Search

Skeleton creation is an important phase in the character animation pipeline. However, handcrafting skeleton takes extensive labor time and domain knowledge. Automatic skeletonization provides a solution. However, most of the current approaches are far from real-time and lack the flexibility to control the skeleton complexity. In this paper, we present an efficient skeletonization method, which can be seamlessly integrated into the sketch-based modeling process in real-time. The method contains three steps: local sub-skeleton extraction; sub-skeleton connection; and global skeleton refinement. Firstly, the local skeleton is extracted from the processed polygon stroke and forms a subpart along with the sub-mesh. Then, local sub-skeletons are connected according to the intersecting relationships and the modeling sequence of subparts. Lastly, a global refinement method is proposed to give users coarse-to-fine control on the connected skeleton. We demonstrate the effectiveness of our method on a variety of examples created by both novices and professionals., Shape Modeling International 2021

Human identification plays a prominent role in terms of security. In modern times security is becoming the key term for an individual or a country, especially for countries which are facing internal or external threats. Gait analysis is interpreted as the systematic study of the locomotive in humans. It can be used to extract the exact walking features of individuals. Walking features depends on biological as well as the physical feature of the object; hence, it is unique to every individual. In this work, gait features are used to identify an individual. The steps involve object detection, background subtraction, silhouettes extraction, skeletonization, and training 3D Convolution Neural Network (3D-CNN) on these gait features. The model is trained and evaluated on the dataset acquired by CASIA—B Gait, which consists of 15,000 videos of 124 subjects’ walking pattern captured from 11 different angles carrying objects such as bag and coat. The proposed method focuses more on the lower body part to extract features such as the angle between knee and thighs, hip angle, angle of contact, and many other features. The experimental results are compared with amongst accuracies of silhouettes as datasets for training and skeletonized image as training data. The results show that extracting the information from skeletonized data yields improved accuracy.

Strand proposed a distance-based thinning algorithm for computing surface skeletons on the body-centered cubic (BCC) grid. In this paper, we present two modified versions of this algorithm that are faster than the original one, and less sensitive to the visiting order of points in the sequential thinning phase. In addition, a novel algorithm capable of producing curve skeletons is also reported.

Background: Systems of the Internet of Things are actively implementing biometric systems. For fast and high-quality recognition in sensory biometric control and management systems, skeletonization methods are used at the stage of fingerprint recognition. The analysis of the known skeletonization methods of Zhang-Suen, Hilditch, Ateb-Gabor with the wave skeletonization method has been carried out and it shows a good time and qualitative recognition results. Methods: The methods of Zhang-Suen, Hildich and thinning algorithm based on Ateb-Gabor filtration, which form the skeletons of biometric fingerprint images, are considered. The proposed thinning algorithm based on Ateb-Gabor filtration showed better efficiency because it is based on the best type of filtering, which is both a combination of the classic Gabor function and the harmonic Ateb function. The combination of this type of filtration makes it possible to more accurately form the surroundings where the skeleton is formed. Results: Along with the known ones, a new Ateb-Gabor filtering algorithm with the wave skeletonization method has been developed, the recognition results of which have better quality, which allows to increase the recognition quality from 3 to 10%. Conclusion: The Zhang-Suen algorithm is a 2-way algorithm, so for each iteration, it performs two sets of checks during which pixels are removed from the image. Zhang-Suen's algorithm works on a plot of black pixels with eight neighbors. This means that the pixels found along the edges of the image are not analyzed. Hilditch thinning algorithm occurs in several passages, where the algorithm checks all pixels and decides whether to replace a pixel from black to white if certain conditions are satisfied. This Ateb-Gabor filtering will provide a better performance, as it allows to obtain more hollow shapes, organize a larger range of curves. Numerous experimental studies confirm the effectiveness of the proposed method.

Chemotherapy for non-central nervous system cancers is associated with abnormalities in brain structure and function. Diffusion tensor imaging (DTI) allows for studying in vivo microstructural changes in brain white matter. Tract-based spatial statistics (TBSS) is a widely used processing pipeline in which DTI data are typically normalized to a generic DTI template and then ‘skeletonized’ to compensate for misregistration effects. However, this approach greatly reduces the overall white matter volume that is subjected to statistical analysis, leading to information loss. Here, we present a re-analysis of longitudinal data previously analyzed with standard TBSS (Menning et al., BIB 2018, 324–334). For our current approach, we constructed a pipeline with an optimized registration method in Advanced Normalization Tools (ANTs) where DTI data are registered to a study-specific, high-resolution T1 template and the skeletonization step is omitted. In a head to head comparison, we show that with our novel approach breast cancer survivors who had received chemotherapy plus or minus endocrine therapy (BC + SYST, n = 26) showed a global decline in overall FA that was not present in breast cancer survivors who did not receive systemic therapy (BC-SYST, n = 23) or women without a cancer diagnosis (no cancer controls, NC, n = 30). With the standard TBSS approach we did not find any group differences. Moreover, voxel-based analysis for our novel pipeline showed a widespread decline in FA in the BC + SYST compared to the NC group. Interestingly, the BC-SYST group also showed a decline in FA compared to the NC group, although in much less voxels. These results were not found with the standard TBSS approach. We demonstrate that a modified processing pipeline makes DTI data more sensitive to detecting changes in white matter integrity in non-CNS cancer patients after treatment, particularly chemotherapy.

