Dilated filters for edge detection algorithms

TL;DR

This paper explores the use of dilated filters in edge detection algorithms, demonstrating that dilation improves performance across various methods by leveraging the benefits of dilated convolution techniques.

Contribution

It introduces the idea of replacing classical filters with dilated filters in edge detection algorithms and provides experimental evidence of improved results.

Findings

Dilation of filters enhances edge detection accuracy.

Dilated filters outperform classical filters in experiments.

Positive impact observed across simple and complex algorithms.

Abstract

Edges are a basic and fundamental feature in image processing, that are used directly or indirectly in huge amount of applications. Inspired by the expansion of image resolution and processing power dilated convolution techniques appeared. Dilated convolution have impressive results in machine learning, we discuss here the idea of dilating the standard filters which are used in edge detection algorithms. In this work we try to put together all our previous and current results by using instead of the classical convolution filters a dilated one. We compare the results of the edge detection algorithms using the proposed dilation filters with original filters or custom variants. Experimental results confirm our statement that dilation of filters have positive impact for edge detection algorithms form simple to rather complex algorithms.