1 AUTOMATIC REGISTRATION OF CEREBRAL VASCULAR STRUCTURES , Marwa HERMASSI, Hejer JELASSI, Kamel HAMROUNI
In this paper we present a registration method for cerebral vascular structures in the 2D MRA images. The method is based on bifurcation structures. The usual registration methods, based on point matching, largely depend on the branching angels of each bifurcation point. This may cause multiple feature correspondence due to similar branching angels. Hence, bifurcation structures offer better registration. Each bifurcation structure is composed of a master bifurcation point and its three connected neighbors. The characteristic vector of each bifurcation structure consists of the normalized branching angle and length, and it is invariant against translation, rotation, scaling, and even modest distortion. The validation of the registration accuracy is particularly important. Virtual and physical images may provide the gold standard for validation. Also, image databases may in the future provide a source for the objective comparison of different vascular registration methods.
2 CONNECTIONIST PROBABILITY ESTIMATORS IN HMM USING GENETIC CLUSTERING APPLICATION FOR SPEECH RECOGNITION AND MEDICAL DIAGNOSIS, Lilia Lazli, Boukadoum Mounir, Abdennasser Chebira, Kurosh Madani, Mohamed Tayeb Laskri
The main goal of this paper is to compare the performance which can be achieved by five different approaches analyzing their applications’ potentiality on real world paradigms. We compare the performance obtained with (1) Multi-network RBF/LVQ structure (2) Discrete Hidden Markov Models (HMM) (3) Hybrid HMM/MLP system using a Multi Layer- Perceptron (MLP) to estimate the HMM emission probabilities and using the Kmeans algorithm for pattern clustering (4) Hybrid HMM-MLP system using the Fuzzy C-Means (FCM) algorithm for fuzzy pattern clustering and (5) Hybrid HMM-MLP system using the Genetic Algorithm (AG) for genetic clustering. Experimental results on Arabic speech vocabulary and biomedical signals show significant decreases in error rates of hybrid HMM/MLP/AG pattern recognition in comparison to those of other research experiments by integrating three types of features (PLP, log-RASTA PLP, JRASTA PLP) were used to test the robustness of our hybrid recognizer in the presence of convolution and additive noise.