About The Research

The past years of COVID-19 have attracted researchers to carry out benchmark work in face mask detection. However, the existing work does not focus on the problem of reconstructing the face area behind the mask and completing the face that can be used for face recognition. In order to address this problem, in this work we have proposed a spatial attention module-based conditional generative adversarial network method that can generate plausible images of faces without masks by removing the face masks from the face region. The method proposed in this work utilizes a self-created dataset consisting of faces with three types of face masks for training and testing purposes. With the proposed method, an SSIM value of 0.91231 which is 3.89% higher and a PSNR value of 30.9879 which is 3.17% higher has been obtained as compared to the vanilla C-GAN method. read more

Datasets

We've curated a custom dataset by integrating face masks into images sourced from the Bollywood Celebrity Faces dataset . This dataset comprises two sets: one featuring faces without masks and the other adorned with masks. Initially, we had 11,262 authentic images of unmasked individuals. To simulate masked faces realistically, we added three types of masks: White, Anti-COVID, and 3M masks. Consequently, the edited dataset now includes 11,262 images each of unmasked faces, faces with White masks, faces with Anti-COVID masks, and faces with 3M masks. Importantly, our method retains facial identity by using the same images for masked and unmasked faces in the synthetic dataset

Sample Dataset