Analysis of neural networks for face recognition systems with feature extraction to develop an eye localization based method

Rizk, Mohamed R. M.; Taha, Amtul Mohimin

doi:10.1109/icecs.2002.1046380

Cited by 7 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of methods, simple filtering techniques, morphology operations and heuristics have become popular [22][23][24]. Other approaches adapt the idea of Eigenface to the eye localization problem (Eigeneye) [25][26][27], or are based on horizontal and vertical projections of the edge image [28], on wavelet decompositions [29], on discrete cosine transformed mean-subtracted face images [30] or on applying neural networks on colour images [31]. In [32] the authors argue that the point on the nose between the eyes is easier to find than the eyes themselves, and therefore derive the eye positions based on the detection of this point.…”

Section: Previous Work On Eye Localizationmentioning

confidence: 99%

Eye localization in low and standard definition content with application to face matching

Kroon

Maas

Boughorbel

et al. 2009

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Section: Previous Work On Eye Localizationmentioning

confidence: 99%

Eye localization in low and standard definition content with application to face matching

Kroon

Maas

Boughorbel

et al. 2009

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…As a special study of pattern recognition, face recognition has proved to be very useful in daily life such as for security access control systems, content-based indexing, and bank teller machines [1][2][3][4][5]. Generally, there are two kinds of approaches to face recognition, namely, feature-based and template matching (holistic approaches).…”

Section: Introductionmentioning

confidence: 99%

An empirical study using combination of SVM with PSO based scattering ratio optimization and K-means

Azami

Bozorgtabar

2012

2012 2nd International eConference on Computer and Knowledge Engineering (ICCKE)

View full text Add to dashboard Cite

One of the most significant practical challenges for face recognition is a likeness of faces which leads to a big problem in classification of different classes. To tackle this problem, we present a novel method based on similarity of each face with other faces using the Pearson correlation coefficients. Besides, another problem is variability in lighting intensity which its physics are difficult for accurate model. In this paper, first, discrete wavelet transform (DWT) is used for feature extraction. Next, with respect to the correlation matrix, two algorithms are employed, namely, K-means clustering and particle swarm optimization (PS O) based scattering ratio matrix of correlation features. Then for each cluster, the process of classification is continued by normalization of the each subset firstly and then the decision making for each subset is performed by support vector machine (S VM). The experiments are performed on the ORL and Yale databases and the results show that there are a significant improvement in 45 features based weighted recognition rate.

show abstract

“…A method that can verify or indentify a person from a digital image is named face recognition. As a special study of pattern recognition, face recognition has proved to be very useful in daily life such as for security access control systems, content-based indexing, and bank teller machines [1][2][3][4][5]. Generally, there are two kinds of approaches to face recognition, namely, feature-based and template matching (holistic approaches).…”

Section: Introductionmentioning

confidence: 99%

A New Neural Network Approach For Face Recognition Based On Conjugate Gradient Algorithms And Principal Component Analysis

Azami¹,

Malekzadeh²,

Sanei³

2013

J. Math. Computer Sci.

View full text Add to dashboard Cite

This paper presents a new approach based on conjugate gradient algorithms (CGAs) and principal component analysis (PCA) for face recognition. First, images are decomposed into a set of time-frequency coefficients using discrete wavelet transform (DWT). Basic back propagation (BP) is a well established technique in training a neural network. However, since in this algorithm the steepest descent direction is not the quickest convergence, it is slow for many practical problems and in many cases including face recognition, its performance is not satisfactory. To overcome this problem, four algorithms, namely, Fletcher-Reeves CGA, Polak-Ribikre CGA, Powell-Beale CGA, and scaled CGA have been proposed. Also, in this paper the PCA as a preprocessing step to create the uncorrelated and distinct features of the DWT of images is used. The simulation results show that all of the proposed methods, compared with the basic BP, have greater accuracies.

show abstract

Analysis of neural networks for face recognition systems with feature extraction to develop an eye localization based method

Cited by 7 publications

References 7 publications

Eye localization in low and standard definition content with application to face matching

Eye localization in low and standard definition content with application to face matching

An empirical study using combination of SVM with PSO based scattering ratio optimization and K-means

A New Neural Network Approach For Face Recognition Based On Conjugate Gradient Algorithms And Principal Component Analysis

Contact Info

Product

Resources

About