Active Canny: Edge Detection and Recovery with Open Active Contour Models

TL;DR

This paper presents Active Canny, a novel edge detection and recovery method using open active contour models (snakelets) that improve edge continuity and smoothness by growing from initial edge cues, especially in noisy or broken conditions.

Contribution

It introduces a new framework combining open active contour models with gradient flow to recover and smooth edges, surpassing traditional methods like Canny in handling broken or weak edges.

Findings

Successfully recovers most broken or weak edges.

Produces smooth and continuous edge representations.

Enhances higher-level image analysis like contour segmentation.

Abstract

We introduce an edge detection and recovery framework based on open active contour models (snakelets). This is motivated by the noisy or broken edges output by standard edge detection algorithms, like Canny. The idea is to utilize the local continuity and smoothness cues provided by strong edges and grow them to recover the missing edges. This way, the strong edges are used to recover weak or missing edges by considering the local edge structures, instead of blindly linking them if gradient magnitudes are above some threshold. We initialize short snakelets on the gradient magnitudes or binary edges automatically and then deform and grow them under the influence of gradient vector flow. The output snakelets are able to recover most of the breaks or weak edges, and they provide a smooth edge representation of the image; they can also be used for higher level analysis, like contour segmentation.