Artificial Neural Networks for Preprocessing and Recognizing Handwritten Text
Place: Large lecture Room
Affiliation: Univ. Politècnica de València, Spain
In this talk, we will describe the work of our team on how ANNs are used in preprocessing and recognizing handwritten text. In particular:
- The use of hybrid Hidden Markov Model (HMM)/Artificial Neural Network (ANN) models for recognizing unconstrained offline handwritten texts, on a word basis or character basis. The structural part of the optical models has been modeled with Markov chains, and a Multilayer Perceptron is used to estimate the emission probabilities.
- The use of new techniques to remove slope and slant from handwritten text and to normalize the size of text images with ANNs. Slope correction and size normalization are achieved by classifying local extrema of text contours with Multilayer Perceptrons. Slant is also removed in a nonuniform way by using Artificial Neural Networks.
We will show experiments on the offline handwritten text lines from the IAM database (word and character results), and the recognition rates achieved, in comparison to the ones reported in the literature, and in conjuntion with other methods.