FPGA Based LIRA Neural Classifier

Author

Vega, Alejandro ; Baidyk, Tatiana ; Kussul, Ernst ; Silva, José Luis Pérez

Author_Institution

Center of Appl. Sci. & Technol. Dev., Nat. Autonomous Univ. of Mexico (UNAM), Mexico City, Mexico

fYear

2011

fDate

15-18 Nov. 2011

Firstpage

65

Lastpage

70

Abstract

Neural networks can be used for image classification. They are powerful instruments in image and pattern recognition because they have following advantages: parallel structure, training in the process of the classifier preparation, and possibility to implement them as an electronic circuit. A special type of neural classifier, LIRA (Limited Receptive Area) neural classifier, has been developed and used to solve different tasks, for example, handwritten digit recognition, face recognition, texture and shape recognition, etc. It is important to reduce the time of system work so the neural classifier was implemented in a FPGA device.

Keywords

face recognition; field programmable gate arrays; handwriting recognition; image classification; image texture; neural nets; shape recognition; FPGA; LIRA neural classifier; classifier preparation; electronic circuit; face recognition; handwritten digit recognition; image classification; image recognition; limited receptive area; neural networks; parallel structure; pattern recognition; shape recognition; texture recognition; Biological neural networks; Face recognition; Field programmable gate arrays; Handwriting recognition; Image recognition; Neurons; Random access memory; LIRA neural classifier; logic circuits; neural networks; neuron;

fLanguage

English

Publisher

ieee

Conference_Titel

Electronics, Robotics and Automotive Mechanics Conference (CERMA), 2011 IEEE

Conference_Location

Cuernavaca, Morelos

Print_ISBN

978-1-4577-1879-3

Type

conf

DOI

10.1109/CERMA.2011.18

Filename

6125800