Tahani Bouchrika

Neural solutions to interact with computers by hand gesture recognition

This paper attempts to present a vision-based interface which interacts with computers by hand gesture recognition. This work aims at creating a natural and intuitive application employing both static and dynamic hand gestures. The proposed application can be summarized in three main steps: hands detection in a video, hands tracking and converting hand shapes or trajectories into computer commands. To accomplish this application, a classification phase is paramount whether at the part of hand detection, or at the phase of “commanding computers”. For this reason, we have proposed to use a wavelet network classifier (WNC) learnt by fast wavelet transform (FWT). To emphasize the robustness of this classifier, we have used a neural network classifier (NNC) version in order to compare the two classifiers’ performances aiming at proving the strength of our proposed one. Global rates given by experimental results show the effectiveness of our proposed approaches of hand detection, hand tracking and hand gesture recognition. The comparison of the two classifier’s result helps to choose the best classifier, which can improve the performances of our application.

Ordering computers by hand gestures recognition based on wavelet networks

The automatic interpretation of gestures based on computer vision offers new possibilities to interact with machines. These interactions are more natural and more intuitive than those with classical devices. In this paper, we are interested in using our hands as pointing devices to remotely ordering computers. The proposed application can be summarized in three main steps: hands detection in a video, tracking of detected hands and converting hands shapes or trajectories into computer orders. To achieve this application a classification phase is paramount whether at the part of hands detection, or at the phase of ordering computer. For this reason, we have employed a wavelet network classifier (WNC) based on fast wavelet transform (FWT) for its robustness and for its pertinent results in the classifications domain. Experiments show that our employed methods are effective for real-time hands detection, hands tracking and hands gestures recognition.

A New Hand Posture Recognizer Based on Hybrid Wavelet Network Including a Fuzzy Decision Support System

In this paper we present a novel hand posture recognizer based on wavelet network learnt by fast wavelet transform (FWN) including a fuzzy decision support system (FDSS). Our contribution in this paper resides in proposing a new classification way for the FWN classifier. The FWN having an hybrid architecture (using as activation functions both wavelet and scaling ones) provides hybrid weight vectors when approximating an image. The FWN classification phase was achieved by computing simple distances between test and training weight vectors. Those latter are composed of two types of coefficients that are not in the same value range which may influence on the distances computing. This can cause wrong recognitions. So, to overcome this lacuna, a new classification strategy is proposed. It operates a human reasoning mode employing a FDSS to calculate similarity degrees between test and training images. Comparisons with other works are presented and discussed. Obtained results have shown that the new hand posture recognizer performs better than previously established ones. …

Cascaded hybrid Wavelet Network for hand gestures recognition

This paper presents a new cascaded hybrid Wavelet Network Classifier (CHWNC) designed for hand gesture recognition in real time applications. This paper contains two key contributions. The first is the amelioration of our previous works in the classification domain employing wavelet networks (WN). Precisely, by ameliorating the training way of the latest wavelet network classifier (WNC) version by representing each training class by one WN instead of creating a WN for each training image. This contribution makes very rapid the test phase by reducing the number of comparisons between test images WNs and training WNs. The second contribution is the proposition of a new wavelet network architecture including the cascade notion which decomposes the WN on a set of stages. The new architecture has as aim not only to make recognitions robust and rapid but also to reject as fast as possible gestures which must not be considered by the system (spontaneous gestures). Experiments, based on a well known hand posture dataset, show that our method is very robust and rapid compared to already existing ones.

A new supervised image classifier architecture based on multiresolution wavelet network including a fuzzy decision support system

The problem of image classification remains to be a major challenge to the computer vision community. In this paper, we propose a new classifier architecture based on multiresolution wavelet network learnt by fast wavelet transform including a fuzzy decision support system (FWN-FDSS). The proposed classifier has many advantages compared to other ones. It is characterized by its new method of computing similarity distances and his way of decision-making which operates a human reasoning mode. Comparisons with other classifiers are presented and discussed. Obtained results have shown that the new classifier performs better than previously established ones.

CSWN: A Cascaded Architecture of Separator Wavelet Networks for Image Classification

Image classification is an important task within the field of computer vision. In this paper we propose a new wavelet network classifier (WNC) based on the cascaded architecture. This classifier is characterized by its new learning approach and its novel architecture which brings a novel robust test way. So, our contributions in this paper reside in two major points. The first one is the proposition of a new training algorithm which overcomes lacuna detected in the latest version of WN learning approach. Hence, our new approach creates separator WNs discriminating classes (n -- 1 WNs to classify n classes) instead of creating a WN for each training image. This contribution makes very rapid the classification process by reducing the number of comparisons between test images WNs and training WNs. The second contribution is the proposition of a novel architecture which brings a new test approach radically different to those employed in ancient WN versions. By the new architecture which is based on the cascade notion, we aim at reducing the number of kernels employed in the approximation of test images. Experiments, using well known benchmarks, show that our new classifier is very robust and rapid compared to already existing ones.

Hand posture recognizer based on separator wavelet networks

This paper presents a novel hand posture recognizer based on separator wavelet networks (SWNs). Aiming at creating a robust and rapid hand posture recognizer, we have contributed by proposing a new training algorithm for the wavelet network classifier based on fast wavelet transform (FWN). So, the contribution resides in reducing the number of WNs modeling training data. To make that, inspiring from the adaboost feature selection method, we thought to create SWNs (n-1 WNs for n classes) instead of modeling each training sample by its wavelet network (WN). By proposing the new training algorithm, the recognition phase will be positively influenced. It will be more rapid thanks to the reduction of the number of comparisons between test images WNs and training WNs. Comparisons with other works, employing universal hand posture datasets are presented and discussed. Obtained results have shown that the new hand posture recognizer is comparable to previously established ones.

Supervised wavelet-network based fuzzy-logic classifier performance on the UCI databases

Supervised machine learning is an important field with many immediate applications. As a result, there is an increasing number of public tools with a diversity of learning approaches. In this paper we propose a new architecture of wavelet network classifier learnt by a fast wavelet transform (FWN). This classifier is well suited for data classification and has many advantages compared to other ones. We have contributed by proposing a new classification way. It is characterized by its novel technique for processing data similarity distances, with involvement of a fuzzy decision support system (FDSS) in decision-making, which operates a human reasoning mode. The empirical results demonstrate that the proposed system outperforms the other ones, published in the literature, in terms of global classification rates on different well known datasets.

Arabic sign language recognition system based on wavelet networks

Developing an automatic arabic sign language recognition system is of great importance, it can be used as a communication means between hearing-impaired and other people.

Model based and model free methods for features extraction to recognize gait using fast wavelet network classifier

Human gait is an attractive modality for recognizing people at a distance. Gait recognition systems aims to identify people by studying their manner of walking. In this paper, we contribute by the creation of a new approach for gait recognition based on fast wavelet network (FWN) classifier. To guaranty the effectiveness of our gait recognizer, we have employed both static and dynamic gait characteristics. So, to extract the static features (dimension of the body part), model based method was employed. Thus, for the dynamic features (silhouette appearance and motion), model free method was used. The combination of these two methods aims at strengthens the WN classification results. Experimental results employing universal datasets show that our new gait recognizer performs better than already established ones.