A Multi-featured Approach by Integrating Digital Hand and Dental X-Ray for Human Age Estimation

Abstract

Traditionally, human bone age is estimated manually by inspecting the multiple body part X-ray images, which is extremely time-consuming and prone to error. The accuracy of the human estimate depends on the experience of the medical practitioner, and thus it suffers from intra- and inter-observer variability. Hence, efficient automatic approaches are required to determine human age with high accuracy. In this work, we propose a human age estimation technique using Deep Learning (DL) technique based on hand X-ray images combined with dental orthopantomographs (OPGs) is proposed. Here, the input X-ray image is pre-processed first using Non-Local Means (NLM) first, followed by Region of Interest (RoI) extraction. Later, color and position image augmentation are performed in order to balance the dataset. Thereafter, the salient features in the image are determined, and based on these features, human age estimation is carried out using the Deep Residual Network (DRN). Here, the DRN is trained using the Beluga whale lion optimization (BWLO) algorithm. Furthermore, the BWLO_DRN is examined for its superiority considering the model accuracy and is found to obtain value of 90.1% on hand-wrist and 89.9% OPG real time dataset, thus showing superior performance for hand-wrist images.