Age identification are significant factors in the fields of forensics, bioarchaeology, and anthropology. Dental images offer valuable insights for both medical diagnoses and forensic examinations. Various techniques for dental age identification have specific limitations, such as minimum reliability and accuracy requirements. In our proposed work, the input image was improved using the Upgraded Kaun Filter and then segmented with the Active Contour model. We addressed a weight optimization issue using the Analytic Hierarchy Process. Consequently, valuable features were extracted from the segmented area, which is beneficial for age classification when applying the modified ELM-CSA classifier. The investigational outcomes intended for age identification with modified ELM-CSA approach exhibited higher performance, achieving 86.5% of exactness, specificity of 83.7%, precision of 79.21%, recall of 84.25%, and an F-measure of 74.26%. These results outperformed existing classifiers, including ELM-TLBO, ELM, SVM, and RBFN.