Deep convolutional neural networks applied to hand keypoints estimation

• Autor(a) principal: Santos, Bruno M.
• Data de Publicação: 2020
• Outros Autores: Pais, Pedro, Ribeiro, Francisco M., Lima, José, Goncalves, Gil, Pinto, Vítor H.
• Idioma: eng
• Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Texto Completo: http://hdl.handle.net/10198/21876
• topic: Hand keypoints estimation; Convolutional neural network; VGG; FreiHAND

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.