The output of handwritten word recognizers (HWR) tends to be very noisy due to various factors. In order to compensate for this behaviour, several choices of the HWR must be initi...
We propose a domain specific model for statistical machine translation. It is wellknown that domain specific language models perform well in automatic speech recognition. We show ...
A common approach to split selection in classification trees is to search through all possible splits generated by predictor variables. A splitting criterion is then used to evalu...
This paper addresses variational supervised texture segmentation. The main contributions are twofold. First, the proposed method circumvents a major problem related to classical t...
Abstract—In this paper, we define meta-recognition, a performance prediction method for recognition algorithms, and examine the theoretical basis for its post-recognition score ...
Walter J. Scheirer, Anderson Rocha, Ross J. Michea...