Wyniki wyszukiwania - BazTech

1

Prediction mechanism for the face tracking algorithm

Gomółka Z., Twaróg B., Krutys P.

Przegląd Elektrotechniczny

|

2013

|

R. 89, nr 7

202--205

EN

The paper presents a modified version of the algorithm dedicated for face tracking in video stream. The detection procedure involves gradient technique and the prediction of the face coordinates by the modified adaptive Kalman filter. The proposed combination of face contour detection and coordinates extraction can be used in modern interfaces to facilitate user interaction with the computer.

PL

W pracy przedstawiono zmodyfikowaną wersję algorytmu śledzenia twarzy w strumieniu video z wykorzystaniem techniki gradientowej macierzy oraz predykcji współrzędnych twarzy poprzez zmodyfikowany adaptacyjny filtr Kalmana. Zaproponowana metoda wyodrębniania konturu i współrzędnych twarzy może znaleźć zastosowanie w nowoczesnych interfejsach ułatwiających interakcję użytkownika z komputerem.

2

Face based identification of people from a video stream

Kukharev G., Nowosielski A.

Computing, Multimedia and Intelligent Techniques

|

2005

|

Vol. 1 nr 1

99-110

EN

This paper presents an analysis of the problem of people identification based on the images of their faces received from a video stream. Considering a single scene image, the task of the identification consists of detection of faces and then the process of recognition follows. In a real-life face recognition system we have a sequence of consecutive images where the number of faces, their localizations, their sizes and orientations are unknown. Considering a video stream all those parameters listed above change with time but not significantly from frame to frame. By tracking a face in a sequence and aggregating individual results of face recognition, a much stable and reliable final recognition result may be obtained. Based on the analysis of the problem the algorithm for people identification from a video stream is developed.

3

Variations of Grey World for face tracking

Buenoposada J., Baumela L.

Image Processing & Communications

|

2001

|

Vol. 7, no 3-4

51--61

EN

This paper deals with the problem of colour constancy for real-time face tracking. We present two extensions of the Grey World (GW) algorithm in order to deal with dynamic image sequences with varying illumination intensity. The first extension consists in a new colour normalisation, the Projective Grey World Normalisation, which makes GW more robust to illumination intensity variations. The second extension, the Dynamic Grey World Algorithm, permits the use of GW with dynamic image sequences. We have conducted several experiments with these extensions and compared the results obtained with the rg- normalisation algorithm, possibly the most popular colour constancy procedure among the face tracking community.

4

Face tracking approach for the development of hand-free user interfaces

Atienza V., Valiente J.

Image Processing & Communications

|

2000

|

Vol. 6, no 3-4

47-60

EN

This paper describes a face tracking algorithm for the development of human computer interfaces. This tracking algorithm uses a 2-D vectorial model that captures the relative positions of a set of feature points and allows the implementation of a fast multiple match scheme. This process tries to find in each frame the best arrangement of the model that minimises a measure of dissimilarity - defined as a weighted sum of absolute differences between templates representing featue points and the image. The algorithm is mainly based on a smooth motion assumption and without 3D structure head models. A complete system is described, covering aspects of automatic feature point selection, tracking, detection of tracking failures and recovery from them. The system has been implemented on a low cost platform with frame rates of up to 24 fps.