Processing Second Edition Rafael C. Gonzalez University of Tennessee, Prentice Hall Upper Saddle River, New Jersey 07458. [9] Image Processing and Pattern Recognition: Fundamentals and Techniques,Frank Y. Shih,wiley.
AUTHOR PROFILES
K.Ganapathi Babu, pursuing M.Tech in Computer Science Engineering at Vignan's LARA Institute Of Technology and Science, Vadlamudi, Guntur Dist., A.P., India. His research interest includes Image Processing, Pattern Recognition and Network Security. M.A.Rama Prasad, Asst.Prof, Department of CSE, Vignan's LARA Institute Of Technology & Science, Vadlamudi Guntur Dist., A.P., India. His research interest includes Network Security, Mobile Computing and Image Processing.
Page 219

An Effective Approach in Face Recognition Using Image Processing Concepts

Uploaded by

Copyright:

Available Formats

An Effective Approach in Face Recognition Using Image Processing Concepts

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

An Effective Approach in Face Recognition Using Image Processing Concepts

Uploaded by

Copyright:

Available Formats

International Journal of Application or Innovation in Engineering & Management (IJAIEM)