Skeletonization Algorithm Research Articles

Hardware implementation of digital image skeletonization algorithm using FPGA for computer vision applications

Nowadays embedded multimedia devices are designed for computationally intensive applications such as image processing in various multimedia systems. Image processing algorithms should be implemented on hardware platforms for improving the performance. Reconfigurable hardware implementation using Field Programmable Gate Arrays (FPGAs) provides low latency with high performance in real time applications. FPGAs offer the reprogrammability of an application specific solution while retaining the performance advantage. In real time applications as image sizes increase rapidly, only hardware systems must be used with low complex software. In this paper, main perspective of developing and implementing skeletonization algorithm as a part of computer vision, pattern recognition application is focused and presented. A simple algorithm to skeletonize the 2-D image using MATLAB is developed. An architecture and implementation of this skeletonization algorithm for 2-D gray scale images is proposed. For analyzing pixel values 3 × 3 windowing operator is used. The proposed architecture is tested for an image size of 8 × 8, but the approach presented in this paper can be used for images of any size (M × N), if the FPGA memory is sufficiently large. The implementation was carried out on Xilinx Vertex 5 board.

Influence of a Marker-Based Motion Capture System on the Performance of Microsoft Kinect v2 Skeleton Algorithm

Microsoft Kinect sensors are being widely used as low-cost marker-less motion capture systems in various kinematic studies. Previous studies investigated the reliability and validity of Microsoft Kinect sensors by employing marker-based motion capture systems. Both systems employ infrared emitters and detectors to track human posture and physical activities. This paper hypothesizes that the motion capture systems may interfere with Microsoft Kinect one sensor and may influence the sensor’s performance in tracking the skeleton. Hence, this paper investigated the impact of a motion capture system on the Microsoft Kinect v2 skeleton algorithm using a mannequin in the presence of eight Qualisys Oqus 300/310 cameras and retroreflective markers. It was found that the motion capture system introduced a destructive impact on the Microsoft Kinect v2 skeleton tracking algorithm. In addition, it was observed that retroreflective markers placed near the joints caused the Microsoft Kinect v2 to give an incorrect reading of estimate the joint position. The motion capture cameras thus caused a time-varying distortion of the Microsoft Kinect estimate of the joint position. It is believed that the inference can be reduced by decreasing the number of markers and avoiding facing the motion capture cameras in sight of Microsoft Kinect v2.

Skeleton-Based Visual Servoing in Unknown Environments

The generalized Voronoi diagram (GVD) is a powerful environment representation that defines a set of paths at maximal distance from the obstacles. Many works implicitly use this property to define safe navigation strategies for a mobile robot, but, in practice, only a few explicitly extracts in real time the GVD from the robot perception. In this paper, a real-time skeleton-based visual servoing approach is proposed for safe autonomous navigation of mobile robots in unknown structured environments. The control is based on an approximation of the local GVD using the delta medial axis, a fast and robust skeletonization algorithm. The latter produces a filtered skeleton of the freespace surrounding the robot using a pruning parameter that takes into account the robot size. A unified virtual perception frame is also introduced to project the navigable freespace obtained by possibly multiple sensors and observations. After freespace skeletonization and GVD approximation, a visual servoing control is designed and studied to ensure autonomous robot navigation along the extracted GVD branches. The approach is first tested using a simulated environment. Then, an experimental validation is carried out on a real differential wheelchair allowing the system to navigate safely and autonomously without any human intervention. Static and dynamic environment scenarios are studied. The method is immediately generalizable to any differential drive wheeled robot.

Gesture recognition based on skeletonization algorithm and CNN with ASL database

In the field of human-computer interaction, vision-based gesture recognition methods are widely studied. However, its recognition effect depends to a large extent on the performance of the recognition algorithm. The skeletonization algorithm and convolutional neural network (CNN) for the recognition algorithm reduce the impact of shooting angle and environment on recognition effect, and improve the accuracy of gesture recognition in complex environments. According to the influence of the shooting angle on the same gesture recognition, the skeletonization algorithm is optimized based on the layer-by-layer stripping concept, so that the key node information in the hand skeleton diagram is extracted. The gesture direction is determined by the spatial coordinate axis of the hand. Based on this, gesture segmentation is implemented to overcome the influence of the environment on the recognition effect. In order to further improve the accuracy of gesture recognition, the ASK gesture database is used to train the convolutional neural network model. The experimental results show that compared with SVM method, dictionary learning + sparse representation, CNN method and other methods, the recognition rate reaches 96.01%.

