A 3-layer recurrent neural network is proposed for parallel thinning. This network iteratively removes the contour points of an object shape by template matching. After the neural network converges, a perfectly 8-connected skeleton is derived. The set of templates which the neural network tries to match is specially designed for a one-pass parllel thinning algorithm. The proposed neural network...

This paper proposes a 2-subfield thinning algorithm for extracting medial curves on 3D binary images where the set of all voxels of an image is partitioned into two isometric subsets and the algorithm works alternatively on each subset at a time. The thinning algorithm is proved to preserve topology. An algorithm for verifying the topology soundness of thinning algorithms should be established ...

Hormones play a critical role in regulating tissue function by promoting cell survival, proliferation, and differentiation. Our study explores the influence of endocrine function in regulating metabolism and inflammatory pathways in Keratoconus (KC), which is a corneal thinning disease associated with reduced stromal deposition. KC is known to be a multifactorial disease with an elusive pathoge...

Thinning is a widely used approach for skeletonization. Sequential thinning algorithms use contour tracking: they scan border points and remove the actual one if it is not designated a skeletal point. They may produce various skeletons for different visiting orders. In this paper, we present a new 2-dimensional sequential thinning algorithm, which produces the same result for arbitrary visiting...

A widely used technique to obtain skeletons of binary objects is thinning, which is an iterative layer-by-layer erosion in a topology preserving way. Thinning in 3D is capable of extracting various skeleton-like shape descriptors (i.e., centerlines, medial surfaces, and topological kernels). This chapter describes a family of new parallel 3D thinning algorithms for (26,6) binary pictures. The r...

Thinning is a frequently used strategy to produce skeletonlike shape features of binary objects. One of the main problems of parallel thinning is to ensure topology preservation. Solutions to this problem have been already given for the case of orthogonal and hexagonal grids. This work introduces some characterizations of simple pixels and some sufficient conditions for parallel thinning algori...

A 3D thinning algorithm erodes a 3D image layer by layer to extract the skeletons. This paper presents an improved fully parallel 3D thinning algorithm which extracts medial lines from a 3D image. This algorithm is based on Ma and Sonka’s thinning algorithm [16], which fails to preserve connectivity of 3D objects. We start with Ma and Sonka’s algorithm and examine its verification of connectivi...

Aim of study: This contribution describes a systematic search method for identifying optimum thinning regimes for beech forests (Fagus sylvatica L.) by using a combination of optimization heuristics and a simple whole stand growth prediction model. Area of study: Data to build the model come from standard and management forest inventories as well as yield tables from the Northern and Western pa...

Apples show biennial fluctuations in yields (alternate bearing). The alternate bearing cycle can be broken by reducing excessive flowers using either chemical or mechanical means. Currently, automatic thinning systems are treating the trees uniformly despite the fact that neighbouring trees can have a very different numbers of flowers resulting in different thinning requirements. In order to so...

PURPOSE To evaluate whether β-zone parapapillary atrophy (PPA) is associated with the rate of retinal nerve fiber layer (RNFL) thickness change as assessed by trend-based analysis using time-domain optical coherence tomography (OCT). METHODS This retrospective cohort study included 202 glaucomatous eyes that were observed for ≥3 years with serial OCTs and stereo disc photographs. Subjects wer...