Parallel Thinning Research Articles

Basal Forebrain Atrophy, Cortical Thinning, and Amyloid-β Status in Parkinson's disease-Related Cognitive Decline.

Degeneration of the cortically-projecting cholinergic basal forebrain (cBF) is a well-established pathologic correlate of cognitive decline in Parkinson's disease (PD). In Alzheimer's disease (AD) the effect of cBF degeneration on cognitive decline was found to be mediated by parallel atrophy of denervated cortical areas. To examine whether the association between cBF degeneration and cognitive decline in PD is mediated by parallel atrophy of cortical areas and whether these associations depend on the presence of comorbid AD pathology. We studied 162 de novo PD patients who underwent serial 3 T magnetic resonance imaging scanning (follow-up: 2.33 ± 1.46 years) within the Parkinson's Progression Markers Initiative. cBF volume and regional cortical thickness were automatically calculated using established procedures. Individual slopes of structural brain changes and cognitive decline were estimated using linear-mixed models. Associations between longitudinal cBF degeneration, regional cortical thinning, and cognitive decline were assessed using regression analyses and mediation effects were assessed using nonparametric bootstrap. Complementary analyses assessed the effect of amyloid-β biomarker positivity on these associations. After controlling for global brain atrophy, longitudinal cBF degeneration was highly correlated with faster cortical thinning (PFDR < 0.05), and thinning in cBF-associated cortical areas mediated the association between cBF degeneration and cognitive decline (rcBF-MoCA = 0.30, P < 0.001). Interestingly, both longitudinal cBF degeneration and its association with cortical thinning were largely independent of amyloid-β status. cBF degeneration in PD is linked to parallel thinning of cortical target areas, which mediate the effect on cognitive decline. These associations are independent of amyloid-β status, indicating that they reflect proper features of PD pathophysiology. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Efficient Parallel Thinning of 3d Objects on the Body-centered Cubic Lattice

We consider thinning methods to extract one dimensional skeletons from discrete objects defined on the body-centered cubic (bcc) lattice. In Strand (2004), a condition has been given that guarantees the preservation of the object’s topology in such a thinning process. In this paper, we present stronger conditions that even allow the topological invariant point removal in a parallelized process. These conditions for p -simplicity can be efficiently evaluated which leads to a very fast thinning process. We show that p -simplicity is a new concept that cannot be obtained by adapting the checking plane conditions of Tsao and Fu to the bcc lattice. Furthermore, we introduce distance information and an optional pruning mechanism into the thinning process to improve the quality of the resulting skeletons. The presented results show that our method generates high quality skeletons that reproduce the symmetries of the models even under the condition of added noise and contain only very few spurious branches. The presented running times demonstrate the linear run-time behavior of our algorithm and the speedup that is achieved by the parallelization. • Curve-like skeletons of closed 3D objects are used for many different purposes in computer graphics. • Thinning is a method to extract the skeleton which requires the object to be discretized on a lattice. • Only for thinning on the cubic grid parallel algorithms are available. • We present the first parallel thinning algorithm on the bcc lattice. • Our method generates high quality skeletons that contain only very few spurious branches. • The skeletons reproduce the symmetries of the models even under the condition of added noise.

Method for detecting 2D grapevine winter pruning location based on thinning algorithm and Lightweight Convolutional Neural Network

In viticulture, there is an increasing demand for automatic winter grapevine pruning devices, for which detection of pruning location in vineyard images is a necessary task, susceptible to being automated through the use of computer vision methods. In this study, a novel 2D grapevine winter pruning location detection method was proposed for automatic winter pruning with a Y-shaped cultivation system. The method can be divided into the following four steps. First, the vineyard image was segmented by the threshold two times Red minus Green minus Blue (2R−G−B) channel and S channel; Second, extract the grapevine skeleton by Improved Enhanced Parallel Thinning Algorithm (IEPTA); Third, find the structure of each grapevine by judging the angle and distance relationship between branches; Fourth, obtain the bounding boxes from these grapevines, then pre-trained MobileNetV3_small×0.75 was utilized to classify each bounding box and finally find the pruning location. According to the detection experiment result, the method of this study achieved a precision of 98.8% and a recall of 92.3% for bud detection, an accuracy of 83.4% for pruning location detection, and a total time of 0.423 s. Therefore, the results indicated that the proposed 2D pruning location detection method had decent robustness as well as high precision that could guide automatic devices to winter prune efficiently. Keywords: grapevine winter pruning, Lightweight Convolutional Neural Network, thinning algorithm, detection method DOI: 10.25165/j.ijabe.20221503.6750 Citation: Yang Q H, Yuan Y H, Chen Y Q, Xun Y. Method for detecting 2D grapevine winter pruning location based on thinning algorithm and Lightweight Convolutional Neural Network. Int J Agric & Biol Eng, 2022; 15(3): 177–183.

