Automated dental recognition by wavelet descriptors in CT multi-slices data

Abstract

Purpose Teeth are one of the most important anatomical components in ergonomic appearance of the face and crucial in craniofacial surgeries and dentistry. Besides, teeth have specific roles in forensic to identify death persons. In this paper, we propose a hybrid technique to classify teeth in computed tomography (CT) dental images. Method Our method consists of three steps: segmentation, feature extraction and classification. We segment the teeth by a hybrid approach including anatomical-based histogram thresholding, panaromic resampling and level-set techniques. In the second step, for each segmented tooth, we calculate the 2D discrete wavelet transform. We then determine 1D inverse discrete wavelet transform by the same mother wavelet, calculate energy of decomposition and approximation coefficients. Next, we utilize these coefficients as feature vectors for classification in the third step. Teeth classification is performed by a conventional feed forward neural network. Results The proposed method is evaluated in the presence of 180 teeth. Experimental results reveal that the technique is effective to automatically classify teeth, on an average, in more than 95% of the cases in both jaws. Conclusion Our method is independent of anatomical information such as the sequence and locality of the teeth in jaws. The techniques are applicable to both forensic and dentistry investigations.

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

“…We get 100% recognition rate for all the rotation angles and scaling factors. These results demonstrate the effectiveness of proposed algorithm against a previous work [19]. We used additive Gaussian noise to the centroid distance signature of teeth contours to study the effect on classification performance.…”

“…The classification performance of the proposed methods are tested and compared with FDs and WDs technique, which are introduced in [12] and [19], respectively. The average classification performance for different type of teeth has been shown in Fig.…”

“…We employ a feed-forward neural network classifier to discriminate different teeth from each other. In this regard, we experimentally found that a feed-forward neural network with one hidden layer and a transfer function of 'tansig' was suitable for undertaking the task [19]. The classification is done by Neuro-Solutions for Excel in which the training, testing and validation data are selected in whole data set and in an automatic way.…”

“…In the previous work [19], we introduced a new technique by applying wavelet descriptors (WDs) for dental recognition in CT images which is not rotation invariant.…”

Dental segmentation in cone-beam computed tomography images using watershed and morphology operators

“…Experimental results reveal that their proposed technique is effective to automatically teeth classification. [4] Akhoondali et al . used a 3D median filter to reduce noise in CT data.…”