Summary A best evidence topic in cardiac surgery was written according to a structured protocol. The question addressed was, ‘in patients undergoing coronary artery bypass grafting is semi-skeletonized harvesting superior to pedicled harvesting of the left internal mammary artery (LIMA) in terms of conduit length, flow, rate of sternal wound infections and post-operative bleeding?’. Altogether, 235 papers were found using the reported search, of which 5 represented the best evidence to answer the clinical question. Three studies were cohort studies and 2 were randomized controlled trials. The authors, journal, date and country of publication, patient group studied, study type, relevant outcomes and results of these papers are tabulated. One randomized controlled trial showed superiority with semi-skeletonized harvesting in terms of conduit length (P

The success of new scientific areas can be assessed by their potential for contributing to new theoretical approaches aligned with real-world applications. The Euclidean distance transform (EDT) has fared well in both cases, providing a sound theoretical basis for a number of applications, such as median axis transform, fractal analysis, skeletonization, and Voronoi diagrams. Despite its wide applicability, the discrete form of the EDT includes interesting properties that have not yet been fully exploited in the literature. In this paper, we are particularly interested in the properties of 1) working with multiple objects/labels; and 2) identifying and counting equidistant pixels/voxels from certain points of interest. In some domains (such as dataset classification, texture, and complexity analysis), the result of applying the EDT transform with different objects, and their respective tied distances, may compromise the performance. In this sense, we propose an efficient modification in the method presented in [1], which leads to a novel approach for computing the distance transform in a space with multiple objects, and for counting equidistant pixels/voxels.

Image skeletonisation plays an important role in applications such as object identification, object’s shape description, pattern recognition, computer vision, telemedicine, and image compression. I...

This study deals with differences of femoral geometric focus on the bowing and width. Analysis using three-dimensional skeletonization showed increase of femoral bowing and femur width over life (more in women), and widening of the medullary canal only in women after 50 years old, not in men. The changes in femur geometry that occur with aging and lead to fragility or insufficiency fracture remain unclear. The role of the lower limb geometry, including the femur and femoral bowing, has become a point of discussion, especially in atypical femur fracture. This study aimed to analyze femur shaft geometry using three-dimensional skeletonization. We acquired computed tomography images of both femurs obtained. A total of 1400 age- and sex-stratified participants were enrolled and were divided into subgroups according to age (by decade) and sex. The computed tomography images were used to produce 3-dimensional samplings of anatomical elements of the human femur using reconstruction and parametrization from these datasets. The process of skeletonization was conducted to obtain compact representation of the femur. With the skeletonization, we were able to compare all parameters according to age and sex. The femur length was 424.4 ± 28.6 mm and was longer in men (P

The aim of this work is the preliminary clinical validation and accuracy evaluation of our automatic algorithms in assessing progression fetal femur length (FL) in ultrasound images. To compare the random forest regression model with the SegNet model from the two aspects of accuracy and robustness. In this study, we proposed a traditional machine learning method to detect the endpoints of FL based on a random forest regression model. Deep learning methods based on SegNet were proposed for the automatic measurement method of FL, which utilized skeletonization processing and improvement of the full convolution network. Then the automatic measurement results of the two methods were evaluated quantitatively and qualitatively with the results marked by doctors. 436 ultrasonic fetal femur images were evaluated by the two methods above. Compared the results of the above three methods with doctor's manual annotations, the automatic measurement method of femur length based on the random forest regression model was 1.23 ± 4.66 mm and the method based on SegNet was 0.46 ± 2.82 mm. The indicator for evaluating distance was significantly lower than the previous literature. Measurement method based SegNet performed better in the case of femoral end adhesion, low contrast, and noise interference similar to the shape of the femur. The segNet-based method achieves promising performance compared with the random forest regression model, which can improve the examination accuracy and robustness of the measurement of fetal femur length in ultrasound images.

Objective Concerns have been raised regarding whether skeletonization of the internal thoracic artery could damage the graft and thereby reduces its patency. The objective of this study was to compare patency rates at mid- and long-term follow-up between pedicled and skeletonized left internal thoracic artery grafts. Methods This randomized controlled trial included 109 patients undergoing coronary artery bypass surgery. The patients were assigned to receive either one pedicled or one skeletonized left internal thoracic artery graft to the left anterior descending artery. Follow-up was performed at 3 years with conventional angiography, and at 8 years with computed tomography angiography. Differences between patency rates were analyzed with Fisher’s exact test and a generalized linear model. Results The patency rates for pedicled and skeletonized left internal thoracic artery grafts were 46/48 (95.8%) versus 47/52 (90.4%), p = 0.44 at 3 years, and 40/43 (93.0%) versus 37/41 (90.2%), p = 0.71 at 8 years, respectively. The difference in patency rates for pedicled and skeletonized grafts was 5.4% (95% confidence interval: −4.2–14.5) at 3 years and 2.8% (95% confidence interval: −9.9–14.1) at 8 years. All failed grafts, except for one with a localized stenosis, were anastomosed to native coronary arteries with a stenosis less than 70%. Three patients suffered sternal wound infections (two in the pedicled group, one in the skeletonized group). Conclusions The skeletonization technique can be used without jeopardizing the patency of the left internal thoracic artery. The most important factor in graft failure was target artery stenosis below 70%.

Convolutional Neural Network (CNN) has been increasingly used for land cover mapping of remotely sensed imagery. However, large-area classification using traditional CNN is computationally expensive and produces coarse maps using a sliding window approach. To address this problem, object-based CNN (OCNN) becomes an alternative solution to improve classification performance. However, previous studies were mainly focused on urban areas or small scenes, and implementation of OCNN method is still needed for large-area classification over heterogeneous landscape. Additionally, the massive labeling of segmented objects requires a practical approach for less computation, including object analysis and multiple CNNs. This study presents a new multiscale OCNN (multi-OCNN) framework for large-scale land cover classification at 1-m resolution over 145,740 km2. Our approach consists of three main steps: (i) image segmentation, (ii) object analysis with skeleton-based algorithm, and (iii) application of multiple CNNs for final classification. Also, we developed a large benchmark dataset, called IowaNet, with 1 million labeled images and 10 classes. In our approach, multiscale CNNs were trained to capture the best contextual information during the semantic labeling of objects. Meanwhile, skeletonization algorithm provided morphological representation (“medial axis”) of objects to support the selection of convolutional locations for CNN predictions. In general, proposed multi-OCNN presented better classification accuracy (overall accuracy ~87.2%) compared to traditional patch-based CNN (81.6%) and fixed-input OCNN (82%). In addition, the results showed that this framework is 8.1 and 111.5 times faster than traditional pixel-wise CNN16 or CNN256, respectively. Multiple CNNs and object analysis have proved to be essential for accurate and fast classification. While multi-OCNN produced a high-level of spatial details in the land cover product, misclassification was observed for some classes, such as road versus buildings or shadow versus lake. Despite these minor drawbacks, our results also demonstrated the benefits of IowaNet training dataset in the model performance; overfitting process reduces as the number of samples increases. The limitations of multi-OCNN are partially explained by segmentation quality and limited number of spectral bands in the aerial data. With the advance of deep learning methods, this study supports the claim of multi-OCNN benefits for operational large-scale land cover product at 1-m resolution.