Hybrid Parallel Image Processing Algorithm for Binary Images with Image Thinning Technique

Image thinning is the most essential pre-processing technique that plays major role in image processing applications such as image analysis and pattern recognition. It is a process that reduces a thick binary image into thin skeleton. In the present paper we have used hybrid parallel thinning algorithm to obtain the skeleton of the binary image. The result skeleton contains one pixel width which preserves the topological properties and retains the connectivity.

1-Attempt parallel thinning

Thinning is a frequently used technique capable of producing all kinds of skeleton-like shape features in a topology-preserving way. It is an iterative object reduction: some border points of binary objects that satisfy some topological and geometrical constraints are deleted, and the entire process is repeated until stability is reached. In the conventional implementation of thinning algorithms, the deletability of all border points in the actual picture is to be investigated. That is why, we introduced the concept of k-attempt thinning ( $$k\ge 1$$ ) in our previous work (presented in the 20th International Workshop on Combinatorial Image Analysis, IWCIA 2020). In the case of a k-attempt algorithm, if a border point ‘survives’ at least k successive iterations, it is ‘immortal’ (i.e., it cannot be deleted later). In this paper, we give a computationally efficient implementation scheme for 1-attempt thinning, and a 1-attempt 2D parallel thinning algorithm is reported. The advantage of the new implementation scheme over the conventional one is also illustrated.

Road Centerline Extraction From VHR Images Using SVM and Multi-Scale Maximum Response Filter

In this work, an integrated framework comprising of pixel-based classification, road network filtering, and multi-scale Gabor filter is proposed to address the various prevailing issues in road centerline extraction from VHR images. The proposed framework is composed of three steps; generation of the initial road map, road network filtering and road centerline extraction. In the first step, pixel-based classification using support vector machine (SVM) is performed on VHR imagery to classify it into the road and non-road classes. In the road network filtering step, to retain the road features in classified imagery, an edge-preserving guided filter is applied and to improve the veracity of road extraction, undesirable components are eliminated by shape feature analysis. Finally, the complete and accurate road centerline are obtained by combining multi-scale Gabor filter and fast parallel thinning algorithm. The maximum response from a multi-scale Gabor filter is not only used for extraction but also used for reconstructing the broken road network, which is due to occlusions and artifacts. The proposed framework is implemented on publically available VHR images dataset. The simulation outcomes reflect the dominance of the proposed framework on different quantitative evaluation parameters as compared to up-to-date methods.

Research on the application of convolutional-deep neural networks in parallel fingerprint minutiae matching

In order to overcome the problem of low throughput and time-consuming of traditional fingerprint minutiae matching methods, a new convolutional-deep neural network is proposed for parallel fingerprint minutiae matching. This method realises the preprocessing of the initial image through four steps: normalisation, image enhancement, parallel thinning and image segmentation. The convolutional-deep neural network is constructed from convolution kernel, convolution layer, pooling layer and full connection layer to extract minutiae of fingerprint image. Through feature minutiae matching, local matching and global matching, the matching results of fingerprint parallel nodes are obtained. The experimental results show that compared with the traditional matching method, the fingerprint matching throughput of convolutional-deep neural network is increased by 25%, and the matching time is saved by about 8 seconds.

