Tiago Candeias

Learn More
Mahalanobis distance has already proved its strength in human skin detection using a set of skin values. We present this work that uses automatic skin detection after an initial camera calibration. The calibration is done by human sampling from test individuals. A scaling is performed on the work data, before applying the Mahalanobis distance that ensures(More)
We propose a new type of skin segmentation in color images especially developed for applications that require low resources. In our recent [7] work we made use of the Mahalanobis distance that proved its value in human skin segmentation. The calculation of the mentioned distance is very computational demanding. This is often a drawback to an implementation(More)
In this paper we present an approach for diatom classification on the basis of contour information. First an initial feature set is analysed. Then we present a method to reduce this initial feature space while preserving its discriminative power. Both results based on the initial feature space and the reduced one are compared and the classification method(More)
  • 1