# Automatic cephalometric landmarks detection on frontal faces: an approach based on supervised learning techniques

## TL;DR

This paper presents a supervised learning-based method for automatic detection of cephalometric landmarks on frontal face images, achieving accuracy comparable to human experts and outperforming existing automatic methods.

## Contribution

The work introduces a novel supervised learning approach for automatic cephalometric landmark detection, improving accuracy over previous automatic methods and matching expert-level precision.

## Key findings

- Achieves a normalized mean distance error of 0.014 pixels.
- Matches the precision of human expert markers.
- Outperforms other automatic landmark detection frameworks.

## Abstract

Facial landmarks are employed in many research areas such as facial recognition, craniofacial identification, age and sex estimation among the most important. In the forensic field, the focus is on the analysis of a particular set of facial landmarks, defined as cephalometric landmarks. Previous works demonstrated that the descriptive adequacy of these anatomical references for an indirect application (photo-anthropometric description) increased the marking precision of these points, contributing to a greater reliability of these analyzes. However, most of them are performed manually and all of them are subjectivity inherent to the expert examiners. In this sense, the purpose of this work is the development and validation of automatic techniques to detect cephalometric landmarks from digital images of frontal faces in forensic field. The presented approach uses a combination of computer vision and image processing techniques within a supervised learning procedures. The proposed methodology obtains similar precision to a group of human manual cephalometric reference markers and result to be more accurate against others state-of-the-art facial landmark detection frameworks. It achieves a normalized mean distance (in pixel) error of 0.014, similar to the mean inter-expert dispersion (0.009) and clearly better than other automatic approaches also analyzed along of this work (0.026 and 0.101).