Showing papers by "Mongi A. Abidi published in 2013"

Studies on the Effectiveness of Multispectral Images for Face Recognition: Comparative Studies and New Approaches

Abstract: In this paper, we investigate face recognition in unconstrained illumination conditions. A twofold contribution is proposed: First, three state of the art algorithms, namely Multiblock Local Binary Pattern (MBLBP), Histogram of Gabor Phase Patterns (HGPP) and Local Gabor Binary Pattern Histogram Sequence (LGBPHS) are challenged against the IRIS-M3 multispectral face data base to evaluate their robustness against high illumination variation. Second, we propose to enhance the Performance of the three mentioned algorithms, which has been drastically decreased because of the non-monotonic illumination variation that distinguishes the IRIS-M3 face database. Instead of the usual braod band images, we use narrow band sub spectral images selected from the visible spectrum. Selection of best spectral bands is formulated as a pursuit optimization problem wherein the vector of weights determining the importance of each visible spectral band is supposed to be sparse, and hence can be determined by minimizing its L1-norm. The results highlight further the still challenging problem of face recognition in conditions with high illumination variation, as well as the effectiveness of our sub spectral images based approach to increase the accuracy of the studied algorithms by at least 14% upon the proposed database.

A FCM and SURF Based Algorithm for Segmentation of Multispectral Face Images

Abstract: In this paper, we propose a novel clustering algorithm based on Fuzzy C-Means (FCM) and Speeded-Up Robust Feature (SURF) for multispectral image segmentation. In the experiments, color images and multispectral images from IRIS Lab data base, which consists of face images taken along the visible spectrum, have been used to illustrate the performances of the proposed algorithm and to compare its outputs with other algorithms. Results demonstrate that the proposed method outperforms other clustering methods in segmenting color images as well as multispectral images.

Integration of multispectral face recognition and multi-PTZ camera automated surveillance for security applications

Abstract: Due to increasing security concerns, a complete security system should consist of two major components, a computer-based face-recognition system and a real-time automated video surveillance system. A computerbased face-recognition system can be used in gate access control for identity authentication. In recent studies, multispectral imaging and fusion of multispectral narrow-band images in the visible spectrum have been employed and proven to enhance the recognition performance over conventional broad-band images, especially when the illumination changes. Thus, we present an automated method that specifies the optimal spectral ranges under the given illumination. Experimental results verify the consistent performance of our algorithm via the observation that an identical set of spectral band images is selected under all tested conditions. Our discovery can be practically used for a new customized sensor design associated with given illuminations for an improved face recognition performance over conventional broad-band images. In addition, once a person is authorized to enter a restricted area, we still need to continuously monitor his/her activities for the sake of security. Because pantilt-zoom (PTZ) cameras are capable of covering a panoramic area and maintaining high resolution imagery for real-time behavior understanding, researches in automated surveillance systems with multiple PTZ cameras have become increasingly important. Most existing algorithms require the prior knowledge of intrinsic parameters of the PTZ camera to infer the relative positioning and orientation among multiple PTZ cameras. To overcome this limitation, we propose a novel mapping algorithm that derives the relative positioning and orientation between two PTZ cameras based on a unified polynomial model. This reduces the dependence on the knowledge of intrinsic parameters of PTZ camera and relative positions. Experimental results demonstrate that our proposed algorithm presents substantially reduced computational complexity and improved flexibility at the cost of slightly decreased pixel accuracy as compared to Chen and Wang’s method [18].

Pixel level fusion of multispectral face images: Short review

Abstract: With the recent rapid development in the field of multispectral face imaging, the use of image fusion has emerged as a new and important research area. Many studies have attempted to improve the performance of face recognition by fusing the infrared (IR) and visible face images, yet few comparison studies have been conducted to examine which fusion method is preferable over another. In this paper, we provide an overview of the most widely used pixel level fusion algorithms, and establish a comparison to evaluate each fusion method Our experiments were validated by comparing cumulative match characteristics (CMC) of multispectral image fusion by weighted sum, principal component analysis, empirical mode decomposition, and wavelet transform.

Fundamental relationship between bilateral Kernel and locally adaptive regression Kernel

Abstract: The relationship between the bilateral kernel function and the recently proposed locally adaptive regression kernel is examined. Despite the difference in implementation, both locally adaptive approaches are designed to prevent averaging across edges while smoothing an image. Their similarity suggests that they can reasonably be linked although both filtering approaches have grown to become well-established theories in their fields. First, the locally adaptive regression kernel is analysed theoretically. Then, the connection between the methods is explored by applying the spectral distance measure to the bilateral kernel. Finally, a direct relation is established between the bilateral kernel and the locally adaptive regression kernel.

The Comparative Study between Difference Actions and Full Actions

Abstract: An appearance-based feature set is proposed. With Hidden Markov Model (HMM) handling any temporal variance, the contributions of features, which are from full foreground sequence and from temporal difference sequence, are compared in details by methods which are based on feature selecting and feature voting. The experimental analysis shows that the comparative contributions can be achieved for human action identifying by the two data sources. This introduces the opportunity to analyze human behavior based on temporal difference sequence instead of full foreground sequence, and validates the far-reaching significance of this work.