Robust cephalometric landmark identification using support vector machines

Shantanu Chakrabartty; Masakazu Yagi; Tadashi Shibata; Gert Cauwenberghs

Robust cephalometric landmark identification using support vector machines

Shantanu Chakrabartty, Masakazu Yagi, Tadashi Shibata, Gert Cauwenberghs

Research output: Contribution to journal › Conference article › peer-review

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 language	English
Pages (from-to)	825-828
Number of pages	4
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2
State	Published - 2003
Event	2003 IEEE International Conference on Accoustics, Speech, and Signal Processing - Hong Kong, Hong Kong Duration: Apr 6 2003 → Apr 10 2003

Cite this

@article{61396f4e84fb4901a45a553db3e20eed,

title = "Robust cephalometric landmark identification using support vector machines",

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.",

author = "Shantanu Chakrabartty and Masakazu Yagi and Tadashi Shibata and Gert Cauwenberghs",

year = "2003",

language = "English",

volume = "2",

pages = "825--828",

journal = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

issn = "1520-6149",

note = "2003 IEEE International Conference on Accoustics, Speech, and Signal Processing ; Conference date: 06-04-2003 Through 10-04-2003",

}

TY - JOUR

T1 - Robust cephalometric landmark identification using support vector machines

AU - Chakrabartty, Shantanu

AU - Yagi, Masakazu

AU - Shibata, Tadashi

AU - Cauwenberghs, Gert

PY - 2003

Y1 - 2003

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0141565089&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0141565089

SN - 1520-6149

VL - 2

SP - 825

EP - 828

JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

T2 - 2003 IEEE International Conference on Accoustics, Speech, and Signal Processing

Y2 - 6 April 2003 through 10 April 2003

ER -

Robust cephalometric landmark identification using support vector machines

Abstract

Other files and links

Fingerprint

Cite this