The Experts below are selected from a list of 237 Experts worldwide ranked by ideXlab platform

Zhengguang Xu - One of the best experts on this subject based on the ideXlab platform.

  • a new gabor phase Difference Pattern for face and ear recognition
    Computer Analysis of Images and Patterns, 2009
    Co-Authors: Guoying Zhao, Jie Chen, Matti Pietikainen, Zhengguang Xu
    Abstract:

    A new local feature based image representation method is proposed. It is derived from the local Gabor phase Difference Pattern (LGPDP). This method represents images by exploiting relationships of Gabor phase between pixel and its neighbors. There are two main contributions: 1) a novel phase Difference measure is defined; 2) new encoding rules to mirror Gabor phase Difference information are designed. Because of them, this method describes Gabor phase Difference more precisely than the conventional LGPDP. Moreover, it could discard useless information and redundancy produced near quadrant boundary, which commonly exist in LGPDP. It is shown that the proposed method brings higher discriminative ability to Gabor phase based Pattern. Experiments are conducted on the FRGC version 2.0 and USTB Ear Database to evaluate its validity and generalizability. The proposed method is also compared with several state-of-the-art approaches. It is observed that our method achieves the highest recognition rates among them.

  • CAIP - A New Gabor Phase Difference Pattern for Face and Ear Recognition
    Computer Analysis of Images and Patterns, 2009
    Co-Authors: Guoying Zhao, Jie Chen, Matti Pietikainen, Zhengguang Xu
    Abstract:

    A new local feature based image representation method is proposed. It is derived from the local Gabor phase Difference Pattern (LGPDP). This method represents images by exploiting relationships of Gabor phase between pixel and its neighbors. There are two main contributions: 1) a novel phase Difference measure is defined; 2) new encoding rules to mirror Gabor phase Difference information are designed. Because of them, this method describes Gabor phase Difference more precisely than the conventional LGPDP. Moreover, it could discard useless information and redundancy produced near quadrant boundary, which commonly exist in LGPDP. It is shown that the proposed method brings higher discriminative ability to Gabor phase based Pattern. Experiments are conducted on the FRGC version 2.0 and USTB Ear Database to evaluate its validity and generalizability. The proposed method is also compared with several state-of-the-art approaches. It is observed that our method achieves the highest recognition rates among them.

  • local gabor phase Difference Pattern for face recognition
    International Conference on Pattern Recognition, 2008
    Co-Authors: Zhengguang Xu
    Abstract:

    A new image representation method is proposed for face recognition in this paper, called local Gabor phase Difference Pattern (LGPDP). Unlike the Histogram of Gabor Phase Patterns (HGPP) that exploits the relationships of Gabor phase between neighborhood pixels, the LGPDP captures the Gabor phase Difference relationships to represent the image. In order to avoid the sensitivity of the Gabor phase to location variations, the feature encodes the discriminative information in an elaborate way. The impressive experimental results of the proposed method compared with some other state-of-art methods conducted on the FERET database and the ORL face database demonstrate its efficiency and validity.

  • ICPR - Local Gabor phase Difference Pattern for face recognition
    2008 19th International Conference on Pattern Recognition, 2008
    Co-Authors: Zhengguang Xu
    Abstract:

    A new image representation method is proposed for face recognition in this paper, called local Gabor phase Difference Pattern (LGPDP). Unlike the Histogram of Gabor Phase Patterns (HGPP) that exploits the relationships of Gabor phase between neighborhood pixels, the LGPDP captures the Gabor phase Difference relationships to represent the image. In order to avoid the sensitivity of the Gabor phase to location variations, the feature encodes the discriminative information in an elaborate way. The impressive experimental results of the proposed method compared with some other state-of-art methods conducted on the FERET database and the ORL face database demonstrate its efficiency and validity.

Andrea Massa - One of the best experts on this subject based on the ideXlab platform.

  • reconfigurable sum Difference Pattern by means of parasitic elements for forward looking monopulse radar
    Iet Radar Sonar and Navigation, 2013
    Co-Authors: Paolo Rocca, Massimo Donelli, Giacomo Oliveri, Federico Viani, Andrea Massa
    Abstract:

    This study describes the design of forward-looking monopulse arrays able to reconfigure the radiation Pattern from the sum mode to the Difference one by electronically switching a set of parasitic dipoles placed in front of a driven array of radiating dipoles. The antenna architecture is synthesised by optimising the geometric parameters of the passive elements, namely their positions and lengths. The generation of the Difference beam is yielded by imposing a phase displacement of π to the excitations of half active array and activating the parasitic array by turning-on the switches that partition their lengths. As for the sum Pattern, the effect of the parasitic dipoles is made negligible by turning-off the switches. A set of representative results is reported and discussed to show the effectiveness of the proposed approach.

  • A Design Procedure for Sum and Difference Patterns by Means of Reactive Sorting Algorithm
    2011
    Co-Authors: Luca Manica, Paolo Rocca, Davide Franceschini, Andrea Massa
    Abstract:

    A new approach for the synthesis of both sum and Difference antenna Pattern is proposed. The approach allows to obtain an optimal sum Pattern and a sub-optimal Difference Pattern through the search of a minimal cost path inside an incomplete binary tree.

