Automatic Detection of Anatomical Features on 3D Ear Impressions for Canonical Representation

摘要：

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.

作者: Sajjad Baloch Rupen Melkisetoglu Simon Flory Sergei Azernikov Greg Slabaugh Alexander Zouhar Tong Fang

作者单位: Siemens Corporate Research, Princeton, NJ, USA Vienna University of Technology, Wien, Austria Medicsight PLC, London, UK

会议类型: 国际会议

会议名称: The 13th International Conference on Medical Image Computing and Computer-Assisted Intervention(第13届医学影像计算与计算机辅助介入国际会议 MICCAI 2010)

会议地点: 北京

会议语种:英文

页码: 555–562

在线出版日期: 2010-09-01（万方平台首次上网日期，不代表论文的发表时间）