Distance Signature Research Articles

Classification and numbering of teeth in multi-slice CT images using wavelet-Fourier descriptor

Teeth arrangement is essential in face ergonomics and healthiness. In addition, they play key roles in forensic medicine. Various computer-assisted procedures for medical application in quantitative dentistry require automatic classification and numbering of teeth in dental images. In this paper, we propose a multi-stage technique to classify teeth in multi-slice CT (MSCT) images. The proposed algorithm consists of the following three stages: segmentation, feature extraction and classification. We segment the teeth by employing several techniques including Otsu thresholding, morphological operations, panoramic re-sampling and variational level set. In the feature extraction stage, we follow a multi-resolution approach utilizing wavelet-Fourier descriptor (WFD) together with a centroid distance signature. We compute the feature vector of each tooth by employing the slice associated with largest tooth tissues. The feature vectors are employed for classification in the third stage. We perform teeth classification by a conventional supervised classifier. We employ a feed- forward neural network classifier to discriminate different teeth from each other. The performance of the proposed method was evaluated in the presence of 30 different MSCT data sets including 804 teeth. We compare classification results of the WFD technique with Fourier descriptor (FD) and wavelet descriptor (WD) techniques. We also investigate the invariance properties of the WFD technique. Experimental results reveal the effectiveness of the proposed method. We provided an integrated solution for teeth classification in multi-slice CT datasets. In this regard, suggested segmentation technique was successful to separate teeth from each other. The employed WFD approach was successful to discriminate and numbering of the teeth in the presence of missing teeth. The solution is independent of anatomical information such as knowing the sequence of teeth and the location of each tooth in the jaw.

Two-dimensional object recognition using partial contours

Most simple algorithms for generating 2D shape descriptors, whether they are based on boundary features or regional features, require that the complete object is visible. This paper introduces a simple boundary-based shape descriptor, the normal contour distance (NCD) signature, which does not require knowledge of the complete boundary and is suitable for recognition of partially occluded objects. The ability of the NCD descriptor to discriminate between standard 2D shapes has been tested and details are provided of the results obtained using 50%, 50%, 70%, 80%, 90% and 100% of the complete object boundary.

Efficient graph automorphism by vertex partitioning

We describe a vertex partitioning method and squeeze tree search technique, which can be used to determine the automorphism partition of a graph in polynomial time for all graphs tested, including those which are strongly regular. The vertex partitioning procedure is based on first transforming the graph by the 1-or 2-subdivision transform or the 1-or 2-superline transform and then employing a distance signature coding technique on the vertices of the transformed graph. The resulting adjacency refinement partition of the transformed graph is reflected back to the original graph where it can be used as an initial vertex partition which is equal to or coarser than the desired automorphism partition. The squeeze tree search technique begins with two partitions, one finer than the automorphism partition and one coarser than the automorphism partition. In essence, it searches through all automorphisms refining the coarser partition and coarsening the finer partition until the two are equal. At this point the result is the automorphism partition. The vertex partitioning method using the 2-superline graph transform preceeding the squeeze tree search is so powerful that for all the graphs in our catalog (random, regular, strongly regular, and balanced incomplete block designs) it produces the automorphism partition, thereby making the tree search nothing more than a verification that the initial partition is indeed the automorphism partition.