In this study, we present deep learning‐based approaches to automatic segmentation and applicator reconstruction with high accuracy and efficiency in the planning computed tomography (CT) for cervical cancer brachytherapy (BT). A novel three‐dimensional (3D) convolutional neural network (CNN) architecture was proposed and referred to as DSD‐UNET. The dataset of 91 patients received CT‐based BT of cervical cancer was used to train and test DSD‐UNET model for auto‐segmentation of high‐risk clinical target volume (HR‐CTV) and organs at risk (OARs). Automatic applicator reconstruction was achieved with DSD‐UNET‐based segmentation of applicator components followed by 3D skeletonization and polynomial curve fitting. Digitization of the channel paths for tandem and ovoid applicator in the planning CT was evaluated utilizing the data from 32 patients. Dice similarity coefficient (DSC), Jaccard Index (JI), and Hausdorff distance (HD) were used to quantitatively evaluate the accuracy. The segmentation performance of DSD‐UNET was compared with that of 3D U‐Net. Results showed that DSD‐UNET method outperformed 3D U‐Net on segmentations of all the structures. The mean DSC values of DSD‐UNET method were 86.9%, 82.9%, and 82.1% for bladder, HR‐CTV, and rectum, respectively. For the performance of automatic applicator reconstruction, outstanding segmentation accuracy was first achieved for the intrauterine and ovoid tubes (average DSC value of 92.1%, average HD value of 2.3 mm). Finally, HDs between the channel paths determined automatically and manually were 0.88 ± 0.12 mm, 0.95 ± 0.16 mm, and 0.96 ± 0.15 mm for the intrauterine, left ovoid, and right ovoid tubes, respectively. The proposed DSD‐UNET method outperformed the 3D U‐Net and could segment HR‐CTV, bladder, and rectum with relatively good accuracy. Accurate digitization of the channel paths could be achieved with the DSD‐UNET‐based method. The proposed approaches could be useful to improve the efficiency and consistency of treatment planning for cervical cancer BT.

Optical coherence tomography angiography (OCT-A) is a novel imaging modality for the diagnosis of chorioretinal diseases. A number of FDA-approved OCT-A devices are currently commercially available, each with unique algorithms and scanning protocols. Although several published studies have compared different combinations of OCT-A machines, there is a lack of agreement on the consistency of measurements across OCT-A devices. Therefore, we conducted a prospective quantitative comparison of four available OCT-A platforms. Subjects were scanned on four devices: Optovue RTVue-XR, Heidelberg Spectralis OCT2 module, Zeiss Plex Elite 9000 Swept-Source OCT, and Topcon DRI-OCT Triton Swept-Source OCT. 3 mm × 3 mm images were utilized for analysis. Foveal avascular zone (FAZ) area was separately and independently measured by two investigators. Fractal dimension (FD), superficial capillary plexus (SCP), and deep capillary plexus (DCP) vessel densities (VD) were calculated from binarized images using the Fiji image processing software. SCP and DCP VD were further calculated after images were skeletonized. Repeated measures ANOVA, post hoc tests, and interclass correlation coefficient (ICC) were performed for statistical analysis. Sixteen healthy eyes from sixteen patients were scanned on the four devices. Images of five eyes from the Triton device were excluded due to poor image quality; thus, the authors performed two sets comparisons, one with and one without the Triton machine. FAZ area showed no significant difference across devices with an ICC of > 95%. However, there were statistically significant differences for SCP and DCP VD both before and after skeletonization (p < 0.05). Fractal analysis revealed no significant difference of FD at the SCP; however, a statistically significant difference was found for FD at the DCP layer (p < 0.05). The results showed that FAZ measurements were consistent across all four devices, while significant differences in VD and FD measurements existed. Therefore, we suggest that for both clinical follow-up and research studies, FAZ area is a useful parameter for OCT-A image analysis when measurements are made on different machines, while VD and FD show significant variability when measured across devices.

PurposeTo find a successful human action recognition system (HAR) for the unmanned environments.Design/methodology/approachThis paper describes the key technology of an efficient HAR system. In this paper, the advancements for three key steps of the HAR system are presented to improve the accuracy of the existing HAR systems. The key steps are feature extraction, feature descriptor and action classification, which are implemented and analyzed. The usage of the implemented HAR system in the self-driving car is summarized. Finally, the results of the HAR system and other existing action recognition systems are compared.FindingsThis paper exhibits the proposed modification and improvements in the HAR system, namely the skeleton-based spatiotemporal interest points (STIP) feature and the improved discriminative sparse descriptor for the identified feature and the linear action classification.Research limitations/implicationsThe experiments are carried out on captured benchmark data sets and need to be analyzed in a real-time environment.Practical implicationsThe middleware support between the proposed HAR system and the self-driven car system provides several other challenging opportunities in research.Social implicationsThe authors’ work provides the way to go a step ahead in machine vision especially in self-driving cars.Originality/valueThe method for extracting the new feature and constructing an improved discriminative sparse feature descriptor has been introduced.

