We present a method to label an audio-visual database and to setup a system for audio-visual speech recognition based on a hybrid Artificial Neural Network/Hidden Markov Model (ANN/HMM) approach. The multi-stage labeling process is presented on a new audiovisual database recorded at the Institute de la Communication Parlée (ICP). The database was generated via transposition of the audio databas...

The paper describes a new pictorial database oriented to image analysis, implemented inside the MIDAS data analysis system. Pictorial databases need expressive data structures in order to represent a wide class of information from the numerical to the visual. The model of the database is relational; however, a full normalization is not achievable, owing to the complexity of the visual informati...

This report describes work on 3D content generation performed under the Austrian 3D-ConTourNet participation project Hyperion3D. We review key processing steps such as disparity computation, inter-camera mapping and virtual view synthesis, and give information on a publicly available database for evaluating 3D visual discomfort. Keywords—trifocal camera; 3D film; stereo matching; view synthesis...

This paper describes the development of a system for automatic television broadcast news processing, transcription and indexing. The main task of our system is automatic transcription of television broadcast programs from audio signal. The transcribed recordings are indexed and saved to the database, therefore as the second task we have created the web-system for searching in the database. It i...

Citation: Mohr J, Seyfarth J, Lueschow A, Weber JE, Wichmann FA and Obermayer K (2016) BOiS—Berlin Object in Scene Database: Controlled Photographic Images for Visual Search Experiments with Quantified Contextual Priors. Front. Psychol. 7:749. doi: 10.3389/fpsyg.2016.00749 BOiS—Berlin Object in Scene Database: Controlled Photographic Images for Visual Search Experiments with Quantified Contextu...

Image information systems, particularly in the medical field, require methods for defining and entering the geometric entities and their properties into the database system. As the geometric entities can be defined in different ways, where definitions can also be implicit, traditional databases and their associated schemes do not apply. In this contribution we argue why object-oriented systems ...

Biometrics means the automated methods of identifying a person and verify the identity of a person based on physiological or behavioural characteristics. Visual cryptography divide the original image into different shares but any of the share does not give any clue about the original image. As biometric template are stored in the centralized database. Asymmetric digital watermarking is provide ...

Border ownership is a problem of identifying which visual region the borders of a visual image belong. It has valuable and essential information for visual systems. Existing computational approaches either use artificial or limited type and number of images. In this study, we propose a new comprehensive database, which contains border ownership information from the edges and segments of 500 ind...

Poor attention of drivers towards driving can cause accidents that can harm the driver or surrounding people. The poor attention is not only caused by the drowsiness of the driver but also due to the various emotions/moods (for example sad, angry, joy, pleasure, despair and irritation) of the driver. The emotions are generally measured by analyzing either head movement patterns or eyelid moveme...

This work aims to understand and model the inter-modal temporal relations between the audio and visual modalities of speech and validate whether the captured relations can improve the performance of audio-visual bimodal modeling for such applications as audio-visual speaker identification. We propose to extend our audio-visual correlative model (AVCM) with explicit durational modeling of the pa...