Spinal deformity detection employing back propagation on neural network
We propose a new technique for automatic spinal deformity detection from moire topographic images. Normally the moire stripes of a human body show a symmetric pattern. According to the progress of the deformity of a spine, asymmetry becomes larger. Numerical representation of the degree of asymmetry...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Book Section |
| Published: |
Springer
2005
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/7172/ https://link.springer.com/chapter/10.1007%2F11552499_79 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1845471758696579072 |
|---|---|
| author | Kim, H. Tan, J. K. Ishikawa, S. Khalid, Marzuki Viergever, M. Otsuka, Y. Shinomiya, T. |
| author2 | S., Singh |
| author_facet | S., Singh Kim, H. Tan, J. K. Ishikawa, S. Khalid, Marzuki Viergever, M. Otsuka, Y. Shinomiya, T. |
| author_sort | Kim, H. |
| building | UTM Library |
| collection | Institutional Repository |
| content_provider | Universiti Teknologi Malaysia |
| content_source | UTM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | We propose a new technique for automatic spinal deformity detection from moire topographic images. Normally the moire stripes of a human body show a symmetric pattern. According to the progress of the deformity of a spine, asymmetry becomes larger. Numerical representation of the degree of asymmetry is therefore useful in evaluating the deformity. Displacement of local centroids and difference of gray value are calculated between the left-hand side and the right-hand side regions of the moire images with respect to the extracted middle line. Extracted 4 feature vectors (mean value and standard deviation from the each displacement) from the left-hand side and right-hand side rectangle areas apply to train a neural network. An experiment was performed employing 1,200 real moire images and 90.3% of the images were classified correctly.
|
| format | Book Section |
| id | my.utm.eprints-7172 |
| institution | Universiti Teknologi Malaysia |
| publishDate | 2005 |
| publisher | Springer |
| record_format | eprints |
| spelling | my.utm.eprints-71722017-08-13T07:59:29Z http://eprints.utm.my/7172/ Spinal deformity detection employing back propagation on neural network Kim, H. Tan, J. K. Ishikawa, S. Khalid, Marzuki Viergever, M. Otsuka, Y. Shinomiya, T. QH426 Genetics We propose a new technique for automatic spinal deformity detection from moire topographic images. Normally the moire stripes of a human body show a symmetric pattern. According to the progress of the deformity of a spine, asymmetry becomes larger. Numerical representation of the degree of asymmetry is therefore useful in evaluating the deformity. Displacement of local centroids and difference of gray value are calculated between the left-hand side and the right-hand side regions of the moire images with respect to the extracted middle line. Extracted 4 feature vectors (mean value and standard deviation from the each displacement) from the left-hand side and right-hand side rectangle areas apply to train a neural network. An experiment was performed employing 1,200 real moire images and 90.3% of the images were classified correctly. Springer S., Singh 2005 Book Section PeerReviewed Kim, H. and Tan, J. K. and Ishikawa, S. and Khalid, Marzuki and Viergever, M. and Otsuka, Y. and Shinomiya, T. (2005) Spinal deformity detection employing back propagation on neural network. In: Pattern Recognition and Image Analysis. Lecture Notes in Computer Science, 3687 . Springer , Berlin / Heidelberg, pp. 719-725. ISBN 978-3-540-28833-6 https://link.springer.com/chapter/10.1007%2F11552499_79 10.1007/11552499 |
| spellingShingle | QH426 Genetics Kim, H. Tan, J. K. Ishikawa, S. Khalid, Marzuki Viergever, M. Otsuka, Y. Shinomiya, T. Spinal deformity detection employing back propagation on neural network |
| title | Spinal deformity detection employing back propagation on neural network |
| title_full | Spinal deformity detection employing back propagation on neural network |
| title_fullStr | Spinal deformity detection employing back propagation on neural network |
| title_full_unstemmed | Spinal deformity detection employing back propagation on neural network |
| title_short | Spinal deformity detection employing back propagation on neural network |
| title_sort | spinal deformity detection employing back propagation on neural network |
| topic | QH426 Genetics |
| url | http://eprints.utm.my/7172/ https://link.springer.com/chapter/10.1007%2F11552499_79 |
| url_provider | http://eprints.utm.my/ |