A wide variety of texture feature extraction methods have been proposed for texture based image classification and segmentation. These methods are typically evaluated over windows...
We introduce two fourth-order regularization methods that remove geometric noise without destroying significant geometric features. These methods leverage ideas from image denoisi...
We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. In particular, each component mul...
Taylor Berg-Kirkpatrick, Alexandre Bouchard-C&ocir...
: An OCR free word spotting method is developed and evaluated under a strong experimental protocol. Different feature sets are evaluated under the same experimental conditions. In ...
Israel Rios, Alceu de Souza Britto Jr., Alessandro...
We address the problem in signal classification applications, such as automatic speech recognition (ASR) systems that employ the hidden Markov model (HMM), that it is necessary to...