Contour Integration using Graph-Cut and Non-Classical Receptive Field

TL;DR

This paper introduces a novel graph-based method inspired by visual cortex mechanisms to improve binary contour detection from soft edge segment outputs, considering connectivity, smoothness, and length for better accuracy.

Contribution

It presents a new graph-cut based approach that integrates biological insights to enhance contour detection beyond traditional thresholding methods.

Findings

Improves binary contour maps by considering connectivity and smoothness.

Outperforms existing methods in qualitative and quantitative tests.

Effectively suppresses texture noise in contour detection.

Abstract

Many edge and contour detection algorithms give a soft-value as an output and the final binary map is commonly obtained by applying an optimal threshold. In this paper, we propose a novel method to detect image contours from the extracted edge segments of other algorithms. Our method is based on an undirected graphical model with the edge segments set as the vertices. The proposed energy functions are inspired by the surround modulation in the primary visual cortex that help suppressing texture noise. Our algorithm can improve extracting the binary map, because it considers other important factors such as connectivity, smoothness, and length of the contour beside the soft-values. Our quantitative and qualitative experimental results show the efficacy of the proposed method.