Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: perceptual grouping

Sortuj według:

Ogranicz wyniki do:

Modulation masking for recurrent low-noise noise masker

Kutzner D.J.

Archives of Acoustics

2006

Vol. 31, No. 4

543-549

The main purpose of these investigations was to examine modulation masking phenomenon for recurrent low-noise noise masker. Such masker is characterized by three parameters, namely: repetition frequency, frep, centre frequency, fo, and bandwidth, b. The parameter frep is not reflected in the signal power spectrum and is related to the autocorrelation period. The parameters fo and b describe spectral properties of the interfering signal, i.e. localization and concentration of its power in the frequency domain. In order to separate possible effects of the masker temporal repetition and its spectral parameters, modulation masking measurements were carried out for fo=64 Hz, b=16 Hz and frep=1 s-1 (without repetition), 4 s-1 and 8 s-1 and probe signal of frequencies fp=1, 2, 4, 6, 8, 12, 16, 32, 52 and 64 Hz. The masker rms modulation depth was 30%; carrier signal was a 4-kHz sinusoid. The main conclusion is that modulation masking patterns are determined by the spectral properties of the masker.

A feature-based approach for segmenting faces

Zaqout I., Zainuddin R., Baba S.

Machine Graphics and Vision

2004

Vol. 13, No. 3

249-259

Human face detection has always been an important problem for face, expression and gesture recognition. Though numerous attempts have been made to detect and localize faces, these approaches have made assumptions that restrict their extension to more general cases. We identify that the key factor in a generic and robust system is that of using a large amount of image evidence, related and reinforced by model knowledge through a probabilistic framework. In this paper, we propose a feature-based algorithm for segmenting faces that is sufficiently generic and is also easily extensible to cope with more demanding variations of the imaging conditions. The algorithm detects feature points from the image and groups them into face candidates using geometric and grey level constraints. Preliminary results are provided to support the validity of the approach and demonstrate its capability to segment faces under different scales, orientations and viewpoints.