2D skeleton extraction based on heat equation

Object skeleton is a useful geometric tool for shape analysis tasks. It encodes the topological structure of the primitive shape and preserves a geometric cue as well. Skeletonization is a seemingly simple but difficult research problem. A desirable skeletonization algorithm has to be topologically complete, insensitive to boundary noise, without any branch pruning and free of user-specified parameters. In this paper, we propose a novel method based on the heat equation to extract skeletons assuming that the input is a binary image. Based on the connection between the skeleton and ridge lines, we use the smooth heat diffusion height surface to approximate the real distance field, and then extract the ridge lines of the surface as the output skeleton. Different from the existing approaches, the proposed method in this paper has the above-mentioned excellent properties and can capture the clean and stable skeleton directly. Extensive experimental results show that the new approach can yield better skeletons than the state-of-the-art.

Visual Servoing on the Generalized Voronoi Diagram Using an Omnidirectional Camera

The Generalized Voronoi Diagram (GVD) is a powerful environment representation, since, among other reasons, it defines a set of paths at maximal distance from the obstacles. Many works implicitly use this property to define safe navigation strategies for a mobile robot, but, in practice, only a few explicitly extract in real time the GVD from its perception to induce motion. This article addresses this challenge for a mobile robot solely equipped with an omnidirectional camera, and proposes an autonomous navigation strategy in unknown indoor and/or outdoor environments. The problem is formulated as a visual servoing task, and uses an anisotropic skeletonization algorithm to identify the projection in the image of the local GVD, while suppressing unsafe navigable paths thanks to a context-defined pruning parameter. Unlike rangefinder based system, the use of an omnidirectional camera allows to efficiently deal with outdoor scenes, since the navigable space is extracted using photometric cues. The servoing is then performed using a local linear approximation of the GVD, defined by a conic extracted in real time in the omnidirectional image. To assert the relevancy and efficiency of the proposed approach, extended experimental results are presented, both on indoor and outdoor scenarios.

Combining Skeletonization, Setpoint Curves, and Heuristic Algorithms to Define District Metering Areas in the Battle of Water Networks District Metering Areas

AbstractThe problem presented in this edition of the Battle of the Water Networks is to define district metering areas (DMAs) in a large network. The problem is addressed in two phases. First, the ...

A Three-Dimensional Skeletonization Algorithm for Morphological Analysis of Renal Cysts in Patients with Autosomal Dominant Polycystic Kidney Disease

A Three-Dimensional Skeletonization Algorithm for Morphological Analysis of Renal Cysts in Patients with Autosomal Dominant Polycystic Kidney Disease

A novel 3D skeleton algorithm based on neutrosophic cost function

This paper proposed a novel algorithm to extract the skeleton for the objects on three dimensional images with or without noise.Neutrosophic cost function is proposed based on neutrosophic set.Neutrosophic cost function is employed to define the cost between each point on skeleton. A skeleton provides a synthetic and thin representation of three dimensional objects, and is useful for shape description and recognition. In this paper, a novel 3D skeleton algorithm is proposed based on neutrosophic cost function. Firstly, the distance transform is used to a 3D volume, and the distance matrix is obtained for each voxel in the volume. The ridge points are identified based on their distance transform values and are used as the candidates for the skeleton. Then, a novel cost function, namely neutrosophic cost function (NCF) is proposed based on neutrosophic set, and is utilized to define the cost between each ridge points. Finally, a shortest path finding algorithm is used to identify the optimum path in the 3D volume with least cost, in which the costs of paths are calculated using the new defined NCF. The optimum path is treated as the skeleton of the 3D volume. A variety of experiments have been conducted on different 3D volume. The experimental results demonstrate the better performance of the proposed method. It can identify the skeleton for different volumes with high accuracy. In addition, the proposed method is robust to the noise on the volume. This advantage will lead it to wide application in the skeleton detection applications in the real world.

Representative elementary volume (REV) of cementitious materials from three-dimensional pore structure analysis

The representative elementary volume (REV) is a fundamental property of a material, but no direct measurements exist for cementitious materials. In this paper, the REV of cement pastes with supplementary cementitious materials (GGBS, PFA, SF) was determined by analysing the three-dimensional pore structure (>0.2μm) using laser scanning confocal microscopy (LSCM). The effect of axial distortion inherent to LSCM on 3D pore structure was also investigated. A range of 3D pore parameters was measured using skeletonisation, maximal ball and random walker algorithms. Results show that axial distortion has insignificant effects on most parameters except Euler connectivity, average pore and throat volumes and directional diffusion tortuosities. Most pore parameters become independent of sampling volume at ≈603μm3 except diffusion tortuosities and formation factor. The REV for porosity calculated based on a statistical approach at eight realisations and 5% relative error was found to be ≈1003μm3.

Fuzzy Object Skeletonization: Theory, Algorithms, and Applications.

