Image analysis using modified multifractal measure based on sigmoid function

In this paper we propose the new multifractal measure inspired by sigmoid activation function usually used in neural networks. By using new measure the Hölder exponent and multifractal spectrum are determined in classical way. New measure is applied to image processing, especially in texture classi...

Full description

Saved in:
Bibliographic Details
Main Authors: Paskas, M. P., Gavrovska, A. M., Milivojevic, M. S., Reljin, B. D.
Format: Conference Proceeding
Language:English
Subjects:
Educational institutions
Electrical engineering
Fractals
Hölder exponent
Image analysis
Multifractal measure
multifractal spectrum
Neurons
sigmoid function
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we propose the new multifractal measure inspired by sigmoid activation function usually used in neural networks. By using new measure the Hölder exponent and multifractal spectrum are determined in classical way. New measure is applied to image processing, especially in texture classification. It was shown that by changing the slope of the sigmoid function different details can be extracted from analyzed image. Initial results are promising and indicate to high potential of new measure in image processing.
DOI:10.1109/NEUREL.2012.6420007