Whole-book recognition is a document image analysis strategy that operates on the complete set of a book’s page images, attempting to improve accuracy by automatic unsupervised ...
The word error rate of any optical character recognition system (OCR) is usually substantially below its component or character error rate. This is especially true of Indic langua...
Venkat Rasagna, Anand Kumar 0002, C. V. Jawahar, R...
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fea...
Abdel-rahman Mohamed, Tara N. Sainath, George Dahl...
This paper describes the derivation of probability of correctness from scores assigned by most recognizers. Motivation for this research is three-fold: i probability values can be...
Djamel Bouchaffra, Venu Govindaraju, Sargur N. Sri...
We define a rewrite strategy for a class of non-confluent constructor-based term graph rewriting systems and discuss its correctness. Our strategy and its extension to narrowing...