There are significant differences in microvascular morphological features in diseased tissues, such as cancerous lesions, compared to noncancerous tissue. Quantification of microvessel morphological features could play an important role in disease diagnosis and tumor classification. However, analyzing microvessel morphology in ultrasound Doppler is a challenging task due to limitations associated with this technique. Our main objective is to provide methods for quantifying morphological features of microvasculature obtained by ultrasound Doppler imaging. To achieve this goal, we propose multiple image enhancement techniques and appropriate morphological feature extraction methods that enable quantitative analysis of microvasculature structures. Vessel segments obtained by the skeletonization of the regularized microvasculature images are further analyzed to satisfy other constraints, such as vessel segment diameter and length. Measurements of some morphological metrics, such as tortuosity, depend on preserving large vessel trunks. To address this issue, additional filtering methods are proposed. These methods are tested on in vivo images of breast lesion and thyroid nodule microvasculature, and the outcomes are discussed. Initial results show that using vessel morphological features allows for differentiation between malignant and benign breast lesions (p-value

Spondyloarthritis (SpA) is a group of inflammatory diseases that cause severe damage in the structure of the skeleton. One of the most important features that are assessed in the diagnosis of SpA disorders and during the monitoring of the progression of this disease is the shape of the vertebrae and the appearance of bony outgrowths in the spine region. For this purpose, radiography is often used. This paper presents a novel automated method of external contour segmentation of vertebrae in X-ray images. The proposed algorithm consists of preprocessing, edge detection using the Sobel operator, binarization, area opening, and skeletonization. During the study, the impact of different filters (i.e., Gaussian filter, sigma filter, and anisotropic diffusion filter) on the quality of the results was also investigated. The method’s efficiency was tested on a dataset containing 11 lateral cervical spine radiographs. The results show that the method has the potential to become an automatic tool used by physicians to determine the shape of vertebrae.

One of the most important tasks regarding autonomous mobile robots is to plan a path for movement. Given a pre-built map, a robot is able to follow a path that is determined manually by setting way points on the map prior to exploration. However, for cases without pre-built maps, a robot has to derive its path while traveling autonomously and analyzing the surrouding environment. In this paper, we propose a method of path planning for autonomous movement under unknown environments in the case where a pre-built map does not exist. This system successfully determines way points on a road following the skeleton extracted by combining multiple data processing algorithms.

The aim of this study is to establish a novel aircraft design approach replacing the conventional airframe by utilizing biomimetics. This design approach particularly focused on the dragonfly wing, whose reinforcement structures are composed of cross- veins and longitudinal veins. The cross-veins have been emulated by weighted Centroidal Voronoi Tessellation (WCVT) following the out-of-plane displacement on the skin, while the longitudinal veins have been emulated by extracting a centerline from the topology optimization result on the skin to be reinforced, through image analysis of binarization and skeletonization. The longitudinal layout can reduce the compliance distributing the inner load with only essential reinforcement on the skin without increasing the mass. The weighted CVT layout can improve the effectiveness of the reinforced skin against buckling drastically. Thus, the skin reinforced along the cross- longitudinal layout by the topology optimization and weighted CVT pattern increased buckling load 2.7 times higher even with less mass than the conventional layout.

Kinematics is the analysis of certain parameters related to human locomotion to detect potential behaviour and gait activities of a particular subject. Gait analysis is a systematic study of motion in humans which is characterized by measurement, description, and assessment of quantities. Most research has focused solely on signal or image of movement by involving several body segments for modelling which increases research complexity and computation time. Thus, the problem raised is how to capture modelled movements using flexible methods especially for smart cities. This chapter presents an investigation on the kinematics of jogging, walking, and hand-drawn motion path. It was a search for the best possible methods for motion tracking, analysis, and recognition using a wearable sensor that can potentially be applicable in smart cities. This was done by developing a low-cost recognition system utilizing one sensor to collect kinematic data, and a skeletonization model involving one to two body segments. Signal data was analyzed using a wearable sensor that used 3-space sensing as statistical classifiers as a classification learning system. The proposed recognition system achieved an accuracy of more than 98% to recognize human activities. The results indicate that motion based on the proposed system can be identified for smart motion detection. The study has shown that human locomotion can be successfully classified by the proposed kinematic data using Explainable Artificial Intelligence (XAI).

International audience; In this paper, we propose a novel end-to-end system to extract strokes from offline math expressions. Using a multi-task neural network we simultaneously predict the location of the pen and the pen state. Our approach is based on a recent state-of-the-art image-to-sequence method limited to small fixed-sizes images. We generalize it to large and multi-symbol images without preprocessing steps such as skeletonization or binarization. This architecture allows an end-to-end training. A curriculum learning strategy have been used to address the complexity of the images. We achieve comparable results to the state of the art on the UNIPEN English character dataset considering the next point prediction. We propose a stroke level metrics that allows us to measure the stroke reconstruction. Experiments show the advantages and limitations of the adopted Image-to-Sequence method when scaling up to large and complex images such as math equations.

Background3D imaging, such as X-ray CT and MRI, has been widely deployed to study plant root structures. Many computational tools exist to extract coarse-grained features from 3D root images, such as total volume, root number and total root length. However, methods that can accurately and efficiently compute fine-grained root traits, such as root number and geometry at each hierarchy level, are still lacking. These traits would allow biologists to gain deeper insights into the root system architecture (RSA).ResultsWe present TopoRoot, a high-throughput computational method that computes fine-grained architectural traits from 3D X-ray CT images of field-excavated maize root crowns. These traits include the number, length, thickness, angle, tortuosity, and number of children for the roots at each level of the hierarchy. TopoRoot combines state-of-the-art algorithms in computer graphics, such as topological simplification and geometric skeletonization, with customized heuristics for robustly obtaining the branching structure and hierarchical information. TopoRoot is validated on both real and simulated root images, and in both cases it was shown to improve the accuracy of traits over existing methods. We also demonstrate TopoRoot in differentiating a maize root mutant from its wild type segregant using fine-grained traits. TopoRoot runs within a few minutes on a desktop workstation for volumes at the resolution range of 400^3, without need for human intervention.ConclusionsTopoRoot improves the state-of-the-art methods in obtaining more accurate and comprehensive fine-grained traits of maize roots from 3D CT images. The automation and efficiency makes TopoRoot suitable for batch processing on a large number of root images. Our method is thus useful for phenomic studies aimed at finding the genetic basis behind root system architecture and the subsequent development of more productive crops.

