Narrow Results

Along with the development of the motion capture (mocap) technique, large-scale 3D motion databases have become increasingly available. In this paper, a novel approach is presented for motion retrieval based on double-reference index (DRI). Due to the high dimensionality of motion's features, Isomap nonlinear dimension reduction is used. In addition, an algorithmic framework is employed to approximate the optimal mapping function by a Radial Basis Function (RBF) in handling new data. Subsequently, a DRI is built based on selecting a small set of representative motion clips in the database. Thus, the candidate set is obtained by discarding the most unrelated motion clips to significantly reduce the number of costly similarity measures. Finally, experimental results show that these approaches are effective for motion data retrieval in large-scale databases.

In practical applications, recognition accuracy is sometimes not the only criterion; capability to reject erroneous patterns might also be needed. We show that there is a trade-off between these two properties. An efficient solution to this trade-off is brought about by the use of different algorithms implemented in various modules, i.e. multi-modular architectures.

We present a general mechanism for designing and training multi-modular architectures, integrating various neural networks into a unique pattern recognition system, which is globally trained. It is possible to realize, within the system, feature extraction and recognition in successive modules which are cooperatively trained. We discuss various rejection criteria for neural networks and multi-modular architectures.

We then give two examples of such systems, study their rejection capabilities and show how to use them for segmentation. In handwritten optical character recognition, our system achieves performances at state-of-the-art level, but is eight times faster. In human face recognition, our system is intended to work in the real world.

This paper proposes an intelligent classification technique to identify two categories of MRI volume data as normal and abnormal. The manual interpretation of MRI slices based on visual examination by radiologist/physician may lead to incorrect diagnosis when a large number of MRIs are analyzed. In this work, the textural features are extracted from the MR data of patients and these features are used to classify a patient as belonging to normal (healthy brain) or abnormal (tumor brain). The categorization is obtained using various classifiers such as support vector machine (SVM), radial basis function, multilayer perceptron and k-nearest neighbor. The performance of these classifiers are analyzed and a quantitative indication of how better the SVM performance is when compared with other classifiers is presented. In intelligent computer aided health care system, the proposed classification system using SVM classifier can be used to assist the physician for accurate diagnosis.

In practical applications, recognition accuracy is sometimes not the only criterion; capability to reject erroneous patterns might also be needed. We show that there is a trade-off between these two properties. An efficient solution to this trade-off is brought about by the use of different algorithms implemented in various modules, i.e. multi-modular architectures.

We present a general mechanism for designing and training multi-modular architectures, integrating various neural networks into a unique pattern recognition system, which is globally trained. It is possible to realize, within the system, feature extraction and recognition in successive modules which are cooperatively trained. We discuss various rejection criteria for neural networks and multi-modular architectures.

We then give two examples of such systems, study their rejection capabilities and show how to use them for segmentation. In handwritten optical character recognition, our system achieves performances at state-of-the-art level, but is eight times faster. In human face recognition, our system is intended to work in the real world.

First the paper explains why fuzzy inference system can be regarded as just another interesting grey-box way of approximating non-linear mapping. Then it contributes at clarifying the current confusion raised by a lot of works comparing or merging neural nets with fuzzy inference systems. Practical comparisons with RBF are performed which show that the small structural addition leading to fuzzy systems can be of interest for function identification. To face the curse of dimensionality problem, the paper presents an algorithm developed in a biological spirit and dedicated to the on-line incremental building of fuzzy systems for function approximation. It is called EFUSS (Evolving Fuzzy Systems Structure) and aims at automatically and incrementally finding the minimal number of membership functions along with their appropriate shaping. Its main characteristics are that the structural additions occur at a lower time scale than the parametric changes. They are guided by the endogenous dynamics of the parametric learning and aim at compensating for the weakest parts of the systems.