Median radial basis function neural network,” (1996)

by A G Bors, I Pitas
Venue:IEEE Trans. Neural Networks,
Add To MetaCart
Results 11 - 20 of 34

Face Recognition With RadialBasis Function (RBF) Neural Networks

by Joo Meng , Member, IEEE Shiqian Er , Member, IEEE Juwei Wu , Student Member, IEEE Hock Lye Lu , Member, IEEE Toh - Neural Network , 2002
"... Abstract-A general and efficient design approach using a radial basis function (RBF) neural classifier to cope with small training sets of high dimension, which is a problem frequently encountered in face recognition, is presented in this paper. In order to avoid overfitting and reduce the computat ..."
Abstract - Cited by 4 (0 self) - Add to MetaCart
Abstract-A general and efficient design approach using a radial basis function (RBF) neural classifier to cope with small training sets of high dimension, which is a problem frequently encountered in face recognition, is presented in this paper. In order to avoid overfitting and reduce the computational burden, face features are first extracted by the principal component analysis (PCA) method. Then, the resulting features are further processed by the Fisher's linear discriminant (FLD) technique to acquire lower-dimensional discriminant patterns. A novel paradigm is proposed whereby data information is encapsulated in determining the structure and initial parameters of the RBF neural classifier before learning takes place. A hybrid learning algorithm is used to train the RBF neural networks so that the dimension of the search space is drastically reduced in the gradient paradigm. Simulation results conducted on the ORL database show that the system achieves excellent performance both in terms of error rates of classification and learning efficiency. Index Terms-Face recognition, Fisher's linear discriminant, ORL database, principal component analysis, radial basis function (RBF) neural networks, small training sets of high dimension.
(Show Context)

Digital Image Processing In Painting Restoration And Archiving

by N. Nikolaidis, I. Pitas - in Proceedings of the IEEE International Conference on Image Processing (ICIP , 2001
"... Digital image processing and analysis can be an important tool for the restoration of works of art. This paper presents three applications of image processing in this field: a method for digital crack restoration of paintings, a technique for color restoration of old paintings and a method for mosai ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
Digital image processing and analysis can be an important tool for the restoration of works of art. This paper presents three applications of image processing in this field: a method for digital crack restoration of paintings, a technique for color restoration of old paintings and a method for mosaicing of partial images of works of art painted on curved surfaces. A digital archiving system for works of arts is also described. 1.
(Show Context)

Object Segmentation in 3-D Images Based on Alpha-Trimmed Mean Radial Basis Function Network

by Adrian G. Bors, Ioannis Pitas
"... This paper presents a new approach for 3-D object segmentation. Objects from a stack of images are represented as overlapping ellipsoids. Graylevel statistics and shape features are simultaneously employed for object modeling in an unsupervised approach. The extension of the Hough Transform in the 3 ..."
Abstract - Cited by 3 (3 self) - Add to MetaCart
This paper presents a new approach for 3-D object segmentation. Objects from a stack of images are represented as overlapping ellipsoids. Graylevel statistics and shape features are simultaneously employed for object modeling in an unsupervised approach. The extension of the Hough Transform in the 3-D space is used for finding the ellipsoid centers. Each ellipsoid is modeled by a Radial Basis Function (RBF) and the entire structure is represented by means of an RBF network. The proposed algorithm is applied for blood vessel segmentation from tooth pulp in a stack of microscopy images.

Object Segmentation and Modeling in Volumetric Images

by Adrian G. Bors, Ioannis Pitas , 1998
"... We propose a pattern classification based approach for simultaneous 3-D object modeling and segmentation in image volumes. The 3-D objects are described as a set of overlapping ellipsoids. The segmentation relies on the geometrical model and graylevel statistics. The extension of the Hough Transform ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
We propose a pattern classification based approach for simultaneous 3-D object modeling and segmentation in image volumes. The 3-D objects are described as a set of overlapping ellipsoids. The segmentation relies on the geometrical model and graylevel statistics. The extension of the Hough Transform algorithm in the 3-D space by employing the spherical coordinate system is used for ellipsoidal center estimation. The characteristic parameters of the ellipsoids and of the graylevel statistics are embedded in a Radial Basis Function (RBF) network and they are found by means of unsupervised training. We propose a new robust training algorithm for RBF networks based on o-Trimmed Mean statistics. The proposed algorithm is applied for tooth pulpal blood vessel segmentation in a stack of microscopy images.

Alpha-Trimmed Mean Radial Basis Functions And Their Application In Object Modeling

by Adrian G. Bors, Ioannis Pitas, Adrian G. Bor��s Ioannis Pitas - CD-ROM Proc of the IEEE Workshop on Nonlinear Signal and Image Processing (NSIP'97 , 1997
"... In this paper we use Radial Basis Function (RBF) networks for object modeling in images. An object is composed from a set of overlapping ellipsoids and has assigned an output unit in the RBF network. Each basis function can be geometrically represented by an ellipsoid. We introduce a new robust stat ..."
Abstract - Cited by 2 (2 self) - Add to MetaCart
In this paper we use Radial Basis Function (RBF) networks for object modeling in images. An object is composed from a set of overlapping ellipsoids and has assigned an output unit in the RBF network. Each basis function can be geometrically represented by an ellipsoid. We introduce a new robust statistics based algorithm for training radial basis function networks. This algorithm relies on ff-trimmed mean statistics. The use of the proposed algorithm in estimating ellipse parameters is analyzed. 1. INTRODUCTION Radial basis function neural network consists of a two layer feed-forward structure employed for functional approximation and classification proposes. When used in pattern classification an RBF network successfully approximates the Bayesian classifier [1, 2]. In this case, the underlying probability functions are decomposed in a sum of kernel functions with localized support. The functions, implemented by the hidden units, are usually chosen as Gaussian. The intersection of an...

