Vision-based bone image recognition using geometric properties

Abstract

An effective approach for bone image anal­ysis, including segmentation and recognition is presented in this paper. Bone segmenta­tion is carried out by K-means clustering of the bone image, whereas the recognition phase is based on fea­ture extraction and two-level statistical classification. The proposed approach has applications in medicine and vet­erinary anatomy studies, orthopedics, paleontology and archaeology. Several image features, including geomet­ric and moment invariants (regular and Zernike), are de­rived for recognition. The first-level classification is used to distinguish different kinds of bone and the second-level to recognize the right animal to which the bone belongs. Two-dimensional structures, called cluster-property and cluster-features matrices, have been employed to evalu­ate different bone characteristics. Experimental results for the first-level recognition exhibit better performance of the geometric features compared to moment invariants and Zernike moments. On the other hand, Zernike moments showed supremacy in differential diagnosis at the second level to recognize animals.