Skeletonization offers a compact representation of an object while preserving important topological and geometrical features. Literature on skeletonization of binary objects is quite mature. However, challenges involved with skeletonization of fuzzy objects are mostly unanswered. This paper presents a new theory and algorithm of skeletonization for fuzzy objects, evaluates its performance, and demonstrates its applications. A formulation of fuzzy grassfire propagation is introduced; its relationships with fuzzy distance functions, level sets, and geodesics are discussed; and several new theoretical results are presented in the continuous space. A notion of collision-impact of fire-fronts at skeletal points is introduced, and its role in filtering noisy skeletal points is demonstrated. A fuzzy object skeletonization algorithm is developed using new notions of surface- and curve-skeletal voxels, digital collision-impact, filtering of noisy skeletal voxels, and continuity of skeletal surfaces. A skeletal noise pruning algorithm is presented using branch-level significance. Accuracy and robustness of the new algorithm are examined on computer-generated phantoms and micro- and conventional CT imaging of trabecular bone specimens. An application of fuzzy object skeletonization to compute structure-width at a low image resolution is demonstrated, and its ability to predict bone strength is examined. Finally, the performance of the new fuzzy object skeletonization algorithm is compared with two binary object skeletonization methods.

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.

3D tree modeling from incomplete point clouds via optimization and L1-MST

ABSTRACTReconstruction of 3D trees from incomplete point clouds is a challenging issue due to their large variety and natural geometric complexity. In this paper, we develop a novel method to effectively model trees from a single laser scan. First, coarse tree skeletons are extracted by utilizing the L1-median skeleton to compute the dominant direction of each point and the local point density of the point cloud. Then we propose a data completion scheme that guides the compensation for missing data. It is an iterative optimization process based on the dominant direction of each point and local point density. Finally, we present a L1-minimum spanning tree (MST) algorithm to refine tree skeletons from the optimized point cloud, which integrates the advantages of both L1-median skeleton and MST algorithms. The proposed method has been validated on various point clouds captured from single laser scans. The experiment results demonstrate the effectiveness and robustness of our method for coping with complex shapes of branching structures and occlusions.

Skeletonization algorithm-based blood vessel quantification using in vivo 3D photoacoustic imaging

Blood vessels are the only system to provide nutrients and oxygen to every part of the body. Many diseases can have significant effects on blood vessel formation, so that the vascular network can be a cue to assess malicious tumor and ischemic tissues. Various imaging techniques can visualize blood vessel structure, but their applications are often constrained by either expensive costs, contrast agents, ionizing radiations, or a combination of the above. Photoacoustic imaging combines the high-contrast and spectroscopic-based specificity of optical imaging with the high spatial resolution of ultrasound imaging, and image contrast depends on optical absorption. This enables the detection of light absorbing chromophores such as hemoglobin with a greater penetration depth compared to purely optical techniques. We present here a skeletonization algorithm for vessel architectural analysis using non-invasive photoacoustic 3D images acquired without the administration of any exogenous contrast agents. 3D photoacoustic images were acquired on rats (n = 4) in two different time points: before and after a burn surgery. A skeletonization technique based on the application of a vesselness filter and medial axis extraction is proposed to extract the vessel structure from the image data and six vascular parameters (number of vascular trees (NT), vascular density (VD), number of branches (NB), 2D distance metric (DM), inflection count metric (ICM), and sum of angles metric (SOAM)) were calculated from the skeleton. The parameters were compared (1) in locations with and without the burn wound on the same day and (2) in the same anatomic location before (control) and after the burn surgery. Four out of the six descriptors were statistically different (VD, NB, DM, ICM, p < 0.05) when comparing two anatomic locations on the same day and when considering the same anatomic location at two separate times (i.e. before and after burn surgery). The study demonstrates an approach to obtain quantitative characterization of the vascular network from 3D photoacoustic images without any exogenous contrast agent which can assess microenvironmental changes related to disease progression.

An interactive editor for curve-skeletons: SkeletonLab

Curve-skeletons are powerful shape descriptors able to provide higher level information on topology, structure and semantics of a given digital object. Their range of application is wide and encompasses computer animation, shape matching, modelling and remeshing. While a universally accepted definition of curve-skeleton is still lacking, there are currently many algorithms for the curve-skeleton computation (or skeletonization) as well as different techniques for building a mesh around a given curve-skeleton (inverse skeletonization). Despite their widespread use, automatically extracted skeletons usually need to be processed in order to be used in further stages of any pipeline, due to different requirements. We present here an advanced tool, named SkeletonLab, that provides simple interactive techniques to rapidly and automatically edit and repair curve skeletons generated using different techniques proposed in the literature, as well as handcrafting them. The aim of the tool is to allow trained practitioners to manipulate the curve-skeletons obtained with skeletonization algorithms in order to fit their specific pipelines or to explore the requirements of newly developed techniques.

Quantification of choroidal neovascularization vessel length using optical coherence tomography angiography.

