Delineation of line patterns in images using B-COSFIRE filters

TL;DR

This paper introduces trainable B-COSFIRE filters inspired by visual cortex neurons for detecting line patterns in diverse images, demonstrating robustness and effectiveness across medical and aerial datasets.

Contribution

The paper presents a novel trainable filter model based on V1 neurons, capable of automatically configuring to detect various line structures in images.

Findings

Effective delineation of line patterns in medical and aerial images.

Robustness confirmed across different datasets.

Automatic configuration enhances adaptability.

Abstract

Delineation of line patterns in images is a basic step required in various applications such as blood vessel detection in medical images, segmentation of rivers or roads in aerial images, detection of cracks in walls or pavements, etc. In this paper we present trainable B-COSFIRE filters, which are a model of some neurons in area V1 of the primary visual cortex, and apply it to the delineation of line patterns in different kinds of images. B-COSFIRE filters are trainable as their selectivity is determined in an automatic configuration process given a prototype pattern of interest. They are configurable to detect any preferred line structure (e.g. segments, corners, cross-overs, etc.), so usable for automatic data representation learning. We carried out experiments on two data sets, namely a line-network data set from INRIA and a data set of retinal fundus images named IOSTAR. The results that we achieved confirm the robustness of the proposed approach and its effectiveness in the delineation of line structures in different kinds of images.