Model representation and quantitative analysis of pore three‐dimensional morphological structure based on soil computed tomography images

AbstractComputed tomography technology has contributed greatly to the visualization of soil internal structure. Complex topological structure and spatial distribution of pores have become a focal area for studying the spatiotemporal evolution of soil structure. This is significant for understanding soil functions and ecological processes. Image‐processing software, such as ImageJ and Image Pro‐Plus, is widely used to visualize and quantify soil pores. However, it does not account for the irregularity and heterogeneity of pore structure, leading to low segmentation accuracy and inaccurate description of pore morphology. Therefore, we used the simplified convolutional network (SCN) method to segment the pore structure and proposed a parallel thinning method to extract the pore skeleton structure. Thereafter, using three‐dimensional modelling and quantitative analysis, we initially examined the spatiotemporal evolution of soil pores during freeze–thaw cycles. Based on the custom rule model and soil pore real model, we evaluated the performance of the distance transform method and parallel thinning method in extracting the pore skeleton structure. The parallel thinning method more effectively described the topological characteristics of pores, and the pore skeleton model had better centrality, refinement and connectivity. Quantitative analysis of pore characteristics illustrates that, although freeze–thaw cycles can affect pore structure at different scales, they do not regularly affect pore macroporosity and the three‐dimensional fractal dimension. These results illustrate that the soil pore structure of the viscous layer is sensitive to freeze–thaw cycles and provides preliminary evidence that seasonal freeze–thaw cycles can cause a soil water retention effect and weaken resistance to erosion. This study presents a novel technique for examining soil function at the pore scale and a theoretical foundation for future research on soil structure and hydrology.Highlights Freeze–thaw cycles have important effects on soil pore characteristics and thus on soil ecology. We provide novel evidence of pore structural changes in response to freeze–thaw cycles. Soil macropore skeleton was extracted using the parallel thinning method. Seasonal freeze–thaw cycles reconfigured the soil macropore model.

Role of Skeletonization Techniques for Recognition of Odia Off-Line Characters

Many character recognition methods use a thinning stage which facilitates shape analysis and stroke identification. There are several thinning algorithms reported in the literature of OCR. Odia, one of the Indian languages, has structurally different scripts than other Indian languages. Unlike in other Indian scripts, there has not been any special effort by OCR researchers to develop recognition techniques of this unique structural character set. In this paper, some major thinning algorithms are examined with Odia character set and show that these algorithms exhibit some sort of deficiencies when applied to Odia characters and the vital features of the character is not retained in the process. We propose a new parallel thinning technique that preserves all important features of the script.

Parallel thinning and skeletonization algorithm based on cellular automaton

This paper proposes a parallel image thinning algorithm and a skeletonization algorithm based on cellular automaton (CA). Cellular automaton is a parallel computation model and a non-linear dynamical system. In this paper, each image pixel is identified as a cell of CA and the change of cell depends on the current state of itself and the state of its neighbors. In a binary image, this paper assumes that the objects (white pixel) are preys which are surrounded by many ants (every black pixels). The movement of ants is controlled by cellular automation. The ants gnaw preys until the preys (objects) become skeleton. The proposed parallel skeletonization algorithm can produce a traditional skeleton with a thin line located in the center of object, and the proposed thinning algorithm can produce a new kind of skeleton which is named as the ants-gnawing skeleton. The computation of ants-gnawing skeleton is faster than the traditional skeleton while it contains more the structural features of image. Benefiting from the properties of cellular automation, the proposed thinning algorithm does not change the basic geometry structure of image, and it is invariant for image rotation.

Robust and fast visual tracking for a ball and plate control system: design, implementation and experimental verification

The ball and plate System (BPS) is a two-dimensional electromechanical system with multiple variables, non-linearity and strong coupling. The BPS control problem is to hold the rolling ball in a specific position on the plate by adjusting the plate inclination. Ball tracking is therefore the fundamental step in BPS control, which can largely influence the control effectiveness and efficiency. The segmented path planning based on the sequential thinning algorithm is one popular tracking technology. However, it suffers from high dependence on the operating environment, complex operation and slow speed. This paper innovatively proposes a robust and fast visual tracking solution for BPS. A novel hardware structure has been designed. The sensing camera is rigidly connected to the plate, which avoids the coordinate transformation and thus reduces the complexity. In path recognition, a parallel thinning algorithm is used to improve the processing speed. Additionally, in path planning, a window searching algorithm combining the slope order matching method is proposed to establish the linked list that describes the movement path. A cascaded structure of the BPS tracking controller is also designed. Experiments have shown the effectiveness of the whole system, exhibiting shorter travelling time, smaller tracking errors as well as better stability compared to conventional systems.

