Deep convolutional neural networks applied to hand keypoints estimation

Accurate estimation of hand shape and position is an important task in various applications, such as human-computer interaction, human-robot interaction, and virtual and augmented reality. In this paper, it is proposed a method to estimate the hand keypoints from single and colored images utilizing the pre-trained deep convolutional neural networks VGG-16 and VGG-19. The method is evaluated on the FreiHAND dataset, and the performance of the two neural networks is compared. The best results were achieved by the VGG-19, with average estimation errors of 7.40 pixels and 11.36 millimeters for the best cases of two-dimensional and three-dimensional hand keypoints estimation, respectively.The authors acknowledge the support of R&D Unit SYSTEC Base (UIDB/00147/2020) and Programmatic (UIDP/00147/2020) and the ARISE Associated Laboratory (LA/P/0112/2020), as well as the support of projects: Continental FoF, with reference POCI-01-0247-FEDER- 047512, co-funded by FEDER, through COMPETE 2020, Digitalizac¸ ˜ao da Arte Humana (Cibertoque), with reference POCI-01-0247-FEDER-072627, co-funded by FEDER, through COMPETE 2020 and Next-Gen Quality Control IoRT System with reference POCI-01-0247-FEDER-072616, co-funded by FEDER, through COMPETE 2020.