Small urban areas in developing countries have very little resources, especially for keep up to date maps that serves the management of the territory by public authorities. Roads are probably one of the most rapidly, but important and expensive to maintain elements in infrastructure. Use of the most available and affordable aerial imagery and the sounded deep learning technology could help in this matter. This work presents a pipeline using an Image Translation approach instead of a traditional image segmentation architecture for the extraction of urban roads directly from high resolution drone orthomosaics is presented. The results show that applying overlapping masks, multi-scale re-training and data augmentation besides skeletonization of inferred tiles output clean vector roads.

This paper proposed a novel river detection algorithm for SAR images with an improved version of OTSU algorithm. The width of the river can also be estimated using the detected results. The gray threshold, which is critical in the detection of the river, can be obtained adaptively by the proposed improved OTSU algorithm. Thus, it is more accurate than the conventional OTSU algorithm. In addition, DEM is employed in the river region extraction process to mitigate the effect of mountain shadows. The target refinement, the skeleton extraction and the endpoint removal algorithms are all devised to acquire the river centerline image. And the distance transformation algorithm is applied to generate the river distance map. Henceforth, one can estimate the river width by combining the previously acquired images. In order to create a more constant river centerline image, we employed a bridge removal procedure before the river skeletonization. The data used for the evaluation is from Sentinel 1A single-polarization data of the Yangtze River near Nanjing City, Jiangsu Province. The experiment results have shown that the proposed algorithm is more effective in the river extraction.

Thinning algorithms (TA) are commonly utilized to extract an object's functioning parameters. The skeletonization algorithm (SA) comprises of broad range of complex mathematics and involves lengthy implementations when dealing with real time (RT). Algorithms on hardware platforms can be applied to boost the efficiency of image processing applications. Reconfigurable equipment used as hardware module in the field of Field Programmable Gate Arrays (FPGAs) that can offer high performance with lower latency are being used for real world applications. FPGAs' inherent reprogramming capacity allows them application versatility while maintaining the efficiency benefits of a particular approach for an operation. Just real-time hardware devices can be used with fewer tools as in real-time implementations image sizes get larger. In the proposed architecture, the 8x8 image pixels are processed in one 3x3 window per clock cycle instead of one pixel per cycle. The proposed design shows significant reduction in area.

We introduce Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds. Existing skeletonization methods are limited to tubular shapes and the stringent requirement of watertight input, while our method aims to produce more generalized skeletal representations for complex structures and handle point clouds. Our key idea is to use the insights of the medial axis transform (MAT) to capture the intrinsic geometric and topological natures of the original input points. We first predict a set of skeletal points by learning a geometric transformation, and then analyze the connectivity of the skeletal points to form skeletal mesh structures. Extensive evaluations and comparisons show our method has superior performance and robustness. The learned skeletal representation will benefit several unsupervised tasks for point clouds, such as surface reconstruction and segmentation., Accepted to CVPR2021 (oral). Project: https://github.com/clinplayer/Point2Skeleton

Background The right gastroepiploic artery (RGEA) is a useful in-situ graft, and skeletonization is effective to prevent spasm and achieve good patency. To harvest the skeletonized RGEA easily, ultrasonic scalpel has been widely used, but the tip shape of conventional ultrasonic device was not optimal for this procedure. Recently, a novel hybrid ultrasonic/bipolar energy device (THUNDERBEAT Open Fine Jaw [TOFJ]) has been developed and is widely used in general surgery. Surgical technique The operator holds forceps in left hand and TOFJ in right hand, incises the anterior layer of the omentum, and extends the incision distally along the RGEA. The side branches and satellite veins were sealed and cut. Because the tip of the TOFJ is well-designed to easily grasp and peel off the tissue, there is no need to change instruments throughout the procedure. After the dissection was advanced distally, the proximal side was subsequently dissected. Conclusions This novel device is useful for harvesting skeletonized RGEA.

This paper presents a new approach to detect and classify skin lesions for melanoma diagnosis with high accuracy. Skin lesion detection is based on an image decomposition into two components using the Partial Differential Equation (PDE). The first component that sufficiently preserves the contour is thus exploited to have an adequate segmentation of image lesion while the second component provides a good characterization of the texture. Moreover, to improve the classification accuracy, new and powerful features extracted by skeletonization of the lesion are presented. These features are compared and combined with well-known features from the literature. Features engineering was applied to select the most relevant features to be retained for the classification phase. The proposed approach was implemented and tested on a large database and gave a good classification accuracy compared to recent approaches from the literature.

In this paper, we propose an approach for cooperative mapping of traversable ground from aerial and ground views in structured outdoor and indoor environments. The presented approach achieves a hybrid map building based on traversable ground skeletonization and graph matching. The obtained map is an augmented ground traversability map, represented as a hybrid topological/metric graph from heterogeneous sources. This approach provides a very suitable representation for ground navigation and planning. To validate this approach, the proposed algorithm is applied between aerial views, provided by a UAV flying over an experimental site, and ground maps from ground robots at different exploration stages, in realistic simulation and real-world environments.

