|
Title:
|
AUTOMATIC DETECTION OF SPINAL DEFORMITY BY USE OF DENSITY FEATURES FROM MOIRE TOPOGRAPHIC IMAGES |
|
Author(s):
|
Hyoungseop Kim , Satoshi Nakano , Joo Kooi Tan , Seiji Ishikawa , Takashi Shinomiya |
|
ISBN:
|
978-972-8924-63-8 |
|
Editors:
|
Yingcai Xiao and Eleonore ten Thij |
|
Year:
|
2008 |
|
Edition:
|
Single |
|
Keywords:
|
Pattern recognition, Image analysis, Image classification, Artificial Neural networks |
|
Type:
|
Short Paper |
|
First Page:
|
239 |
|
Last Page:
|
243 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Spinal deformity is a serious disease, mainly suffered by teenagers, during their growth stage. To detect the spinal
deformity in early stage, orthopedists have traditionally performed a painless examination called a forward bending test
or moire topographic image test in mass screening of school. In this paper, we propose a method for automatic detection
of spinal deformity from moire topographic images by using the asymmetric feature which is obtained human back. We
classified the unknown moire image employing artificial neural network which trained by back propagation. The
proposed technique is applied to 1200 real moire topographic images, 85.4% of unknown moire images were successfully
classified correctly. Some experimental results are shown along with discussions. |
|
|
|
|
|
|
