Design of RBF Neural Network Using An Efficient Hybrid Learning Algorithm with Application in Human Face Recognition with Pseudo Zernike Moment

スポンサーリンク

概要

• 論文の詳細を見る

• This paper presents an efficient Hybrid Learning Algorithm (HLA) for Radial Basis Function Neural Network (RBFNN). The HLA combines the gradient method and the linear least squared method for adjusting the RBF parameters and connection weights. The number of hidden neurons and their characteristics are determined using an unsupervised clustering procedure, and are used as input parameters to the learning algorithm. We demonstrate that the HLA, while providing faster convergence in training phase, is also less sensitive to training and testing patterns. The proposed HLA in conjunction with RBFNN is used as a classifier in a face recognition system to show the usefulness of the learning algorithm. The inputs to the RBFNN are the feature vectors obtained by combining shape information and Pseudo Zernike Moment (PZM). Simulation results on the Olivetti Research Laboratory (ORL) database and comparison with other algorithms indicate that the HLA yields excellent recognition rate with less hidden neurons in human face recognition.

• 社団法人電子情報通信学会の論文
• 2003-02-01

著者

• Faez K

  Amirkabir Univ. Technol. Tehran Irn

• Faez Karim

  Electrical Engineering Department Amirkabir University Of Technology

• HADDADNIA Javad

  Electrical Engineering Department, Amirkabir University of Technology

• AHMADI Majid

  Electrical and Computer Engineering Department, University of Windsor

• MOALLEM Payman

  Electrical Engineering Department, Amirkabir University of Technology

• Ahmadi Majid

  Electrical And Computer Engineering Department University Of Windsor

• Moallem Payman

  Electrical Engineering Department Amirkabir University Of Technology

• Haddadnia Javad

  Electrical Engineering Department Amirkabir University Of Technology

• Faez Karim

  Electrical Engineering Dep. Amirkabir Univ. Of Technol.

• Moallem Payman

  Electrical Department Engineering Faculty University Of Isfahan

関連論文

• Signature Pattern Recognition Using Moments Invariant and a New Fuzzy LVQ Model
• Design of RBF Neural Network Using An Efficient Hybrid Learning Algorithm with Application in Human Face Recognition with Pseudo Zernike Moment
• Fast Edge-Based Stereo Matching Algorithms through Search Space Reduction(Regular Section)
• A New Efficient Stereo Line Segment Matching Algorithm Based on More Effective Usage of the Photometric, Geometric and Structural Information(Stereo and Multiple View Analysis,Machine Vision Applications)
• GA-Based Affine PPM Using Matrix Polar Decomposition(Pattern Discrimination and Classification,Machine Vision Applications)
• Adaptive Script-Independent Text Line Extraction
• Illumination-Robust Face Recognition from a Single Image per Person Using Matrix Polar Decomposition
• A Robust Negative Obstacle Detection Method Using Seed-Growing and Dynamic Programming for Visually-Impaired/Blind Persons

スポンサーリンク