Attribute filters allow enhancement and extraction of features without distorting their borders, and never introduce new image features. These are highly desirable properties in bi...
There is a plethora of established and proposed document representation formats but none that can adequately support individual stages within an entire sequence of document image ...
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...
We are interested in diacritizing Semitic languages, especially Syriac, using only diacritized texts. Previous methods have required the use of tools such as part-of-speech tagger...
Manual reconstruction of ripped-up documents can be a very difficult and time-consuming task. This paper discusses a semi-automatic toolset that can be used for reconstructing rip...