A Localization and Extraction Method Research for Phalange ROI and Carpal ROI from Left Hand Radiography

Abstract:

Article Preview

In the research of Automatic bone age assessment,the most efficient location and successful extraction of regions of interest(ROI) from hand radiographs is one of the most difficult and important key technologies. Based on using shape information for phalanges and carpals, a background prediction method is propoesd , which uses a two-dimensional third order polynomial linear regression to fit background. And we also localize the key points of carpal and phalange ROI by using K-cosine algorithm, finally we extract the carpal and phalange ROI successfully and properly. Through experiments, the proposed method resulted in over 93% correct extraction from more than 60 left hand radiograph data. The proposed method is robust to gray value variation of background and the position and orientation of the hand, so it can be used directly for automatic bone age assessment in the following study.

Info:

Periodical:

Edited by:

Honghua Tan

Pages:

259-265

DOI:

10.4028/www.scientific.net/AMR.340.259

Citation:

L. K. Ran et al., "A Localization and Extraction Method Research for Phalange ROI and Carpal ROI from Left Hand Radiography", Advanced Materials Research, Vol. 340, pp. 259-265, 2012

Online since:

September 2011

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.