Medial Skeleton Research Articles

Research on a U-Net Bridge Crack Identification and Feature-Calculation Methods Based on a CBAM Attention Mechanism

Crack detection on bridges is an important part of assessing whether a bridge is safe for service. The methods using manual inspection and bridge-inspection vehicles have disadvantages, such as low efficiency and affecting road traffic. We have conducted an in-depth study of bridge-crack detection methods and have proposed a bridge crack identification algorithm for Unet, called the CBAM-Unet algorithm. CBAM (Convolutional Block Attention Module) is a lightweight convolutional attention module that combines a channel attention module (CAM) and a spatial attention module (SAM), which use an attention mechanism on a channel and spatially, respectively. CBAM takes into account the characteristics of bridge cracks. When the attention mechanism is used, the ability to express shallow feature information is enhanced, making the identified cracks more complete and accurate. Experimental results show that the algorithm can achieve an accuracy of 92.66% for crack identification. We used Gaussian fuzzy, Otsu and medial skeletonization algorithms to realise the post-processing of an image and obtain a medial skeleton map. A crack feature measurement algorithm based on the skeletonised image is proposed, which completes the measurement of the maximum width and length of the crack with errors of 1–6% and 1–8%, respectively, meeting the detection standard. The bridge crack feature extraction algorithm we present, CBAM-Unet, can effectively complete the crack-identification task, and the obtained image segmentation accuracy and parameter calculation meet the standards and requirements. This method greatly improves detection efficiency and accuracy, reduces detection costs and improves detection efficiency.

Reconstruction of tubular structures from 2.5D point clouds: A mesophotic gorgonian coral case study

A method for the surface reconstruction of 3D tubular branched structures characterized by low informative point clouds (i.e., 2.5D) is proposed. These specific clouds can arise when using photogrammetry techniques on complex subjects in challenging scanning environments (e.g., underwater gorgonian coral at mesophotic depths). The core idea behind the proposed Sphere Skeleton Approach (SSA) is to approximate the assumed tubular shapes via merged spheres having variable radii and centered in the points of the medial skeleton. To assess the generality and robustness of the proposed SSA, additional experiments have been conducted on 2.5D point clouds that were synthetically generated from 3D model benchmarks. Hausdorff distances between the target and the reconstructed 3D models are used to quantitatively compare the SSA performances to a classical meshing algorithm. Early results highlight the capability to outperform existing approaches in reconstructing objects from 2.5D clouds.

Automatic triangulated mesh generation of pulmonary airways from segmented lung 3DCTs for computational fluid dynamics.

Computational fluid dynamics (CFD) of lung airflow during normal and pathophysiological breathing provides insight into regional pulmonary ventilation. By integrating CFD methods with 4D lung imaging workflows, regions of normal pulmonary function can be spared during treatment planning. To facilitate the use of CFD simulations in a clinical setup, a robust, automated, and CFD-compliant airway mesh generation technique is necessary. We define a CFD-compliant airway mesh to be devoid of blockages of airflow and leaks in the airway path, both of which are caused by airway meshing errors that occur when using conventional meshing techniques. We present an algorithm to create a CFD-compliant airway mesh in an automated manner. Beginning with a medial skeleton of the airway segmentation, the branches were tracked, and 3D points at which bifurcations occur were identified. Airway branches and bifurcation features were isolated to allow for automated and careful meshing that considered their anatomical nature. We present the meshing results from three state-of-the-art tools and compare them with the meshes generated by our algorithm. The results show that fully CFD-compliant meshes were automatically generated for an ideal geometry and patient-specific CT scans. Using an open-source smoothed-particle hydrodynamics CFD implementation, we compared the airflow using our approach and conventionally generated airway meshes. Our meshing algorithm was able to successfully generate a CFD-compliant mesh from pre-segmented lung CT scans, providing an automatic meshing approach that enables interventional CFD simulations to guide lung procedures such as radiotherapy or lung volume reduction surgery.

AUTNT - A component level dataset for text non-text classification and benchmarking with novel script invariant feature descriptors and D-CNN

Automated scene text recognition from camera images is considered as a pioneer research area through last few decades. Classification of foreground object components from camera images is an essential step of Text Information Extraction (TIE). Text/Non-text separation from complex document images as well as unstructured natural images is still a challenging task. Although, some works have been reported in this direction, component level standard benchmark datasets for specifically text/non-text classification are not available. In this paper, a new multi-script dataset of text and non-text components have been reported along with multi-purpose ground truth annotations. A novel feature set is also designed on the basis of distance information of medial skeleton points to set benchmark performance on this dataset. Also, a Deep Convolution Neural Network (D-CNN) based automated feature extraction and classification framework is developed for benchmarking purpose. More insight is put forward by conducting separate assessment of current two benchmark methods on component images originated from documents and natural scenes. Experimental results show that classification accuracy is over 94.00% for medial skeleton based feature descriptors and over 96.00% for D-CNN framework on both types of sources, which is pretty impressive in practical scenario.

Mean Curvature Skeletons

AbstractInspired by recent developments in contraction‐based curve skeleton extraction, we formulate the skeletonization problem via mean curvature flow (MCF). While the classical application of MCF is surface fairing, we take advantage of its area‐minimizing characteristic to drive the curvature flow towards the extreme so as to collapse the input mesh geometry and obtain a skeletal structure. By analyzing the differential characteristics of the flow, we reveal that MCF locally increases shape anisotropy. This justifies the use of curvature motion for skeleton computation, and leads to the generation of what we call “mean curvature skeletons”. To obtain a stable and efficient discretization, we regularize the surface mesh by performing local remeshing via edge splits and collapses. Simplifying mesh connectivity throughout the motion leads to more efficient computation and avoids numerical instability arising from degeneracies in the triangulation. In addition, the detection of collapsed geometry is facilitated by working with simplified mesh connectivity and monitoring potential non‐manifold edge collapses. With topology simplified throughout the flow, minimal post‐processing is required to convert the collapsed geometry to a curve. Formulating skeletonization via MCF allows us to incorporate external energy terms easily, resulting in a constrained flow. We define one such energy term using the Voronoi medial skeleton and obtain a medially centred curve skeleton. We call the intermediate results of our skeletonization motion meso‐skeletons; these consist of a mixture of curves and surface sheets as appropriate to the local 3D geometry they capture.

An alternate smoothing and stripping algorithm for thinning digital binary patterns

This paper presents an algorithm for thinning digital binary patterns (skeletonization). The algorithm consists of two phases. The first phase thins the input pattern to unit thickness by alternately smoothing of the pattern and stripping of the contour points. The second phase adjusts the resulting skeleton from phase one so that a medial skeleton can be obtained. The performance of this algorithm is first compared experimentally with recent results of two other research groups and then with nine other skeletonization algorithms proposed by other researchers. Results show that the alternate smoothing and stripping algorithm produces skeletons which are smooth and with least distortion and well-formed than the others.