| | |
Summary: VECTOR FIELD CONVOLUTION FOR IMAGE SEGMENTATION USING SNAKES
Bing Li and Scott T. Acton
{bingli, acton}@virginia.edu
University of Virginia, Charlottesville, VA 22904 USA
ABSTRACT
Snakes, or active contours, have been widely used in image
processing applications. Typical roadblocks to consistent
performance include limited capture range, noise sensitivity,
and poor convergence to concavities. This paper proposes a
new design for the snake external force, called vector field
convolution (VFC), to address these problems. Qualitative
and quantitative comparisons with the gradient vector flow
(GVF) external force are presented in this paper to show the
advantages of this innovation.
Index Terms -- Image processing, image segmentation,
image shape analysis, object detection
1. INTRODUCTION
Snakes [1] (a.k.a. active contours) have been widely used
for image segmentation [2] and tracking [3, 4]. Snakes can
deform on the image domain and capture a desired object
|
