IMPROVED NEOCOGNITRON HANDWRITING RECOGNITION RATE BY MODIFYING THE FIRST LEVEL OF TRAINING

RAUL EDUARDO HUAROTE ZEGARRA; INDIRA ELIZABETH ROJAS ESCOBAR; VEGA LUJAN

doi:https://doi.org/10.6036/9307

PAPER SENDING SUBSCRIPTION

Search engine :

DYNA JOURNAL ENGINEERING

Skip to the menu
Skip to the content

Return to the menu

Search

Vote:

Results:

5 points

92 Votes

IMPROVED NEOCOGNITRON HANDWRITING RECOGNITION RATE BY MODIFYING THE FIRST LEVEL OF TRAINING

SEPTEMBER 2019 - Volume: 94 - Pages: 483

DOI:

https://doi.org/10.6036/9307

Authors:

RAUL EDUARDO HUAROTE ZEGARRA

- INDIRA ELIZABETH ROJAS ESCOBAR - VEGA LUJAN

Disciplines:

Computer Sciences (ARTIFICIAL INTELLIGENCE / INTELIGENCIA ARTIFICIAL )

Downloads: 15

How to cite this paper:

Download pdf

Download pdf

Key words:: Neocognitrón, Filtro Gabor, bordes orientados, reconocimiento digital de manuscrito, taza de reconocimiento, Neocognitrón, Gabor filter, oriented edges, handwitten digit recognition, recognition cup.
Article type:: NOTA TECNICA / TECHNICAL NOTE
Section:: TECHNICAL NOTE

Fukushima's neocognitron is characterized by its robustness as it is not affected by changes in position, size or distortion in input patterns and this model has a handwritten character recognition rate of 98.5%, among others as alphanumeric characters, fingerprints, geometric shapes, etc.

Share: