Demography-based Facial Retouching Detection using Subclass Supervised Sparse Autoencoder
This work addresses the challenge of biased retouching detection for face images across different demographics, which is incremental as it builds on prior detection methods by incorporating demographic considerations.
The paper tackles the problem of detecting digitally retouched face images by introducing a new Multi-Demographic Retouched Faces dataset and a novel semi-supervised autoencoder method, which outperforms existing state-of-the-art algorithms and shows that detection accuracy varies significantly based on demographics, with experiments revealing accuracy differences across ethnicities.
Digital retouching of face images is becoming more widespread due to the introduction of software packages that automate the task. Several researchers have introduced algorithms to detect whether a face image is original or retouched. However, previous work on this topic has not considered whether or how accuracy of retouching detection varies with the demography of face images. In this paper, we introduce a new Multi-Demographic Retouched Faces (MDRF) dataset, which contains images belonging to two genders, male and female, and three ethnicities, Indian, Chinese, and Caucasian. Further, retouched images are created using two different retouching software packages. The second major contribution of this research is a novel semi-supervised autoencoder incorporating "subclass" information to improve classification. The proposed approach outperforms existing state-of-the-art detection algorithms for the task of generalized retouching detection. Experiments conducted with multiple combinations of ethnicities show that accuracy of retouching detection can vary greatly based on the demographics of the training and testing images.