Contour Detection from Deep Patch-level Boundary Prediction

TL;DR

This paper introduces a multi-scale CNN framework for contour detection that effectively captures both fine and large-scale contours, enhanced by a guided filtering refinement, demonstrating strong results on benchmark datasets.

Contribution

The paper proposes a novel multi-scale CNN approach for contour detection using patch-level features and a guided filtering method for map refinement.

Findings

Effective detection of large-scale contours

Good performance on benchmark datasets

Capable of detecting fine-scale contours

Abstract

In this paper, we present a novel approach for contour detection with Convolutional Neural Networks. A multi-scale CNN learning framework is designed to automatically learn the most relevant features for contour patch detection. Our method uses patch-level measurements to create contour maps with overlapping patches. We show the proposed CNN is able to to detect large-scale contours in an image efficienly. We further propose a guided filtering method to refine the contour maps produced from large-scale contours. Experimental results on the major contour benchmark databases demonstrate the effectiveness of the proposed technique. We show our method can achieve good detection of both fine-scale and large-scale contours.