Chinese Character Thinning System Based on LabVIEW and BP Neural Network

In order to effectively realize the thinning of Chinese character, a Chinese character thinning system based on LabVIEW platform and BP neural network optimized parallel thinning algorithm is proposed. The BP neural network is trained by the optimized combinatorial templates to obtain the optimized training parameters. Then the optimized parameters are input into the thinning system of Chinese characters for quick thinning. Experiments show that the system not only has the advantages of parallel algorithm based on combinatorial templates, but also simplifies the operation, and its processing speed is about 20% higher than that of combinatorial templates, which is an ideal thinning system. It is widely used in fingerprints, circuit boards and medical image recognition.

Pattern Reconstructability in Fully Parallel Thinning

It is a challenging topic to perform pattern reconstruction from a unit-width skeleton, which is obtained by a parallel thinning algorithm. The bias skeleton yielded by a fully-parallel thinning algorithm, which usually results from the so-called hidden deletable points, will result in the difficulty of pattern reconstruction. In order to make a fully-parallel thinning algorithm pattern reconstructable, a newly-defined reconstructable skeletal pixel (RSP) including a thinning flag, iteration count, as well as reconstructable structure is proposed and applied for thinning iteration to obtain a skeleton table representing the resultant thin line. Based on the iteration count and reconstructable structure associated with each skeletal pixel in the skeleton table, the pattern can be reconstructed by means of the dilating and uniting operations. Embedding a conventional fully-parallel thinning algorithm into the proposed approach, the pattern may be over-reconstructed due to the influence of a biased skeleton. A simple process of removing hidden deletable points (RHDP) in the thinning iteration is thus presented to reduce the effect of the biased skeleton. Three well-known fully-parallel thinning algorithms are used for experiments. The performances investigated by the measurement of reconstructability (MR), the number of iterations (NI), as well as the measurement of skeleton deviation (MSD) confirm the feasibility of the proposed pattern reconstruction approach with the assistance of the RHDP process.

A modified ZS thinning algorithm by a hybrid approach

Thinning is one of the most important techniques in the field of image processing. It is applied to erode the image of an object layer-by-layer until a skeleton is left. Several thinning algorithms allowing to get a skeleton of a binary image are already proposed in the literature. This paper investigates several well-known parallel thinning algorithms and proposes a modified version of the most widely used thinning algorithm, called the ZS algorithm. The proposed modified ZS (MZS) algorithm is implemented and compared against seven existing algorithms. Experimental results and performances evaluation, using different image databases, confirm the proposed MZS algorithm improvement over the seven examined algorithms both in terms of the obtained results quality and the computational speed. Moreover, for an efficient implementation (on Graphics Processing Units), a parallel model of the MZS algorithm is proposed (using the Compute Unified Device Architecture, CUDA, as a parallel programming model). Evaluation results have shown that the parallel version of the proposed algorithm is, on average, more than 21 times faster than the traditional CPU sequential version.

A 3D Skeletonization Algorithm for 3D Mesh Models Using a Partial Parallel 3D Thinning Algorithm and 3D Skeleton Correcting Algorithm

A three-dimensional (3D) skeletonization algorithm extracts the skeleton of a 3D model and provides it for many applications, such as 3D model classification and identification. There are three major skeletonization methodologies used in the literature, distance transform field-based methods, Voronoi diagram-based methods, and thinning-based methods. However, the existing algorithms cannot preserve the connectivity of the skeletons of the 3D mesh models. In this paper, we propose a 3D skeletonization algorithm for 3D mesh models using a partial parallel thinning algorithm and a 3D skeleton correcting algorithm. The proposed algorithm uses pre-defined removing and recovering templates. The partial parallel 3D thinning algorithm separates 62 symmetrical removing templates into two groups based on symmetry. It thins a model with the templates of each group in each thinning procedure. The 3D skeleton correcting algorithm uses six correcting templates to inspect the disconnected voxels in the skeleton and corrects them. The experimental results show several comparisons of skeletons extracted by different skeletonization algorithms. The proposed algorithm can extract the skeleton of each branch of a model and preserve the connectivity.

