Estimating facial angles using Radon transform

Authors: MOHAMAD AMIN BAKHSHALI, MOUSA SHAMSI

Abstract: Analysis of human facial images has become increasingly important due to its numerous applications. In this regard, extracting facial parameters is vital and various studies have been done in this field. Using these methods, different facial parameters such as the location of eyebrows, eye length, and nose angles are extracted. In this article, a robust and automatic method is introduced for determining facial angles from profile view images using the Radon transform. The Radon transform is a type of linear integration along a specific direction and angles play an important role in its performance. The proposed algorithm not only has good precision, but also efficient performance. The precision of this method in angle measurements is 98.51% compared with manual measurement. Compared to various other angle estimation algorithms, the proposed method has higher efficiency.

Keywords: Radon transform, sinogram, facial angles, facial color image, profile view

Full Text: PDF