Evaluation and Selection of Biases in Machine Learning
Machine Learning - Special issue on bias evaluation and selection
Feature Selection: Evaluation, Application, and Small Sample Performance
IEEE Transactions on Pattern Analysis and Machine Intelligence
Wrappers for feature subset selection
Artificial Intelligence - Special issue on relevance
Feature Subset Selection Using Genetic Algorithms for Handwritten Digit Recognition
SIBGRAPI '01 Proceedings of the 14th Brazilian Symposium on Computer Graphics and Image Processing
Integration of Contextual Information in Online Handwriting Representation
ICIAP '09 Proceedings of the 15th International Conference on Image Analysis and Processing
| Hi-index | 0.00 |
An automatic recognition of online handwrittentext has been an on-going research problem fornearly four decades. It has been gaining moreinterest due to the increasing popularity of hand-heldcomputers, digital notebooks and advanced cellularphones. However for these input modalities to beeconomical and user friendly the recognition rateshould be very high for real time use. Also, the largenumber of writing styles and the variability betweenthem makes the handwriting recognition problem avery challenging area for researchers. Manyresearchers have proposed a number of noveltechniques for online handwriting recognition.However, an acceptable classification rate has notbeen achieved yet and there is a lack of techniques,which can find appropriate features, architecture andnetwork parameters for online handwritingrecognition. In this paper we propose a novel neuro-genetictechnique to improve classification accuracythrough the selection of appropriate features andnetwork parameters for online handwritingrecognition. The technique incorporates anevolutionary approach for finding the mostsignificant features, network architecture and itsparameters.