A parallel thinning algorithm based on stroke continuity detection

Thinning algorithms often cause stroke distortions at the crosses or intersections of strokes, which lead to bad results in pattern recognition tasks. In order to overcome these drawbacks, this paper proposes a parallel thinning algorithm based on stroke continuity detection. In the algorithm, before it uses the conditions of parallel algorithms to delete a boundary point, it first detects whether the boundary point is a reserved point to keep stroke’s continuity or not. Consequently, it can produce a skeleton with good symmetry, control the large deformation at the cross or intersection of strokes, and make a better skeleton more quickly. Moreover, it is practically immune to noise.

A pair of equivalent sequential and fully parallel 3D surface-thinning algorithms

Thinning is an iterative object reduction to obtain skeletons from binary digital pictures. The object boundary is traversed in an iteration step of a sequential thinning algorithm, and the actually visited single point is considered for possible removal. On the contrary, parallel thinning algorithms can remove a set of object points simultaneously. In fully parallel thinning algorithms, the same parallel reduction is applied in each iteration step, and it is repeated until stability is reached. Two thinning algorithms are said to be equivalent if they produce the same result for any input picture. This paper presents the first pair of equivalent sequential and fully parallel 3D surface-thinning algorithms. The proposed algorithms use the same deletion rule, and preserve topology for (26,6) pictures.

Automated generation of directed graphs from vascular segmentations

Automated feature extraction from medical images is an important task in imaging informatics. We describe a graph-based technique for automatically identifying vascular substructures within a vascular tree segmentation. We illustrate our technique using vascular segmentations from computed tomography pulmonary angiography images. The segmentations were acquired in a semi-automated fashion using existing segmentation tools. A 3D parallel thinning algorithm was used to generate the vascular skeleton and then graph-based techniques were used to transform the skeleton to a directed graph with bifurcations and endpoints as nodes in the graph. Machine-learning classifiers were used to automatically prune false vascular structures from the directed graph. Semantic labeling of portions of the graph with pulmonary anatomy (pulmonary trunk and left and right pulmonary arteries) was achieved with high accuracy (percent correct⩾0.97). Least-squares cubic splines of the centerline paths between nodes were computed and were used to extract morphological features of the vascular tree. The graphs were used to automatically obtain diameter measurements that had high correlation (r⩾0.77) with manual measurements made from the same arteries.

Asymmetric parallel 3D thinning scheme and algorithms based on isthmuses

Critical kernels constitute a general framework settled in the context of abstract complexes for the study of parallel thinning in any dimension. We take advantage of the properties of this framework, to propose a generic thinning scheme for obtaining “thin” skeletons from objects made of voxels. From this scheme, we derive algorithms that produce curve or surface skeletons, based on the notion of 1D or 2D isthmus. We compare our new curve thinning algorithm with all the published algorithms of the same kind, based on quantitative criteria. Our experiments show that our algorithm largely outperforms the other ones with respect to noise sensitivity. Furthermore, we show how to slightly modify our algorithms to include a filtering parameter that controls effectively the pruning of skeletons, based on the notion of isthmus persistence.

Real-time three-dimensional skeletonisation using general-purpose computing on graphics processing units applied to computer vision-based human pose estimation

Human pose estimation is the process of approximating the configuration of the body’s underlying skeletal articulation in one or more frames. The curve-skeleton of an object is a line-like representation that preserves topology and geometrical information. Finding the curve-skeleton of a volume corresponding to the person is a good starting point for approximating the underlying skeletal structure. In this paper, a GPU implementation of a fully parallel thinning algorithm based on the critical kernel framework is presented. The algorithm is compared to three other state-of-the-art skeletonisation methods—two CPU and one GPU implementation—using both real and synthetic data. It is demonstrated that all four achieve close to real-time frame rates, however, the proposed algorithm yields superior accuracy and robustness when used in a pose estimation context. The GPU implementation is &gt; 8× faster than a CPU implementation of the same algorithm, and the positions of the 4 extremities are estimated with rms error ∼6 cm and ∼98% of frames correctly labelled for some sequences.