In this paper we present a simple novel approach to tackle the challenges of scaling and rotation of face images in face recognition. The proposed approach registers the training and testing visual face images by log-polar transformation, which is capable to handle complicacies introduced by scaling and rotation. Log-polar images are projected into eigenspace and finally classified using an imp...

The accuracy of face recognition is very important for its security in many applications, because wrong face recognition may cause such security problems as authorization. To increase the recognition rate in such face database as ORL, a face recognition algorithm should be good at minimizing the disturbances of facial pose, illumination and expression (PIE) to this recognition. In this paper, t...

In this paper we propose a novel face recognition algorithm based on orientation histogram of Hough Transform Peaks. The novelty of the approach lies in utilizing Hough Transform peaks for determining the orientation angles and computing the histogram from it. For extraction of feature vectors first the images are divided into non overlapping blocks of equal size. Then for each of the blocks th...

M. Gelardi1, N. de CaNdia1, N. QuaraNta1, C. russo2, P. PeCoraro3, M. MaNCiNi4, P. luPerto5, G. loMbardo6, a. MaCChi7, C. boCCioliNi8, a. Ciofalo9, e. de Corso10, G. CiPraNdi11 1 section of otolaryngology, department of basic Medical science, Neuroscience and sensory organs, university of bari, italy; 2 u.o.C. of otolaryngology, ospedale di Venere, Carbonara di bari (ba), italy; 3 orl-asp 6Pale...

A new face recognition system is introduced and analyzed in this paper. The system utilizes a novel statistical pattern recognition method to optimize the feature selection process. The optimized feature set feeds a classification module, which is based on the modified ν-support vector machine approach (ν-SVM). The optimized feature set reduces the burden of the subsequent ν-SVM classifier and ...

This paper presents the experimental evaluation of Gabor filter and Zernike moments for extracting the face features. The dimensionality of the input image is reduced for the overloading process of Gabor filters. 40 sub-images were obtained from the original images by using the Gabor filters in 5 scales and 8 orientations. From each sub-image, four Zernike features were extracted. Thus, the tot...

Face recognition become one of the most important and fastest growing area during the last several years and become the most successful application of image analysis and broadly used in security system. It has been a challenging, interesting, and fast growing area in real time applications. The propose method is tested using a benchmark ORL database that contains 400 images of 40 persons. Pre-P...

As a latest multiresolution analysis method, curvelet transform has improved directional elements with anisotropy and better ability to represent sparsely edges and other singularities along curves. To reduce the dimensionality of facial image and improve the recognition rate, a face recognition system based on curvelet transform and Least Square Support Vector Machine (LS-SVM) has been develop...

Combining the feature sets that are invariant to global as well as to local variations of face images would be an efficient approach to construct an optimal face recognition system. Thus, identification and combination of complementary feature sets has become an active topic of research in recent days. In this paper, a combination of two useful methods, i.e. Zernike Moments (ZMs) and Scale Inva...