Quantification of choroidal neovascularization (CNV) as visualized by optical coherence tomography angiography (OCTA) may have importance clinically when diagnosing or tracking disease. Here, we present an automated algorithm to quantify the vessel skeleton of CNV as vessel length. Initial segmentation of the CNV on en face angiograms was achieved using saliency-based detection and thresholding. A level set method was then used to refine vessel edges. Finally, a skeleton algorithm was applied to identify vessel centerlines. The algorithm was tested on nine OCTA scans from participants with CNV and comparisons of the algorithm’s output to manual delineation showed good agreement.

Road centerlines extraction from high resolution images based on an improved directional segmentation and road probability

It is very important to extract accurate road networks from high resolution remote sensing images for various applications, such as transportation database updating. However, existing approaches cannot get satisfactory results. We propose an improved road networks extraction from remote sensing images based on the shear transform, the directional segmentation, the road probability, shape features and a skeletonization algorithm. The proposed method includes the following steps. First, we combine shear transform with directional segmentation to get the initial road regions. Second, road map based on Mahalanobis distance and thresholding is fused with the initial road regions to improve accuracy. Third, road shape features filtering and hole filling are used to extract reliable road segments. Finally, the road centerlines are extracted by an automatic subvoxel precise skeletonization method based on fast marching. Road networks are then generated by post-processing. Experimental results show that the proposed method can extract smooth and correct road centerlines.

Gesture Analysis For Yoga Alignment

INTRODUCTION: Yoga Therapy research has recently become the focus of rigorous scientific inquiry in the interest of understanding and quantifying its benefits for a wide variety of medical conditions. There remains a disparity between segments of the population who can readily access yoga classes and therapies. For difficult to reach individuals, Yoga in an exergame format could be utilized in clinical or home environments. The purpose of this study was to analyze Yoga posture alignment using a gesture analysis program in order to produce a yoga exergame using the Microsoft Kinect. We captured six yoga postures demonstrated by an advanced yoga teacher, as a gold standard for comparison purposes. METHODS: Six yoga postures were selected for the basis of the training set using Microsoft Visual Gesture Builder (VGB). Programs utilized were included in Kinect version 2 SDK and ran on a PC. RESULTS: Three 3D video clips of the six yoga postures were captured from the yoga teacher, two for VGB training and one for validation. We found that adding the second training clip increased performance accuracy for four out of the six postures. The forward bend and arms up postures might improve with additional training clips. Our prior research has shown that the Kinect skeleton algorithms become confused with yoga postures that change the usual orientation of the head. A convenience sample of undergraduate students with various levels of yoga experience, were recorded executing the same 6 postures before, at the mid-point and at the conclusion of a 10-week yoga class series. We assessed the longitudinal correlation points between yoga experience level and VGB posture accuracy. CONCLUSION: Gesture analysis for yoga alignment training may be a useful tool for the development of home and clinical yoga therapy for hard to reach populations. The Kinect sensor provides a tool that could score the performance of yoga therapy and provide quantitative measures of posture adherence and improvement.

A study on skeletonization of complex petroglyph shapes

In this paper, we present a study on skeletonization of real-world shape data. The data stem from the cultural heritage domain and represent contact tracings of prehistoric petroglyphs. Automated analysis can support the work of archeologists on the investigation and categorization of petroglyphs. One strategy to describe petroglyph shapes is skeleton-based. The skeletonization of petroglyphs is challenging since their shapes are complex, contain numerous holes and are often incomplete or disconnected. Thus they pose an interesting testbed for skeletonization. We present a large real-world dataset consisting of more than 1100 petroglyph shapes. We investigate their properties and requirements for the purpose of skeletonization, and evaluate the applicability of state-of-the-art skeletonization and skeleton pruning algorithms on this type of data. Experiments show that pre-processing of the shapes is crucial to obtain robust skeletons. We propose an adaptive pre-processing method for petroglyph shapes and improve several state-of-the-art skeletonization algorithms to make them suitable for the complex material. Evaluations on our dataset show that 79.8 % of all shapes can be improved by the proposed pre-processing techniques and are thus better suited for subsequent skeletonization. Furthermore we observe that a thinning of the shapes produces robust skeletons for 83.5 % of our shapes and outperforms more sophisticated skeletonization techniques.

Skeleton Generation for Digital Images Based on Performance Evaluation Parameters

Skeletonization is a crucial step in many digital image processing applications like medical imaging, pattern recognition, fingerprint classification etc. The skeleton expresses the structural connectivities of the main component of an object and is one pixel in width. Present paper covers the aspects of pixel deletion criteria in the skeletonization algorithms needed to preserve the connectivity, topology, sensitivity of the binary images. Performance of different skeletonization algorithms can be measured in terms of different parameters such as thinning rate, number of connected components, execution time etc. Present paper focuses on Peak Signal to Noise Ratio, number of connected components, execution time and Mean Square error on Zhang and Suen algorithm and Guo and Hall algorithm.