An automatic lips detection and tracking system based on watershed segmentation and H approach is presented. For some of the lips detection systems, skin/non-skin detection is a prerequisite step to localise the face region and the lips region is then detected from the face region. In this paper, a direct lips detection technique using watershed segmentation without needing preliminary face loc...

Image segmentation is the most practical approach among all virtually automated image recognition systems. Feature extraction and recognition have numerous applications on telecommunication, weather forecasting, environment exploration and medical diagnosis. This paper deals with different image segmentation algorithms. The quality of satellite image is affected by atmosphere, temperature etc. ...

The paper address the problem of retinal image segmentation, and aims at describing a novel segmentation technique, based on the watershed algorithm, able to separate in a clear way blood vessels from background. Automatic accurate analysis and quantitative characterization of diagnostically relevant features of retinal images can help clinicians for diagnosis and follow-up of eye diseases.

In this paper we study the ability of the cooperation of Bayesian color pixel classification in extracting seeds for color watershed. Using color pixel classification alone does not extract accurately enough color regions so we suggest to use a strategy based on three steps : simplification, Bayesian classification and color watershed. Color watershed is based on an aggregation function using l...

This work addresses the problem of signal separation for 2-Dimensional spaces. Instead of resorting to statistical properties of the signals, this work treats the problem as one of image segmentation. Variants of known fuzzy classifiers are studied and compared with existing techniques, as the Unsupervised Maximum Likelihood (MLU) classifier or the watershed technique. The goal is the separatio...

At the present time, one of the best methods for semiautomatic image segmentation seems to be the approach based on the fuzzy connectedness principle. First, we identify some deficiencies of this approach and propose a way to improve it, through the introduction of competitive learning. Second, we propose a different approach, based on watersheds. We show that the competitive fuzzy connectednes...

Mathematical Morphology (MM) offers a generic theoretical framework for data processing and analysis. Nevertheless, it remains essentially used in the context of image analysis and processing, and the attempts to use MM on other kinds of data are still quite rare. We believe MM can provide relevant solutions for data analysis and processing in a far broader range of application fields. To illus...