This diploma thesis investigates appearance-based features for the person-independent vision-based recognition of continuous sign language. A large variety of methods which have been successfully used for automatic speech recognition is applied to this task. Appearance-based approaches do not rely on a segmentation of the images or on predefined models of the image content and use the image its...

For deaf and dumb people, Sign language is the only way of communication. With the help of sign language, these physical impaired people express their emotions and thoughts to other person. Since for the common person, it is difficult to understand these language therefore often these physically challenged has to keep the translator along with them to communicate with the world. Hence sign lang...

This work presents a statistical recognition approach performing large vocabulary continuous sign language recognition across different signers. Automatic sign language recognition is currently evolving from artificial lab-generated data to ’real-life’ data. To the best of our knowledge, this is the first time system design on a large data set with true focus on real-life applicability is thoro...

Road sign detection is important to a robotic vehicle that automatically drives on roads. In this paper, road signs are detected by means of rules that restrict color and shape and require signs to appear only in limited regions in an image. They are then recognized using a template matching method and tracked through a sequence of images. The method is fast and can easily be modified to includ...

We present a novel training method for recognizing traffic sign symbols. The symbol images captured by a car-mounted camera suffer from various forms of image degradation. To cope with degradations, similarly degraded images should be used as training data. Our method artificially generates such training data from original templates of traffic sign symbols. Degradation models and a GA-based alg...

In this paper we present a fast and efficient match algorithm, which consists of two key techniques: Spectral Correlation Based Feature Merge(SCBFM) and Two-Step Retrieval(TSR). SCBFM can remove the redundant information. In consequence, the resulting feature sequence has a smaller size, requiring less storage and computation. In addition, most of the tempo variation is removed; thus a much sim...

This paper addresses the identification and representation of the variations induced by style for the synthesis of realistic and convincing expressive gesture sequences. A qualitative and quantitative comparison between styled gesture sequences is performed. This comparison leads to the identification of temporal, spatial, and stuctural processes that are described in a theoritical model of sig...

We present a system for the large-scale automatic traffic signs recognition and mapping and experimentally justify design choices made for different components of the system. Our system works with more than 140 different classes of traffic signs and does not require labor-intensive labelling of a large amount of training data due to the training on synthetically generated images. We evaluated o...

This paper describes the COALA (Content-Oriented Audiovisual Library Access) project, which aims to offer a framework for the retrieval of audiovisual TV news documents. COALA’s principal design features are based on the analysis of a classical archive system: TSR (Television Suisse Romande) archive. It provides a retrieval interface allowing simple/advanced search capabilities combined with hi...