Free Boundary Conditions Active Contours with Applications for Vision

Abstract

Abstract. Active contours are used extensively in vision for more than two decades, primarily for applications such as image segmentation and object detection. The vast majority of active contours models make use of closed curves and the few that employ open curves rely on either fixed boundary conditions or no boundary conditions at all. In this paper we discuss a new class of open active contours with free boundary conditions, in which the end points of the open active curve are restricted to lie on two parametric boundary curves. We discuss how this class of curves may assist and facilitate various vision applications and we demonstrate its utility in applications such as boundary detection, feature tracking, and seam carving.

Grain-oriented segmentation of scanning electron microscope images

“…Mile's [21] and Bernard's [22] methods identified unexpected regions unrelated to the manual input. Other methods [19,20] didn't detect the grain edges very accurately, but made them too small as too large. Shemesh's [19] technique produced the best results among ACM-based methods.…”

“…Other methods [19,20] didn't detect the grain edges very accurately, but made them too small as too large. Shemesh's [19] technique produced the best results among ACM-based methods. Still, our technique found the grain boundary more accurately and ran faster than the other methods.…”

An evolutionary spline fitting algorithm for identifying filamentous cyanobacteria

“…Open active contours (also called snakes) are capable of identifying curvilinear image features [13,11] after suitable smoothing and initialization. Snakes are splines that attempt to match image features through iterative deformations.…”

Grain‐oriented segmentation of images of porous structures using ray casting and curvature energy minimization

“…ACM uses a simple parametric representation of the contour with internal and external energy terms, and can be extended to cope with noisy images (Kass et al, 1988. In addition, ACM can delineate an object outline by attempting to minimize energy related to the contour as a summation of the internal and external energy. A new open ACM with free boundary conditions has improved several computer-vision applications by simplifying the initialization procedure and providing a natural framework for subpixel computation (Shemesh & Ben-Shahar, 2011). The open ACM assumes that a curve to extract outline is not closed.…”