Combinational neural network using Gabor filters for the classification of handwritten digits

09/18/2017
by   N. Joshi, et al.
0

A classification algorithm that combines the components of k-nearest neighbours and multilayer neural networks has been designed and tested. With this method the computational time required for training the dataset has been reduced substancially. Gabor filters were used for the feature extraction to ensure a better performance. This algorithm is tested with MNIST dataset and it will be integrated as a module in the object recognition software which is currently under development.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/13/2020

Handwritten Character Recognition Using Unique Feature Extraction Technique

One of the most arduous and captivating domains under image processing i...
research
02/19/2015

Unsupervised Network Pretraining via Encoding Human Design

Over the years, computer vision researchers have spent an immense amount...
research
12/25/2014

Joint Deep Learning for Car Detection

Traditional object recognition approaches apply feature extraction, part...
research
02/01/2011

High-Performance Neural Networks for Visual Object Classification

We present a fast, fully parameterizable GPU implementation of Convoluti...
research
05/17/2012

Neural Networks for Handwritten English Alphabet Recognition

This paper demonstrates the use of neural networks for developing a syst...
research
07/15/2022

Local Approximations, Real Interpolation and Machine Learning

We suggest a novel classification algorithm that is based on local appro...
research
04/06/2020

Large-scale spatiotemporal photonic reservoir computer for image classification

We propose a scalable photonic architecture for implementation of feedfo...

Please sign up or login with your details

Forgot password? Click here to reset