Intrinsic Hierarchical Clustering Behavior Recovers Higher Dimensional Shape Information

SUMMARYIn this paper, we investigate the problem of measuring the shape of a continuum robot manipulator using visual information from a fixed camera. Specifically, we capture the motion of a set of fictitious planes, each formed by four or more feature points, defined at various strategic locations along the body of the robot. Then, utilizing expressions for the robot forward kinematics as well as the decomposition of a homography relating a reference image of the robot to the actual robot image, we obtain the three-dimensional shape information continuously. We then use this information to demonstrate the development of a kinematic controller to regulate the manipulator end-effector to a constant desired position and orientation.

Download Full-text

Towards Developing a Practical System to Recover Light, Reflectance and Shape

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001497000457 ◽

1997 ◽

Vol 11 (06) ◽

pp. 991-1022 ◽

Cited By ~ 1

Author(s):

Sanjay Bakshi ◽

Yee-Hong Yang

Keyword(s):

Shape Recovery ◽

Three Dimensional ◽

Shape From Shading ◽

Modular System ◽

Surface Reflectance ◽

Shape Information ◽

Light Reflectance ◽

Dimensional Shape ◽

Lambertian Reflectance ◽

Point Light

Due to the complexity of the shape-from-shading problem, most solutions rely on idealistic conditions. Orthographic imaging, a known distant point light source, and known surface reflectance properties are usually assumed. Furthermore, most real surfaces are neither perfectly diffuse (Lambertian) nor ideally specular (mirror-like); however most shape-from-shading algorithms assume Lambertian reflectance. The behavior of shape-from-shading algorithms that rely on idealistic conditions is unpredictable in real imaging situations. In this paper, the LIRAS (LIght, Reflectance, And Shape) Recovery System is proposed. LIRAS is a practical approach to the shape-from-shading problem, as many of these assumptions are relaxed. LIRAS is also a modular system: there is a component that recovers the surface reflectance properties, thus the assumption of Lambertian reflectance is relaxed. Rather than assume a known illuminant direction, a component exists that can recover the light orientation. Once the reflectance map is determined, another LIRAS module can use this information to recover the shape for non-Lambertian surfaces. Each of these modules is described and a discussion of how the components cooperate to recover three-dimensional shape information in real environments is given. Extensive experimental evaluation is conducted using both synthetic and real images and the results are very encouraging. The contributions of this paper include the design and implementation of LIRAS and the extensive quantative and qualitative experimental results, which can provide guidelines for future refinements of other shape recovery systems.

Download Full-text

A Model Selection Approach to Hierarchical Shape Clustering with an Application to Cell Shapes

10.1101/2020.04.29.067892 ◽

2020 ◽

Author(s):

Mina Mirshahi ◽

Vahid Partovi-Nia ◽

Masoud Asgharian

Keyword(s):

Model Selection ◽

Hierarchical Clustering ◽

Linear Models ◽

Clustering Methods ◽

Shape Information ◽

Novel Approach ◽

Model Selection Approach ◽

Cell Shapes ◽

Living Species ◽

Shape Clustering

AbstractShape is an important phenotype of living species that contain different environmental and genetic information. Clustering living cells using their shape information can provide a preliminary guide to their functionality and evolution. Hierarchical clustering and dendrograms, as a visualization tool for hierarchical clustering, are commonly used by practitioners for classification and clustering. The existing hierarchical shape clustering methods are distance based. Such methods often lack a proper statistical foundation to allow for making inference on important parameters such as the number of clusters, often of prime interest to practitioners. We take a model selection perspective to clustering and propose a shape clustering method through linear models defined on Spherical Harmonics expansions of shapes. We introduce a BIC-type criterion, called CLUSBIC, and study consistency of the criterion. Special attention is paid to the notions of over- and under-specified models, important in studying model selection criteria and naturally defined in model selection literature. These notions do not automatically extend to shape clustering when a model selection perspective is adopted for clustering. To this end we take a novel approach using hypothesis testing. We apply our proposed criterion to cluster a set of real 3D images from HeLa cell line.

Download Full-text

Three-Dimensional Shape Information Acquisition Using Binocular Stereo Vision for Reflective Steel Plate

Proceedings of the 2019 3rd International Conference on Graphics and Signal Processing - ICGSP '19 ◽

10.1145/3338472.3338491 ◽

2019 ◽

Author(s):

Xin Wen ◽

Ke-Chen Song

Keyword(s):

Stereo Vision ◽

Information Acquisition ◽

Steel Plate ◽

Three Dimensional ◽

Shape Information ◽

Binocular Stereo Vision ◽

Binocular Stereo ◽

Dimensional Shape ◽

Three Dimensional Shape

Download Full-text

Specific Shape Characterization of Carbon Black Primary Units

Rubber Chemistry and Technology ◽

10.5254/1.3545012 ◽

1973 ◽

Vol 46 (1) ◽

pp. 204-231 ◽

Cited By ~ 21

Author(s):

W. M. Hess ◽

G. C. McDonald ◽

E. Urban

Keyword(s):

Image Analysis ◽

Carbon Black ◽

Full Range ◽

Image Analysis System ◽

Unit Size ◽

Shape Information ◽

Dimensional Shape ◽

Specific Shape ◽

Analysis System

Abstract A full field feature specific image analysis system has been developed for direct morphological characterization of carbon black in the electron microscope. The system provides quantitative size and non-dimensional shape information, as well as qualitative classification into specific shape categories using pattern recognition programming methods. Data on samplings of 500–1000 primary black units can be recorded on magnetic tape in less than 10 minutes. Although not yet tested on a full range of rubber grade blacks, the new system has demonstrated good sensitivity in resolving morphological differences among a series of four HAF blacks of varied DBP absorption. The blacks exhibited large frequency variations across nine specific shape categories which range from spheroidal to fibrous types. Within each category, the unit size and non-dimensional shape factors were similar for all four blacks. On a composite average basis, however, large differences in unit size (longest dimension or projected area), anisometry (length/width ratio), and irregularity (perimeter/area ratio) were observed. The new image analysis system also has the capability of volume measurements based on microdensitometry. Although data is limited at this time, such measurements should provide more three-dimensional approximations of carbon black unit size. It is also anticipated that microdensitometry will aid in the determination of domain (particle) size.

Download Full-text