抄録
In this paper, we propose a new automatic classification method for spinal deformity from moire topographic images which obtained asymmetric degree by using a new statistical feature. In our method, we detect three features such as mean values, standard deviation from an original moire image and cross correlation value from a converted low resolution image. Extracted three features are applied to employing an artificial neural network for classification. The proposed technique applied 1200 real moire topographic images and obtained some experimental results are shown along with a discussion.
