Using haptic and neural networks for surface and mechanical properties 3D reconstruction

Authors:
Efrain Castillo-Muñiz;Jorge Rivera-Rovelo;Eduardo Bayro-Corrochano
Affiliations:
CINVESTAV del IPN, Unidad Guadalajara, Mexico;Division de Ingenieria, Universidad Anahuac Mayab, Mexico;CINVESTAV del IPN, Unidad Guadalajara, Mexico
Venue:
UCAmI'12 Proceedings of the 6th international conference on Ubiquitous Computing and Ambient Intelligence
Year:
2012

Citing 6
Cited 0

Marching cubes: A high resolution 3D surface construction algorithm

SIGGRAPH '87 Proceedings of the 14th annual conference on Computer graphics and interactive techniques
Fast exact and approximate geodesics on meshes

ACM SIGGRAPH 2005 Papers
A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Poisson surface reconstruction

SGP '06 Proceedings of the fourth Eurographics symposium on Geometry processing
A multi-resolution statistical deformable model (MISTO) for soft-tissue organ reconstruction

Pattern Recognition
A general regression neural network

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The use of haptic interfaces in surgery could provide the surgeon useful sensing information about the patient tissues. Our goal in this work, is to use the haptic interface to obtain some sample points on the surface of an object or organ tissue in medical applications. This elasticity information feeds an artificial neural network. The output of the neural network is an approximation of the compliance of the object which is touched, as well as the coordinates of 3D surface points which in fact are used for the 3D surface reconstruction of the object. Experimental results show that the reconstruction of objects from a elasticity point of view is possible, and that the use of a haptic interface can improve the performance of 3D reconstruction algorithms.