This contribution describes a font family designed to meet the requirements of typesetting mathematical documents in an Arabic presentation. Thus, not only is the text written in an Arabic alphabet-based script, but specific symbols are used and mathematical expressions also spread out from right to left. Actually, this font family consists of two components: an Arabic mathematical font and a d...

font would be used during recognition. This would reduce An algorithm is presented that identifies the predominant font in which the running text in an English language document the confusion caused by training on many fonts and would is printed. Frequent function words (such as the, of, and, a, effectively reduce the recognition problem to choosing the and to) are also recognized as part of th...

This document is an almost-verbatim conversion to LTEX and PDF of plain-text remarks distributed via e-mail to the ICERM report authors. However, to improve readability, I have dressed it up with color, live hyperlinks, and multiple fonts, and fixed my fumble-fingered typos. It is available at http://www.math.utah.edu/~beebe/icerm/ICERM-2014-NOTES.pdf. I have also given it a version number, sta...

This project explores Chinese character font classification and transformation, which are the most important two steps in reconstructing weathered Chinese characters. For font classification, SIFT is first used to capture font features, and neural network is built in Keras with almost perfect results achieved. For font transformation, a convolutional neural network is implemented in Tensorflow,...

In this paper we present some exploratory studies of emotion words basedon large annotated corpora Portuguese. Those were automaticallyannotated with emotionality, and each word was assigned one or moregroups out 26 groups. Our goal is to evaluate those groups byapplying different statistical approaches our material, namely based on (a)co-occurrence in a sentence as sign closeness meaning, (b) ...