  • Design of compromise sum-Difference Patterns through the iterative contiguous partition method
    Iet Microwaves Antennas & Propagation, 2009
    Co-Authors: Paolo Rocca, Luca Manica, A. Martini, Andrea Massa
    Abstract:

    In this paper, an innovative approach for the synthesis of sub-arrayed monopulse linear arrays is presented. A compromise Difference Pattern is obtained through an optimal excitations matching method based on the contiguous partition technique integrated in an iterative procedure ensuring, at the same time, the optimization of the sidelobe level (or other beam Pattern features). The flexibility of such an approach allows one to synthesize various Difference Patterns characterized by different trade-off between angular resolution and noise/interferences rejection in order to match the user-defined requirements. On the other hand, thanks to its computational efficiency, synthesis problems concerned with large arrays are easily managed, as well. An exhaustive numerical validation assesses the reliability and accuracy of the method pointing out the improvements upon state-of-the-art sub-arraying techniques. This paper is a postprint of a paper submitted to and accepted for publication in Microwaves, Antennas & Propagation and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library.

  • Optimization of the Difference Patterns for monopulse antennas by a hybrid real/integer-coded differential evolution method
    IEEE Transactions on Antennas and Propagation, 2005
    Co-Authors: Salvatore Caorsi, Andrea Massa, Matteo Pastorino, Andrea Randazzo
    Abstract:

    The optimization of Difference Patterns of monopulse antennas is considered. The synthesis problem is recast as an optimization problem by defining a suitable cost function. In particular, in this paper, the cost function is based on constraints on the side-lobe levels. A subarray configuration is adopted and the excitations of the Difference Pattern are approximately determined. The optimization problem is efficiently solved by a differential evolution algorithm, which is able to contemporarily handle real and integer unknowns. Numerical results are reported concerning classical array configurations previously considered in the literature.

  • Synthesis of sum and Difference Patterns for monopulse antennas by an hybrid real/integer-coded differential evolution method
    2003
    Co-Authors: Salvatore Caorsi, Andrea Massa, Matteo Pastorino, Andrea Randazzo
    Abstract:

    The synthesis of sum and Difference Patterns of monopulse antennas is considered in this paper. The synthesis problem is recast as an optimization problem by defining a suitable cost function based on the constraints on the side lobe levels. A subarray configuration is considered and the excitations of the Difference Pattern are approximately determined. The optimization problem is efficently solved by a differential evolution algorithm, wich is able to contemporarly handle real and integer unknowns. Numerical results are reported considering classic array configurations previusly assumed in the literature.

Jeanfu Kiang - One of the best experts on this subject based on the ideXlab platform.

  • optimization of asymmetrical Difference Pattern with memetic algorithm
    IEEE Transactions on Antennas and Propagation, 2014
    Co-Authors: Songhan Yang, Jeanfu Kiang
    Abstract:

    A memetic particle swarm optimization (MPSO) algorithm is applied to fine-tune the asymmetrical Difference Pattern of a linear array, which is useful for tracking targets, for example, in radar applications. The side-lobe level of the asymmetrical Difference Pattern with various peak Differences can be successfully reduced, while maintaining the desired squint angle and the side-lobe Difference. Conventional PSO, genetic algorithm (GA) and memetic GA (MGA) have also been applied, with the initial conditions of uniformly-excited and Bayliss linear arrays, to compare their performance of optimization.

Andrea Randazzo - One of the best experts on this subject based on the ideXlab platform.

  • Optimization of the Difference Patterns for monopulse antennas by a hybrid real/integer-coded differential evolution method
    IEEE Transactions on Antennas and Propagation, 2005
    Co-Authors: Salvatore Caorsi, Andrea Massa, Matteo Pastorino, Andrea Randazzo
    Abstract:

    The optimization of Difference Patterns of monopulse antennas is considered. The synthesis problem is recast as an optimization problem by defining a suitable cost function. In particular, in this paper, the cost function is based on constraints on the side-lobe levels. A subarray configuration is adopted and the excitations of the Difference Pattern are approximately determined. The optimization problem is efficiently solved by a differential evolution algorithm, which is able to contemporarily handle real and integer unknowns. Numerical results are reported concerning classical array configurations previously considered in the literature.

  • Synthesis of sum and Difference Patterns for monopulse antennas by an hybrid real/integer-coded differential evolution method
    2003
    Co-Authors: Salvatore Caorsi, Andrea Massa, Matteo Pastorino, Andrea Randazzo
    Abstract:

    The synthesis of sum and Difference Patterns of monopulse antennas is considered in this paper. The synthesis problem is recast as an optimization problem by defining a suitable cost function based on the constraints on the side lobe levels. A subarray configuration is considered and the excitations of the Difference Pattern are approximately determined. The optimization problem is efficently solved by a differential evolution algorithm, wich is able to contemporarly handle real and integer unknowns. Numerical results are reported considering classic array configurations previusly assumed in the literature.

Songhan Yang - One of the best experts on this subject based on the ideXlab platform.

  • optimization of asymmetrical Difference Pattern with memetic algorithm
    IEEE Transactions on Antennas and Propagation, 2014
    Co-Authors: Songhan Yang, Jeanfu Kiang
    Abstract:

    A memetic particle swarm optimization (MPSO) algorithm is applied to fine-tune the asymmetrical Difference Pattern of a linear array, which is useful for tracking targets, for example, in radar applications. The side-lobe level of the asymmetrical Difference Pattern with various peak Differences can be successfully reduced, while maintaining the desired squint angle and the side-lobe Difference. Conventional PSO, genetic algorithm (GA) and memetic GA (MGA) have also been applied, with the initial conditions of uniformly-excited and Bayliss linear arrays, to compare their performance of optimization.