Objective The standard combined transpetrosal approach (CTPA) is fundamentally an epidural approach that has been quite successfully practiced for many decades. However, it has some disadvantages, such as cosmetic problems, difficulties with custom-tailored petrosectomy, and cerebrospinal fluid leakage, as it is a complicated epidural procedure. We describe here a case of primary pontine hemorrhage via intradural CTPA (iCTPA), which is a modified technique of CTPA and includes intradural anterior petrosectomy and partial posterior petrosectomy without mastoidectomy and skeletonization of the sigmoid sinus. Methods A 63-year-old woman with primary pontine hemorrhage underwent surgery via iCTPA to improve postoperative functional outcomes. After the temporal craniotomy without mastoidectomy and skeletonization of the sigmoid sinus, Kawase's triangle and Trautmann's triangle were identified from the intradural space. Resection of Kawase's triangle and partial resection of Trautmann's triangle were performed to approach the frontotemporal surface of the pons. The hematoma was irrigated and totally removed after corticotomy on the pons. Results The postoperative symptoms of the patient improved within 2 weeks without surgical complication. Conclusions The intradural approach allows for custom-tailored petrosectomy and is more straightforward than the epidural route, although it can injure the vein of Labbe. Moreover, it can also reduce cosmetic problems and cerebrospinal fluid leakage. iCTPA could provide enough working space for the frontolateral surface of pontine and petroclival lesions without the need for mastoidectomy and skeletonization of the sigmoid sinus.

Introduction The anterior petrosectomy approach is among the most popular for exposure of the petroclival region. However, the complexity of the anatomy, drilling time required, and risk of injury to neurovascular structures have made this procedure especially challenging. We have proposed a novel combined extradural–intradural technique for en bloc anterior petrosectomy—or one-piece Kawase—and have charted the landmarks that define its surgical boundaries. Methods The approach was performed on 14 embalmed specimens. The one-piece Kawase approach consists of 3 extradural drilling steps, followed by incision of the dura and skeletonization of the superior petrosal sinus. The procedure culminates with 2 intradural drilling steps. The bone piece was then removed en bloc, and the maximum anteroposterior, superoinferior, and mediolateral lengths were recorded. The linear distances between the main neurovascular landmarks were also measured using a stereotactic navigation system. Results The mean measurements were 17.6 ± 2.6 mm for the anteroposterior distance, 10.5 ± 2.3 mm for the superoinferior distance, and 9.5 ± 2.6 mm for the mediolateral distance. The medial linear distance from the mandibular nerve/greater superficial petrosal nerve to the internal carotid artery was 6.8 ± 1.3 mm, to the facial hiatus was 11.6 ± 2.2 mm, and to the lateral internal acoustic canal was 17.9 ± 1.8 mm. The average distance from the porus trigeminus to the medial internal acoustic canal was 19.4 mm. Conclusions The advantages of this technique include the wide exposure of the petroclival region, extensive visualization of critical structures via extradural and intradural corridors, and minimization of bone drilling, which could reduce heat damage. Clinical application of the illustrated technique is required to test its reliability in different pathological subsets.

Human Action Recognition has been an active research topic since early 1980s due to its promising applications in many domains like video indexing, surveillance, gesture recognition, video retrieval and human-computer interactions where the actions in the form of videos or sensor datas are recognized. The extraction of relevant features from the video streams is the most challenging part. With the emergence of advanced artificial intelligence techniques, deep learning methods are adopted to achieve the goal. The proposed system presents a Recurrent Neural Network (RNN) methodology for Human Action Recognition using star skeleton as a representative descriptor of human posture. Star skeleton is the process of jointing the gross contour extremes of a body to its centroid. To use star skeleton as feature for action recognition, the feature is defined as a five-dimensional vector in star fashion because the head and four limbs are usually local extremes of human body. In our project, we assumed an action is composed of a series of star skeletons overtime. Therefore, images expressing human action which are time-sequential are transformed into a feature vector sequence. Then the feature vector sequence must be transformed into symbol sequence so that RNN can model the action. RNN is used because the features extracted are time dependent

Membrane computing is a well-known research area in computer science inspired by the organization and behavior of live cells and tissues. Their computational devices, called P systems, work in parallel and distributed mode and the information is encoded by multisets in a localized manner. All these features make P systems appropriate for dealing with digital images. In this paper, some of the open research lines in the area are presented, focusing on segmentation problems, skeletonization and algebraic-topological aspects of the images. An extensive bibliography about the application of membrane computing to the study of digital images is also provided.

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.

Raw point cloud data are often noisy, superfluous, and with topological defects, such as holes. These issues cause inaccurate geometric representation in 3D reconstruction. As a result, surface reconstruction from point cloud data is a highly challenging problem. In this paper, we address the aforementioned issues by taking advantage of the embedded information of segmentation, skeletonization, and user guidance. First, we pre-process the point cloud data with three steps, relocating each point, upsampling the point data, and optimizing normals to enhance the features and geometric details; second, a segmentation method converts the input cloud into separate parts; finally, we construct curve skeletons for each part and guide the surface reconstruction with minimal user interaction, where the parts of refined smooth shapes are fused to generate the final results. The comparison studies confirmed that the proposed method is able to produce state-of-the-art results in terms of preserving sharp features, handling missing data, and requiring minimal user intervention.

