Automatic detection of anatomical features on 3D ear impressions for canonical representation

Authors:
Sajjad Baloch;Rupen Melkisetoglu;Simon Flöry;Sergei Azernikov;Greg Slabaugh;Alexander Zouhar;Tong Fang
Affiliations:
Siemens Corporate Research, Princeton, NJ;Siemens Corporate Research, Princeton, NJ;Vienna University of Technology, Wien, Austria;Siemens Corporate Research, Princeton, NJ;Medicsight PLC, London, UK;Siemens Corporate Research, Princeton, NJ;Siemens Corporate Research, Princeton, NJ
Venue:
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part III
Year:
2010

Citing 4
Cited 3

Three-dimensional distance field metamorphosis

ACM Transactions on Graphics (TOG)
Constructing a Reeb graph automatically from cross sections

IEEE Computer Graphics and Applications
Crest Lines for Surface Segmentation and Flattening

IEEE Transactions on Visualization and Computer Graphics
Smooth feature lines on surface meshes

SGP '05 Proceedings of the third Eurographics symposium on Geometry processing

Feature driven rule based framework for automatic modeling of organic shapes in the design of personalized medical prosthetics

MIAR'10 Proceedings of the 5th international conference on Medical imaging and augmented reality
Deformable registration of organic shapes via surface intrinsic integrals: application to outer ear surfaces

MCV'10 Proceedings of the 2010 international MICCAI conference on Medical computer vision: recognition techniques and applications in medical imaging
Toward automation in hearing aid design

Computer-Aided Design

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a shape descriptor for 3D ear impressions, derived from a comprehensive set of anatomical features. Motivated by hearing aid (HA) manufacturing, the selection of the anatomical features is carried out according to their uniqueness and importance in HA design. This leads to a canonical ear signature that is highly distinctive and potentially well suited for classification. First, the anatomical features are characterized into generic topological and geometric features, namely concavities, elbows, ridges, peaks, and bumps on the surface of the ear. Fast and robust algorithms are then developed for their detection. This indirect approach ensures the generality of the algorithms with potential applications in biomedicine, biometrics, and reverse engineering.