In practical classification, there is often a mix of learnable and unlearnable classes and only a classifier above a minimum performance threshold can be deployed. This problem is...
We introduce a new class of image features, the Ray feature set, that consider image characteristics
at distant contour points, capturing information which is difficult to repre...
We propose a novel classification approach for automatically detecting pulmonary embolism (PE) from computedtomography-angiography images. Unlike most existing approaches that req...
Online boosting methods have recently been used successfully for tracking, background subtraction etc. Conventional online boosting algorithms emphasize on interchanging new weak ...
This paper presents a simple and efficient method of modeling synthetic vision, memory, and learning for autonomous animated characters in real-time virtual environments. The mode...