Extracting 3D Parametric Curves from 2D Images of Helical Objects

Willcocks, Chris G.; Jackson, Philip T.; Nelson, Carl J.; Obara, Bogusław

doi:10.1109/tpami.2016.2613866

Cited by 11 publications

(6 citation statements)

References 41 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach is having many trigonometric and curve approximation computations involved to reach to the feature vector which reduces performance of the system. An effective representation method was proposed in [18] that makes use of both concavities and convexities of all curvature points. The multi scale convexity concavity (MCC) defines the feature for different Gaussian kernels and derived as the boundary point of each contour point of the previous level.…”

Section: Related Workmentioning

confidence: 99%

Position Invariant Spline Curve Based Image Retrieval Using Control Points

Pande¹,

Chetty²

2019

IJIES

View full text Add to dashboard Cite

In this paper Cubic Bezier curve-based image retrieval system is proposed. This system evaluates similarity of each image in its database to a query image in terms of shape characteristics. Then, returns those images within a desired range of similarity. The proposed system determines nonlinear relationship between image's features for more accurate similarity comparison between query image and existing database images. Among existing approaches to shape feature analysis, statistical approach to extract shape features is adopted here. It works in form of control points of spline curves from both given query image and images of available database. These control points are further used to find out the Fourier Descriptors. Control points and Fourier descriptors are used for image retrieval in proposed system. With the vast number of images available on-line, quality CBIR systems are critical. The performance and results obtained by proposed system are compared to other CBIR systems. Comparison reveals proposed system performance is state of the art. In many parameters it outperforms other CBIR systems.

show abstract

Section: Related Workmentioning

confidence: 99%

Position Invariant Spline Curve Based Image Retrieval Using Control Points

Pande¹,

Chetty²

2019

IJIES

View full text Add to dashboard Cite

show abstract

“…6 red dashed line). The centerline is calculated using the approach proposed in [35], but extended to 3D. Specifically, each coordinate of the 'centerline' is defined to be the centroid of the slice:…”

Section: E Measurementsmentioning

confidence: 99%

“…where Ψ i ⊂ Ω ⊂ 2 is a set of the binary segmented pixels for the i th slice (in the y-axis) in the macular hole after the cutting procedure. The centerline is then smoothed using robust local regression [36], as in the paper [35], using a smoothing parameter (in our case we choose 0.9 to represent a span of 90% of the signal). This is important as it ensures the centerline acts as a descriptor for the overall shape and direction of the hole (especially in the middle as we are not concerned about the centerline veering off at the top and base of the hole) and ensures that it remains highly insensitive to surface noise.…”

Section: E Measurementsmentioning

confidence: 99%

Multi-Scale Segmentation and Surface Fitting for Measuring 3-D Macular Holes

Nasrulloh

Willcocks

Jackson

et al. 2018

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Macular holes are blinding conditions, where a hole develops in the central part of retina, resulting in reduced central vision. The prognosis and treatment options are related to a number of variables, including the macular hole size and shape. High-resolution spectral domain optical coherence tomography allows precise imaging of the macular hole geometry in three dimensions, but the measurement of these by human observers is time-consuming and prone to high inter- and intra-observer variability, being characteristically measured in 2-D rather than 3-D. We introduce several novel techniques to automatically retrieve accurate 3-D measurements of the macular hole, including: surface area, base area, base diameter, top area, top diameter, height, and minimum diameter. Specifically, we introduce a multi-scale 3-D level set segmentation approach based on a state-of-the-art level set method, and we introduce novel curvature-based cutting and 3-D measurement procedures. The algorithm is fully automatic, and we validate our extracted measurements both qualitatively and quantitatively, where our results show the method to be robust across a variety of scenarios. Our automated processes are considered a significant contribution for clinical applications.

show abstract

“…Scientists proposed different approaches in fi nding 3D helical curve from 2D data, like using generalized helicoids (Piuze et al, 2011), computing based on matching the input curve by its orthogonal projection (Cherin et al, 2014), or based on the best approximation of noisy input (Cordier et al, 2016). Willcocks et al (2016) introduced an algorithm to fi nd 3D parametric curves in three steps. In the fi rst step, they compute the main structural curve, as the main part of the computed 2D morphological skeleton.…”

Section: Algorithms In Shape Analysismentioning

confidence: 99%

Area collapse algorithm computing new curve of 2D geometric objects

Buczek

2017

Geodesy and Cartography

View full text Add to dashboard Cite

The processing of cartographic data demands human involvement. Up-to-date algorithms try to automate a part of this process. The goal is to obtain a digital model, or additional information about shape and topology of input geometric objects. A topological skeleton is one of the most important tools in the branch of science called shape analysis. It represents topological and geometrical characteristics of input data. Its plot depends on using algorithms such as medial axis, skeletonization, erosion, thinning, area collapse and many others. Area collapse, also known as dimension change, replaces input data with lower-dimensional geometric objects like, for example, a polygon with a polygonal chain, a line segment with a point. The goal of this paper is to introduce a new algorithm for the automatic calculation of polygonal chains representing a 2D polygon. The output is entirely contained within the area of the input polygon, and it has a linear plot without branches. The computational process is automatic and repeatable. The requirements of input data are discussed. The author analyzes results based on the method of computing ends of output polygonal chains. Additional methods to improve results are explored. The algorithm was tested on real-world cartographic data received from BDOT/GESUT databases, and on point clouds from laser scanning. An implementation for computing hatching of embankment is described.

show abstract

Extracting 3D Parametric Curves from 2D Images of Helical Objects

Cited by 11 publications

References 41 publications

Position Invariant Spline Curve Based Image Retrieval Using Control Points

Position Invariant Spline Curve Based Image Retrieval Using Control Points

Multi-Scale Segmentation and Surface Fitting for Measuring 3-D Macular Holes

Area collapse algorithm computing new curve of 2D geometric objects

Contact Info

Product

Resources

About