—For historical documents, available transcriptions typically are inaccurate when compared with the scanned document images. Not only the position of the words and sentences are ...
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...
In this paper, we describe a new design of a recognition system for a single image of indoor scene including complex occlusions. In our system, rst, the system estimates 3D struc...
In this paper, we present a novel approach for incorporating structural information into the hidden Markov Modeling (HMM) framework for offline handwriting recognition. Traditiona...
Large archives of Ottoman documents are challenging to many historians all over the world. However, these archives remain inaccessible since manual transcription of such a huge vo...