9 results
Now showing1 - 9 of 9
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Real time lip motion analysis for a person authentication system using near infrared illuminationIn this paper we present an approach for lip motion analysis that can be used in conjunction with a person authentication system based on face recognition, to avoid attacks on the system using passive photographs. This work focuses on robustly tracking lips in gray scale images, which may be captured the visible light or near infrared spectrum. We present an approach for locating the two lip corners in a face image. Then we extract suitable features from the mouth region to classify mouth states (visemes). The system shows a classification accuracy of above 85%. The temporal changes in the detected viseme classes can be used for detecting the imposter.Publicationtype: Conference Paper35 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , 22 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , 25 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , An experimental framework for lip reading(w.e.b. Universitätsverlag und Buchhandel, 2003); ; Publicationtype: Conference Paper18 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , A system for automatic lip readingIn this paper, we present our approach of face and lip detection, lip modeling, and tracking. A new lip model based on Bézier Curves is used to capture the dynamics of the lips effi- ciently. The model is defined only through few points which are modeled using the Active Shape Model (ASM). Accurate detection of lip details is implemented using multiple independent feature templates. The method detects tracks and model the lips online and robustly. The results of the lip detection are presented based on our collected data for German language. We also describe also some of the current and future work on audio video integration.Publicationtype: Conference Paper26 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Viseme recognition using multiple feature matchingIn this paper, we present a technique for the extraction of the five main visemes produced in natural speech for German. The method belongs to the LDA (Linear Discriminant Analysis) family. The intensity, the edges, and the line segments are used to locate the lips automatically and for viseme classification. Using many features in the recognition maximizes the probability of recognition rate. The corners of the mouth are used in case of small rotation and scale. An experiment has been carried out on different people, to understand the part of the speech that the human being use. The people grouped the phonemes into five different visemes. The number of distinguished visemes is not the same for each speaker. Everyone express the speech in a different visemes. Good recognition rate has been achieved on different speaker.Publicationtype: Conference Paper29 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Recognition of the German visemes using multiple feature matchingIn this paper, we present a technique for the extraction of the main five visemes for German spoken language analysis from images. The intensity, the edges, and the line segments are used to locate the lips automatically, and to discriminate between the desired viseme classes. Good recognition rate has been achieved on different speakers.Publicationtype: Conference Paper41 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Pencil Mouse: real-time estimation of 6-D pose, position, and motion parameters from a monocular views using a fast line searchThe Pencil Mouse is a six degrees of freedom input device that uses only a monocular camera. A camera egomotion detection algorithm based on a checker-pattern planar surface and its implementation are described. We have developed a precise and fast method for line search depending on line candidate generation. This method enables the real-time features extraction and parameter estimation of the Pencil Mouse, where the estimated parameters were accurate. On a 266 MHz Pentium II system up to 28 frame per second are evaluated. Mesurements are given.Publicationtype: Conference Paper41 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , On-line rank order filtering, median filtering, and data sorting architecture'sPublicationtype: Conference Paper24