In this paper, we proposed an age assessment method evaluated on Malaysian children aged between 1 and 17. The approach is based on global fuzzy segmentation, local feature extraction using a projection-based feature transform and a designed deep convolutional neural networks (DCNNs) model. In the first step, a global labelling process was achieved based on fuzzy segmentation, and then, the first-to-third molar teeth were segmented. The deformation invariant features were next extracted based on an intensity projection technique. This technique provided high-order features which were invariant to rotation and partial deformation changes. Finally, the designed DCNN model extracts a large set of features in the hierarchical layers which provided scale, rotation and deformation invariance. The method using this approach was evaluated using a comprehensive and labelled orthopantomographs of 456 patients, which were captured in the Department of Dentistry and Research at Universiti Sains Islam Malaysia. The results from the analysis have suggested that the method can classify the images with high performance, which enabled automated age estimation with high accuracy. � 2019, Springer-Verlag London Ltd., part of Springer Nature.

Image registration of remotely sensed imagery is challenging, as complex deformations are common. Different deformations, such as affine and homogenous transformation, combined with multimodal data capturing can emerge in the data acquisition process. These effects, when combined, tend to compromise the performance of the currently available registration methods. A new image transform, known as geometric mean projection transform, is introduced in this work. As it is deformation invariant, it can be employed as a feature descriptor, whereby it analyzes the functions of all vertical and horizontal signals in local areas of the image. Moreover, an invariant feature correspondence method is proposed as a point matching algorithm, which incorporates new descriptor�s dissimilarity metric. Considering the image as a signal, the proposed approach utilizes a square Eigenvector correlation (SEC) based on the Eigenvector properties. In our experiments on standard test images sourced from �Featurespace� and �IKONOS� datasets, the proposed method achieved higher average accuracy relative to that obtained from other state of the art image registration techniques. The accuracy of the proposed method was assessed using six standard evaluation metrics. Furthermore, statistical analyses, including t-test and Friedman test, demonstrate that the method developed as a part of this study is superior to the existing methods. � 2018 Kahaki et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.