Image enhancement by high-order gaussian derivative filters simulating non-classical receptive fields in the human visual system

Authors:
Kuntal Ghosh;Sandip Sarkar;Kamales Bhaumik
Affiliations:
Microelectronics Division, Saha Institute of Nuclear Physics, Kolkata, India;Microelectronics Division, Saha Institute of Nuclear Physics, Kolkata, India;Microelectronics Division, Saha Institute of Nuclear Physics, Kolkata, India
Venue:
PReMI'05 Proceedings of the First international conference on Pattern Recognition and Machine Intelligence
Year:
2005

Citing 3
Cited 5

Digital Image Processing

Digital Image Processing
A Regularized Solution to Edge Detection

A Regularized Solution to Edge Detection
Ill-Posed Problems and Regularization Analysis in Early Vision

Ill-Posed Problems and Regularization Analysis in Early Vision

Rapid and brief communication: Proposing new methods in low-level vision from the Mach band illusion in retrospect

Pattern Recognition
Understanding image structure from a new multi-scale representation of higher order derivative filters

Image and Vision Computing
New vision tools from the comparative study of an "old" psychophysical and a "modern" computational model

BioADIT'06 Proceedings of the Second international conference on Biologically Inspired Approaches to Advanced Information Technology
Contour detection model with multi-scale integration based on non-classical receptive field

Neurocomputing
A retina-inspired neurocomputing circuit for image representation

IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advences in computational intelligence - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

The non-linearity exhibited by the non-classical receptive field in human visual system has been combined with the linear classical receptive field model. This enables us to construct higher order Gaussian Derivatives as a linear combination of lower order derivatives at different scales. Based on this, a new kernel which simulates non-classical receptive fields with extended disinhibitory surrounds, has been proposed. It is easy to implement and finds justification from an old psychophysical angle too. The proposed kernel has been shown to perform better than the well-known Laplacian kernel, which models the classical excitatory-inhibitory receptive fields.