We present a comprehensive review of the Hough transform, HT, in image processing and
computer vision. It has long been recognized as a technique of almost unique promise for …

In supervised learning, a training set providing previously known information is used to
classify new instances. Commonly, several instances are stored in the training set but some of …

Synapses enable neurons to communicate with each other and are therefore a prerequisite
for normal brain function. Presynaptically, this communication requires energy and …

… For given P(gli) and Pi there exists a grey level 3 for which grey levels g satisfy (for
example Devijver and Kittler 16)) … In summary, instead of determining ¢ indirectly as in …

We develop a common theoretical framework for combining classifiers which use distinct
pattern representations and show that many existing schemes can be considered as special …

… = 1, 2, ..., D) to form set Xk with the corresponding criterion function J(Xk). In addition, the
values of J(Xi) for all preceding subsets of size i= 1, 2, ..., k-1, are known and stored. …

In this paper we describe the acquisition and content of a large multi-modal database intended
for training and testing of multi-modal veri cation systems. The XM2VTSDB database o …

A new enhancement of ransac, the locally optimized ransac (lo-ransac), is introduced. It has
been observed that, to find an optimal solution (with a given probability), the number of …

A variety of circle detection methods which are based on variations of the Hough Transform
are investigated. The five methods considered are the standard Hough Transform, the Fast …

The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking
activity organized by the VOT initiative. Results of over eighty trackers are presented; many are …