Sharif Digital Repository

This paper proposes an enhanced illumination compensation algorithm, which can compensate for the uneven illuminations on human faces and reconstruct face images in normal lighting conditions. To detect the illumination category, based on 65 categories in YaleB database, the images processed using Block-based Histogram Equalization (BHE) is compared with the original face image processed using histogram equalization (HE). Based on the identified illumination category, a quadratic model is used to reconstruct an image that will visually be under normal illumination. In order to avoid the effect of light source intensity on face images, we used HE method. Experimental results show that, by... 

Recently many works focus on the vehicle type recognition because it is important in security and authentication systems. Computational complexity and low recognition rate especially when the system has to recognize among a large number of vehicles, are two major problems in vehicle type recognition. In recent years wavelet and contourlet transform have been applied in the recognition tasks successfully. In this paper we proposed a method for recognizing vehicle type in different lighting conditions. We used wavelet and contourlet as tools for feature extraction. These features are powerful and robust to illumination and scale variation. We reduced the dimension of feature vector by resizing... 

This paper illustrates the use of a combined neural network model for classification of electrocardiogram (ECG) beats. We present a trainable neural network ensemble approach to develop customized electrocardiogram beat classifier in an effort to further improve the performance of ECG processing and to offer individualized health care. We process a three stage technique for detection of premature ventricular contraction (PVC) from normal beats and other heart diseases. This method includes a denoising, a feature extraction and a classification. At first we investigate the application of stationary wavelet transform (SWT) for noise reduction of the electrocardiogram (ECG) signals. Then... 

We propose an efficient and effective nonlinear feature domain noise suppression algorithm, motivated by the minimum mean square error (MMSE) optimization criterion. Multi Layer Perceptron (MLP) neural network in the log spectral domain minimizes the difference between noisy and clean speech. By using this method as a pre-processing stage of a speech recognition system, the recognition rate in noisy environments is improved. We can extend the application of the system to different environments with different noises without re-training it. We need only to train the preprocessing stage with a small portion ofnoisy data which is created by artificially adding different types of noises from the... 

In this paper, we have proposed an efficient and effective nonlinear feature domain noise suppression algorithm, motivated by the minimum mean square error (MMSE) optimization criterion. A Multi Layer Perceptron (MLP) neural network in the log spectral domain has been employed to minimize the difference between noisy and clean speech. By using this method, as a pre-processing stage of a speech recognition system, the recognition rate in noisy environments has been improved. We extended the application ofthe system to different environments with different noises without retraining HMMmodel. We trained the feature extraction stage with a small portion of noisy data which was created by... 

The variation of pose, illumination, and expression continues to make face recognition a challenging problem. As a pre-processing step in holistic approaches, faces are usually aligned by eyes. The proposed method tries to perform a pixel alignment rather than eye alignment by mapping the geometry of faces to a reference face while keeping their own textures. The proposed geometry alignment not only creates a meaningful correspondence among every pixel of all faces, but also removes expression and pose variations effectively. The geometry alignment is performed pixel-wise, i.e., every pixel of the face is corresponded to a pixel of the reference face. In the proposed method, the information... 

This paper introduces a novel robotic platform, called RASA (Robot Assistant for Social Aims). This educational social robot is designed and constructed to facilitate teaching Persian Sign Language (PSL) to children with hearing disabilities. There are three predominant characteristics from which design guidelines of the robot are generated. First, the robot is designed as a fully functional interactive social robot with children as its social service recipients. Second, it comes with the ability to perform PSL, which demands a dexterous upper-body of 29 actuated degrees of freedom. Third, it has a relatively low development cost for a robot in its category. This funded project, addresses... 

Automatic speech recognition performance degrades significantly when speech is affected by environmental noise. Nowadays, the major challenge is to achieve good robustness in adverse noisy conditions so that automatic speech recognizers can be used in real situations. Spectral subtraction (SS) is a well-known and effective approach; it was originally designed for improving the quality of speech signal judged by human listeners. SS techniques usually improve the quality and intelligibility of speech signal while speech recognition systems need compensation techniques to reduce mismatch between noisy speech features and clean trained acoustic model. Nevertheless, correlation can be expected... 

This paper introduces a novel robotic platform, called RASA (Robot Assistant for Social Aims). This educational social robot is designed and constructed to facilitate teaching Persian Sign Language (PSL) to children with hearing disabilities. There are three predominant characteristics from which design guidelines of the robot are generated. First, the robot is designed as a fully functional interactive social robot with children as its social service recipients. Second, it comes with the ability to perform PSL, which demands a dexterous upper-body of 29 actuated degrees of freedom. Third, it has a relatively low development cost for a robot in its category. This funded project, addresses... 

Spectral Subtraction (SS), as a speech enhancement technique, originally designed for improving quality of speech signal judged by human listeners. it usually improve the quality and intelligibility of speech signals, while the speech recognition systems need compensation techniques capable of reducing the mismatch between the noisy speech features and the clean models. This paper proposes a novel approach for solving this problem by considering the SS and the speech recognizer as two interconnected components, sharing the common goal of improved speech recognition accuracy. The experimental evaluations on a real recorded database and the TIMIT database show that the proposed method can...