6533b7d0fe1ef96bd125a22a
RESEARCH PRODUCT
A Mlp-Based Digit And Uppercase Characters Recognition System
E. MaxtireG. VassalloG. A. M. GioielloFilippo Sorbellosubject
ScannerArtificial neural networkComputer sciencebusiness.industrySpeech recognitionNumerical digitComputingMethodologies_PATTERNRECOGNITIONSoftwareSimple (abstract algebra)Computer Science::Computer Vision and Pattern RecognitionMultilayer perceptronConjugate gradient methodLogical matrixbusinessdescription
A simple software solution for digit and uppercase handwritten characters recognition is presented. The proposed solution is based on a two-layer Multi Layer Perceptron (MLP) trained by a conjugate gradient descent (CGD) optimization algorithm. This neural network is embedded in a software tool for automatic processing of forms achieved using a scanner. The chosen solutions allow us to obtain good results both in terms of recognition rate and speed. In the paper are fully described design details and experimental results.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 1997-01-01 |