José Josemar de Oliveira

Learn More
This paper evaluates NN and HMM classifiers applied to the handwritten word recognition problem. The goal is analyse the individual and combined performance of these classifiers. They are evaluated considering two different combination strategies and the experiments are performed with the same database and similar feature sets. The strategy proposed takes(More)
We present a methodology to analyze Multiple Classifiers Systems (MCS) performance, using the disagreement concept. The goal is to define an alternative approach to the conventional recognition rate criterion, which usually requires an exhaustive combination search. This approach defines a Distance-based Disagreement (DbD) measure using an Euclidean(More)
This work presents a baseline system used to evaluate feature sets for word recognition. The main goal is to determine an optimum feature set to represent the handwritten names for the months of the year in Brazilian Portuguese language. Three kinds of features are evaluated: perceptual , directional and topological. The evaluation shows that taken in(More)
— We present a methodology to analyze Multiple Classifiers Systems (MCS) performance, using the diversity concept. The goal is to define an alternative approach to the conventional recognition rate criterion, which usually requires an exhaustive combination search. This approach defines a Distance-based Disagreement (DbD) measure using an Euclidean distance(More)
This paper presents a multiple classifier system applied to the handwritten word recognition (HWR) problem. The goal is to analyse the influence of different global classi-fiers taken isolatedly as well as combined in a particular HWR task. The application proposed is the recognition of the Portuguese handwritten names of the months. The strategy takes(More)
This paper brings a contribution to the problem of efficiently recognizing handwritten words from a limited size lexicon. For that, a multiple classifier system has been developed that analyzes the words from three different approximation levels, in order to get a computational approach inspired on the human reading process. For each approximation level a(More)
  • 1