Cortical-Inspired Open-Bigram Representation for Handwritten Word Recognition

Théodore Bluche, Christopher Kermorvant, Claude Touzet, Hervé Glotin

Abstract:

Recent research in the cognitive process of reading hypothesized that we do
not read words by sequentially recognizing letters, but rather by identifing
open-bigrams, i.e. couple of letters that are not necessarily next
to each other.
In this paper, we evaluate an handwritten word recognition method based on original
open-bigrams representation. We trained Long Short-Term Memory Recurrent Neural Networks
(LSTM-RNNs) to predict open-bigrams rather than characters, and we show that
such models are able to learn the long-range, complicated and intertwined dependencies
in the input signal, necessary to the prediction.
For decoding, we decomposed each word of a large vocabulary into the set of
constituent bigrams, and apply a simple cosine similarity measure between this
representation and the bagged RNN prediction to retrieve the vocabulary word.
We compare this method to standard word recognition techniques based on
sequential character recognition.
Experiments are carried out on two public databases of handwritten words
(Rimes and IAM), an the results with our bigram decoder are comparable
to more conventional decoding methods based on sequences of letters.

TL;DR: We propose an handwritten word recognition method based on an open-bigram representation of words, inspired from the research in cognitive psychology

Conflicts: a2ia.com, univ-amu.fr, univ-tln.fr