Robust And Adaptive Techniques In Self-Organizing Neural Networks

by I. Pitas, C. Kotropoulos, N. Nikolaidis, A.G. Bors , 1998
"... this paper, we shall describe robust and adaptive training algorithms that have been developed the past three years and aim at enhancing the capabilities of the self-organizing and the RBF neural networks [3]-[12] ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
this paper, we shall describe robust and adaptive training algorithms that have been developed the past three years and aim at enhancing the capabilities of the self-organizing and the RBF neural networks [3]-[12]

Theoretical Interpretations And Applications Of Radial Basis Function Networks

by Enrica Blanzieri, Enrico Blanzieri , 2003
"... Medical applications usually used Radial Basis Function Networks just as Artificial Neural Networks. However, RBFNs are Knowledge-Based Networks that can be interpreted in several way: Artificial Neural Networks, Regularization Networks, Support Vector Machines, Wavelet Networks, Fuzzy Controllers, ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
Medical applications usually used Radial Basis Function Networks just as Artificial Neural Networks. However, RBFNs are Knowledge-Based Networks that can be interpreted in several way: Artificial Neural Networks, Regularization Networks, Support Vector Machines, Wavelet Networks, Fuzzy Controllers, Kernel Estimators, Instanced-Based Learners. A survey of their interpretations and of their corresponding learning algorithms is provided as well as a brief survey on dynamic learning algorithms. RBFNs' interpretations can suggest applications that are particularly interesting in medical domains.
(Show Context)

Moving scene segmentation using Median Radial Basis Function Network

by Adrian G. Bors, Ioannis Pitas , 1997
"... Various approaches were suggested for simultaneous optical flow estimation and segmentation in image sequences. In this study, the moving scene is decomposed in different regions with respect to their motion, by means of a pattern recognition scheme. The inputs of the proposed scheme are the feature ..."
Abstract - Cited by 2 (1 self) - Add to MetaCart
Various approaches were suggested for simultaneous optical flow estimation and segmentation in image sequences. In this study, the moving scene is decomposed in different regions with respect to their motion, by means of a pattern recognition scheme. The inputs of the proposed scheme are the feature vectors representing still image and motion information. The classifier employed is the Median Radial Basis Function (MRBF) neural network. Each class corresponds to a moving object. An error criterion function derived from the probability estimation theory and related to the moving scene model is used as cost function. Marginal median and median of the absolute deviations estimators are employed for estimating the basis function parameters.

Facial expression recognition using shape and texture information

by I Kotsia , I Pitas - IFIP International Federation for Information Processing, 2006, Volume 217, Artificial Intelligence in Theory and Practice
"... Summary. A novel method based on shape and texture information is proposed in this paper for facial expression recognition from video sequences. The Discriminant Non-negative Matrix Factorization (DNMF) algorithm is applied at the image corresponding to the greatest intensity of the facial expressi ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
Summary. A novel method based on shape and texture information is proposed in this paper for facial expression recognition from video sequences. The Discriminant Non-negative Matrix Factorization (DNMF) algorithm is applied at the image corresponding to the greatest intensity of the facial expression (last frame of the video sequence), extracting that way the texture information. A Support Vector Machines (SVMs) system is used for the classification of the shape information derived from tracking the Candide grid over the video sequence. The shape information consists of the differences of the node coordinates between the first (neutral) and last (fully expressed facial expression) video frame. Subsequently, fusion of texture and shape information obtained is performed using Radial Basis Function (RBF) Neural Networks (NNs). The accuracy achieved is equal to 98,2% when recognizing the six basic facial expressions.
(Show Context)

A Differential Evolution Based Incremental Training Method for RBF Networks

by Junhong Liu, Jouni Lampinen
"... The Differential Evolution (DE) is a floating-point encoded evolutionary strategy for global optimization. It has been demonstrated to be an efficient, effective, and robust optimization method, especially for problems containing continuous variables. This paper concerns applying a DE-based algorith ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
The Differential Evolution (DE) is a floating-point encoded evolutionary strategy for global optimization. It has been demonstrated to be an efficient, effective, and robust optimization method, especially for problems containing continuous variables. This paper concerns applying a DE-based algorithm to training Radial Basis Function (RBF) networks with variables including centres, weights, and widths of RBFs. The proposed algorithm consists of three steps: the first step is the initial tuning, which focuses on searching for the center, weight, and width of a one-node RBF network, the second step is the local tuning, which optimizes the three variables of the one-node RBF network — its centre, weight, and width, and the third step is the global tuning, which optimizes all the parameters of the whole network together. The second step and the third step both use the cycling scheme to find the parameters of RBF network. The Mean Square Error from the desired to actual outputs is applied as the objective function to be minimized. Training the networks is demonstrated by approximating a set of functions, using different strategies of DE. A comparison of the net performances with several approaches reported in the literature is given and shows the resulting network performs better in the tested functions. The results show that proposed method improves the compared approximation results.
(Show Context)