Contour Detection from Deep Patch-level Boundary Prediction
This work addresses contour detection for computer vision applications, presenting an incremental improvement with a novel method for a known bottleneck.
The paper tackles contour detection in images by designing a multi-scale CNN framework that learns features for patch-level boundary prediction and refines results with guided filtering, achieving good detection of both fine-scale and large-scale contours on benchmark databases.
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.