Deep learning-based gender classification with dental X-ray images
by B. Vijayakumari; S. Vidhya; J. Saranya
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 42, No. 1, 2023

Abstract: In a forensic department, teeth play a crucial role to recognise a dead or missing person. In forensic analysis, gender difference is a considerable one. Yet, gender identification with dental images using deep learning methods are still in research. An algorithm is proposed here to find human gender using panoramic dental X-ray images (DXI). This work is organised into three sections such as image pre-processing, gradient-based recursive threshold (GBRT) segmentation and classification. Initially, prime magic square filter is used to remove the unwanted noises. Secondly, segmentation GBRT is used. Finally with Resnet50 network, the gender is classified. The dataset of 285 dental images were taken and they are augmented to 4,000 dental images and then they are separated as 3,000 images for training and 1,000 images for testing to carry out experimental evaluation. It provides classification accuracy of 94%. It shows that the proposed work gives convincing results.

Online publication date: Tue, 27-Jun-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Biomedical Engineering and Technology (IJBET):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email