Depth-based thinning: A new non-iterative skeletonization algorithm for 2D digital images

Thinning of binary image processing is a fundamental and important technology. Most of the existing image thinning algorithms are based on processing the same picture multiple times, and deleting the edge points layer by layer. For a amount of information in the image, the image thinning processing is relatively slow. To address this problem, an improved thinning algorithm is proposed in this paper. In particular, this algorithm uses the depth of each point to find the deepest points, only considers the deepest points and its neighboring points to determine the point can be deleted. The thinning processing time is decreased, and the skeleton is smooth, clear and continuous.