Certain investigations on age assessment and image classification for dental age

Abstract

Dental Age (DA) estimation is used for criminal, civil, anthropologic and forensic purposes. Numerous techniques have been provided to evaluate chronological age for these applications. It includes somatic growth measurements which depend on dental development. Tooth development for age estimation has been utilized for long time. In this research, the objective is to provide dissertation to investigate dental age estimation methods with proper validation. Moreover, the purpose of this investigation is to bridge the gap between growing and patterned classification approach for developing tooth with local and environmental influence together with somatic model as DA estimation is essential for dead and also for living individuals, specifically in case of children and young adolescents. Dental clues are increasingly utilized to handle crime. For this, Machine Learning approaches are considered for classification and appropriate validation of results. Initially, a novel Modified Extreme Learning Machine with Sparse Representation Classification (MELM-SRC) is proposed to progress classification accuracy. To start with this, input image is pre-processed for reducing noise and smoothing in image using Anisotropic Diffusion Filter (ADF). Subsequently, teeth image are segmented using Active Contour Model (ACM) with Jaya Optimization (JO) and then morphological post processing has been applied on segmented result to show improved classification accuracy. Next, features like area, perimeter, solidity, Diameter, major and minor axis length and filled area are extracted to enhance prediction accuracy. Lastly, age has been classified with MELM-SRC. In this MELM, effectual features are classified using SRC to increase age classification accuracy. newline