The proposed method has implemented series of steps. First the ratio of existing noise is reduced depending on Wiener Filter, followed by the stage of image borders removing in order to enrich high-density primary regions and suppress remaining ones. Thresholding stage has converted the image into a binary form, then the small foreground elements are removed in a binary image, after that the Skeletonization stage is applied in order to reduce the data points, then a matrix containing all data points which are lying on the target ellipse to be drawn. Detection of the ellipse corresponding to the limits of the fetus head in the input ultrasound image is done via the Least Square Fitting (LSF) algorithm, which returns the ellipse parameters including the minor axis which corresponds to the bi-parietal distance measure. The results of auto-measurements are compared with manual measurements of a specialist to improve the effective of the proposed method. Keywords: The Bi-Parietal Diameter BPD, Least Square Fitting algorithm, Image processing, US imaging, Fetus head, Skeletonization

Reconstructing neuron morphology is central to uncovering the complexity of the nervous system. That is because the morphology of a neuron essentially provides the physical constraints to its intrinsic electrophysiological properties and its connectivity. Recent advances in imaging technologies generated large quantities of high-resolution 3D images of neurons in the brain. Furthermore, the multispectral labeling technology, Brainbow permits unambiguous differentiation of neighboring neurons in a densely labeled brain, therefore enables for the first time the possibility of studying the connectivity between many neurons from a light microscopy image. However, lack of reliable automated neuron morphology reconstruction makes data analysis the bottleneck of extracting rich informatics in neuroscience. Supervoxel-based neuron segmentation methods have been proposed to solve this problem, however, the use of previous approaches has been impeded by the large numbers of errors which arise in the final segmentation. In this paper, we present a novel unsupervised approach to trace neurons from multispectral Brainbow images, which prevents segmentation errors and tracing continuity errors using two innovations. First, we formulate a Gaussian mixture model-based clustering strategy to improve the separation of segmented color channels that provides accurate skeletonization results for the following steps. Next, a skeleton graph approach is proposed to allow the identification and correction of discontinuities in the neuron tree topology. We find that these innovations allow our approach to outperform current state-of-the-art approaches, which results in more accurate neuron tracing as a tree representation close to human expert annotation.

The estimation of the coronary artery wall boundaries in CCTA scans is a costly but essential task in the diagnosis of cardiac diseases. To automatize this task, deep learning-based image segmentation methods are commonly used. However, in the case of coronary artery wall, even state-of-the-art segmentation methods fail to produce an accurate boundary in the presence of plaques and bifurcations. Post-processing reconstruction methods have been proposed to further refine segmentation results, but when applying general-purpose reconstruction to artery wall segmentations, they fail to reproduce the wide variety of boundary shapes. In this paper, we propose a novel method for reconstructing coronary artery wall segmentations, the Tube Beam Stack Search (TBSS). By leveraging the voxel shape of adjacent slices in a CPR volume, our TBSS is capable of finding the most plausible path of the artery wall. Similarly to the original Beam Stack Search, TBSS navigates along the voxel probabilities output by the segmentation method, reconstructing the inner and outer artery walls. Finally, skeletonization is applied on the TBSS reconstructions to eliminate noise and produce more refined segmentations. Also, since our method does not require learning a model, the lack of annotated data is not a limitation. We evaluated our method on a dataset of coronary CT angiography with curved planar reconstruction (CCTA-CPR) of 92 arteries. Experimental results show that our method outperforms the state-of-the-art work in reconstruction.

Recent advances in two-photon fluorescence microscopy (2PM) have allowed large scale imaging and analysis of blood vessel networks in living mice. However, extracting network graphs and vector representations for the dense capillary bed remains a bottleneck in many applications. Vascular vectorization is algorithmically difficult because blood vessels have many shapes and sizes, the samples are often unevenly illuminated, and large image volumes are required to achieve good statistical power. State-of-the-art, three-dimensional, vascular vectorization approaches often require a segmented (binary) image, relying on manual or supervised-machine annotation. Therefore, voxel-by-voxel image segmentation is biased by the human annotator or trainer. Furthermore, segmented images oftentimes require remedial morphological filtering before skeletonization or vectorization. To address these limitations, we present a vectorization method to extract vascular objects directly from unsegmented images without the need for machine learning or training. The Segmentation-Less, Automated, Vascular Vectorization (SLAVV) source code in MATLAB is openly available on GitHub. This novel method uses simple models of vascular anatomy, efficient linear filtering, and vector extraction algorithms to remove the image segmentation requirement, replacing it with manual or automated vector classification. Semi-automated SLAVV is demonstrated on three in vivo 2PM image volumes of microvascular networks (capillaries, arterioles and venules) in the mouse cortex. Vectorization performance is proven robust to the choice of plasma- or endothelial-labeled contrast, and processing costs are shown to scale with input image volume. Fully-automated SLAVV performance is evaluated on simulated 2PM images of varying quality all based on the large (1.4×0.9×0.6 mm3 and 1.6×108 voxel) input image. Vascular statistics of interest (e.g. volume fraction, surface area density) calculated from automatically vectorized images show greater robustness to image quality than those calculated from intensity-thresholded images., Author summary Remarkably little is known about the plasticity (i.e. adaptability) of microvasculature (i.e. capillary networks) in the adult brain because of the barriers to acquisition and processing of in vivo images. However, this basic concept is central to the field of neuroscience, and its investigation would provide insights to neurovascular conditions such as Alzheimer’s, diabetes, and stroke. Our team of (biomedical, optical, and software) engineers is developing the pipeline to image, map out, and monitor the capillary blood vessels over several weeks to months in a healthy mouse brain. One of the major challenges in this workflow is the process of extracting the capillary network roadmap from the raw volumetric microscope image. This challenge is exacerbated by in vivo imaging constraints (e.g. low/anisotropic resolution, low image quality (noise/artifacts), non-standard (tube-shaped) contrast agent). To confront these issues, we developed a general-purpose software method to extract vascular network maps from low quality images of all sorts, enabling researchers to better quantify the vascular anatomy portrayed in their images. The benefit will be a better understanding of the neurovasculature on the spatial and temporal scales relevant to fundamental cellular processes of the brain.

