Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: Warg

Sortuj według:

Ogranicz wyniki do:

Mimicking speaker’s lip movement on a 3D head model using cosine function fitting

Lüsi I., Anbarjafari G.

Bulletin of the Polish Academy of Sciences. Technical Sciences

2017

Vol. 65, nr 5

733--739

Real-time mimicking of human facial movement on a 3D head model is a challenge which has attracted attention of many researchers. In this research work we propose a new method for enhancing the capturing of the shape of lips. We present an automatic lip movement tracking method which employs a cosine function to interpolate between extracted lip features in order to make the detection more accurate. In order to test the proposed method, mimicking lip movements of a speaker on a 3D head model is studied. Microsoft Kinect II is used in order to capture videos and both RGB and depth information are used to locate the mouth of a speaker followed by fitting a cosine function in order to track the changes of the features extracted from the lips.

Method for identification of fragments of lip prints images on the basis of the generalized hough transform

Wrobel K., Doroz R.

Journal of Medical Informatics & Technologies

2013

Vol. 22

189--193

The paper presents a new method for identification of fragments of lip print images on the basis of the Generalized Hough Transform (GHT). The effectiveness of this method was verified in practice. The maximum value obtained from the accumulator array after the Hough transform has been assumed as the measure of similarity between a lip print image and a reference object. The advantage of this method is the possibility of use in forensic science to identify persons who left lip prints at crime scenes.

Lip traces recognition based on lines pattern

Smacki Ł.

Journal of Medical Informatics & Technologies

2010

Vol. 15

53--60

This paper presents a method for automatic lip traces recognition based on lip furrows arrangement. First, lip trace is scanned and subjected to image processing and feature extraction. Then, identification is performed by comparing lip trace characteristics with a collection of comparative lip prints characteristics stored in a database. The proposed solution gives a satisfactory level of identification accuracy. After further improvement, it can be used as part of a system performing analysis of traces recovered from crime scenes.