Training convolutional neural networks (CNNs) on large sets of high-resolution images is too computationally intense to be performed on commodity CPUs. Such architectures however ...
In recent years, the recognition of Farsi and Arabic handwriting is drawing increasing attention. This paper describes the result of the ICDAR 2009 competition for handwritten Far...
To reduce the classification errors of online handwritten Japanese character recognition, we propose a method for confusing characters discrimination with little additional costs....
— This paper describes a Markov random field (MRF) model with weighting parameters optimized by conditional random field (CRF) for on-line recognition of handwritten Japanese cha...
Abstract. To generalize the Fisher Discriminant Analysis (FDA) algorithm to the case of discriminant functions belonging to a nonlinear, finite dimensional function space F (Nonli...