Soft continuum bodies have demonstrated their effectiveness in generating flexible and adaptive functionalities by capitalizing on the rich deformability of soft material. Compared with a rigid-body robot, it is in general difficult to model and emulate the morphology dynamics of a soft continuum body. In addition, a soft continuum body potentially has an infinite degree of freedom, requiring considerable labor to manually annotate its dynamics from external sensory data such as video. In this study, we propose a novel noninvasive framework for automatically extracting the skeletal dynamics from video of a soft continuum body and show the applications and effectiveness of our framework. First, we demonstrate that our framework can extract skeletal dynamics from animal videos, which can be effectively utilized for the analysis of soft continuum body including animal motion. Next, we focus on a soft continuum arm, a commonly used platform in soft robotics, and evaluate the potential information-processing capability. Normally, to control such a high-dimensional system, it is necessary to introduce many sensors to completely capture the motion dynamics, causing the deterioration of the material's softness. We illustrate that the evaluation of the memory capacity and sensory reconstruction error enables us to verify the minimum number of sensors sufficient for fully grasping the state dynamics, which is highly useful in designing a sensor arrangement for a soft robot. Also, we release the software developed in this study as open source for biology and soft robotics communities, which contributes to automating the annotation process required for the motion analysis of soft continuum bodies.

To apply topological information to solve a cervical histopathology image clustering (CHIC) problem, a graph based unsupervised learning (GBUL) approach is proposed in this paper. First, the GBUL method applies color features and k-means clustering to carry out a first-stage “coarse” clustering. Then, a skeletonization based node generation (SBNG) approach is introduced to approximate the distribution of cervical cell nuclei. Thirdly, based on the SBNG nodes, multiple graphs are constructed. Next, graph features are extracted based on the constructed graphs. Finally, k-means clustering is used again for the second-stage clustering. In the experiment, a practical Hematoxylin–eosin staining cervical histopathology image dataset with 40 whole-slide imaging images is tested, obtaining a promising CHIC result and showing a huge potential in the cancer risk prediction field.

This paper introduces a 3-D Ground Penetrating Radar Image Processing System (3DGPRIPS), which reconstructs a 3-D image from a set of subsurface images in 2-D form scanned in a sequence by ground penetration radar (GPR) device and apply various image processing operations developed in the framework of cellular logic array processing. The various 3-D image processing operations developed in the cellular logic array processing framework are: point detection, edge detection, surface detection, thinning, skeletonization and directional textures etc. In the results section performance of Cellular Logic Array Processing (CLAP) based edge detection algorithm is compared against Morphological Based Edge detection algorithms.

Finger vein authentication system (FVAS) is more secure than other forms of authentication, such as signatures and fingerprint authentication. This is because of the fact that veins are present beneath the human skin, which makes them nearly impossible to replicate. Furthermore, the vein pattern remains persistent during the span of a person's life, so it eliminates the risk of alterations in contrast to fingerprint and iris biometrics. In fingerprints, the ridges begin wearing out and start getting spaced out as a person ages. By using Iris authentication, if a person gets a cataract surgery, the iris pattern is altered, which causes a significant problem for security systems. In this paper, the authors plan to develop an authentication system using a finger vein spattern as a unique biometric. An image of the target finger is captured with the help of a Near-Infrared (NIR) camera under the Infrared (IR) light transmission. This NIR camera produces images of the finger containing vein patterns. The image additionally contains various shades produced by the thickness of finger muscles, bones, and tissue networks surrounding the vein. This paper focuses on developing a system to identify finger veins and the procedure to make transactions secure. The proposed method provides an accuracy of over 90% using filtering methods such as Segmentation, Gabor filtering, Masking, and Skeletonization of the image to extract ROI, which will be used for comparison and assist in lowering the occurrences of forgery instances that are caused by other biometrics. The identity of a user is registered through their finger vein image and stored in the database which will be used to test against future authentication thus making sure that the finger vein cannot be replaced.

In this paper the properties of the generalized conics are used to create a unified framework for generating various types of the distance fields. The main concept behind this work is a metric that measures the distance from a point to a line segment according to the definition of the ellipse. The proposed representation provides a possibility to efficiently compute the proximity, arithmetic mean of the distances and a space tessellation with regard to the given set of polygonal objects, line segments and points. In addition, the weights can be introduced for objects, their parts and combinations. This fact leads to a hierarchical representation that can be efficiently obtained using the pixel-wise operations. The practical value of the proposed ideas is demonstrated on an example of applications like skeletonization, smoothing and optimal location finding.

Vessel centerline extraction is fundamental for plentiful medical applications. Majority of current methods require pre-segmentations, distance maps or similar sorts of scanning whole volume action and followed by minimal-path or skeletonization algorithms. In this paper, we demonstrate a deep reinforced tree-traversal agent that automatically traces tree-structure centerlines assuming no post-prune or post-merging. It takes raw images as input and generates tree-structure centerlines naturally. To this end, road mark and dynamic reward mechanisms are proposed to make tree-structure vessels learnable and impart the agent how to learn correspondingly. Besides, a multi-task discriminator is raised to simultaneously detect bifurcations and decide terminations. We experimentally show that traced centerlines have an overlap of more than 90% and a distance less than 0.25 mm with annotated reference centerlines on coronary arteries. Beyond the promising accuracy, the proposed method also surpasses other existing methods by a large margin in terms of the time and memory efficiency. And a flexible trade-off between accuracy and time efficiency is exhibited at the inference. Codes are available at https://github.com/LzVv123456/Deep-Reinforced-Tree-Traversal.

Nowadays one of the most popular topics in fingerprint recognition academic research is the high-resolution fingerprint identification way. This technique has been prominently attractive to the worldwide scientific community thanks to the possibility of using level 3 features like pores which cannot be detected in lower resolution images. In this context, this chapter proposes two contributions: First, a pore detection method for high-resolution fingerprint image based on the morphological operation (skeletonization) and the labeled connect component method. Second, a new method to match pores without an alignment. Our matching approach is based on the contextual characteristics of the pore. It consists of positions and orientations of pore neighbors, which are defined as polar coordinates given in the polar system centered on the considered pore. The proposed algorithms are tested on a high-resolution fingerprint database. Experimental results show that our methods outperform the existing algorithms.