Robust cephalometric landmark identification using support vector machines

Shantanu Chakrabartty, Masakazu Yagi, Tadashi Shibata, Gert Cauwenberghs

Research output: Contribution to journalConference articlepeer-review

17 Scopus citations

Abstract

A robust and accurate image recognizer for cephalometric landmarking is presented. The recognizer uses Gini Support Vector Machine (SVM) to model discrimination boundaries between different landmarks and also between the background frames. Large Margin Classification with non-linear kernels allows to extract relevant details from the landmarks, approaching human expert levels of recognition. In conjunction with Projected Principal-Edge Distribution (PPED) representation as feature vectors, GiniSVM is able to demonstrate more than 95% accuracy for landmark detection on medical cephalograms within a reasonable location tolerance value.

Original languageEnglish
Pages (from-to)825-828
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2
StatePublished - 2003
Event2003 IEEE International Conference on Accoustics, Speech, and Signal Processing - Hong Kong, Hong Kong
Duration: Apr 6 2003Apr 10 2003

Fingerprint

Dive into the research topics of 'Robust cephalometric landmark identification using support vector machines'. Together they form a unique fingerprint.

Cite this