No abstract

Segmentation is the art of partitioning an image into different regions where each one has some degree of uniformity in its feature space. A number of methods have been proposed and blind segmentation is one of them. It uses intrinsic image features, such as pixel intensity, color components and texture. However, some virtues, like poor contrast, noise and occlusion, can weaken the procedure. To overcome them, prior knowledge of the object of interest has to be incorporated in a top-down procedure for segmentation. Consequently, in this work, a novel integrated algorithm is proposed combining bottom-up (blind) and top-down (including shape prior) techniques. First, a color space transformation is performed. Then, an energy function (based on nonlinear diffusion of color components and directional derivatives) is defined. Next, signeddistance functions are generated from different shapes of the object of interest. Finally, a variational framework (based on the level set) is employed to minimize the energy function. The experimental results demonstrate a good performance of the proposed method compared with others and show its robustness in the presence of noise and occlusion. The proposed algorithm is applicable in outdoor and medical image segmentation and also in optical character recognition (OCR).

No abstract

The aim of this paper is to investigate the performance of time delay neural networks (TDNNs) and the probabilistic neural networks (PNNs) trained with nonlinear features (Lyapunov exponents and Entropy) on electroencephalogram signals (EEG) in a specific pathological state. For this purpose, two types of EEG signals (normal and partial epilepsy) are analyzed. To evaluate the performance of the classifiers, mean square error (MSE) and elapsed time of each classifier are examined. The results show that TDNN with 12 neurons in hidden layer result in a lower MSE with the training time of about 19.69 second. According to the results, when the sigma values are lower than 0.56, the best performance in the proposed probabilistic neural network structure is achieved. The results of present study show that applying the nonlinear features to train these networks can serve as useful tool in classifying of the EEG signals

Face recognition systems perform accurately in a controlled environment, but an unconstrained environment dramatically degrades their performance. In this study, a novel pose‐invariant face recognition system is proposed based on the occlusion free regions. This method utilises a gallery set of frontal face images and can handle large pose variations. For a 2D probe face image with an arbitrary pose, the head pose is first obtained using a robust head pose estimation method. Then, this 2D face image is normalised by a novel 3D modelling method from a single input image. In consequence, pose invariant face recognition is converted to a frontal face recognition problem. The 3D structure is reconstructed using a new method based on the estimated head pose and only one facial feature point, which is significantly reduced in comparison with the number of landmarks used in previous methods. According to the estimated poses, occlusion free regions are extracted from normalised images as feature extraction. Finally, face matching and recognition is performed using these regions from normalised test images and the corresponding regions of gallery images. Experimental results on FERET and CAS‐PEAL‐R1 databases demonstrate that the proposed method outperforms other methods, and it is robust and efficient.