Hand Posture Recognition Using Convolutional Neural Networks

Dennis Núñez Fernández (1) , Bogdan Kwolek (2)

1 UNI - Universidad Nacional de Ingeniería
2 AGH UST - AGH University of Science and Technology [Krakow, PL]

In this work we present a convolutional neural network-based algorithm for recognition of hand postures on images acquired by a single color camera. The hand is extracted in advance on the basis of skin color distribution. A neural network-based regressor is applied to locate the wrist. Finally, a convolutional neural network trained on 6000 manually labeled images representing ten classes is executed to recognize the hand posture in a sub-window determined on the basis of the wrist. We show that our model achieves high classification accuracy, including scenarios with different camera used in testing. We show that the convolutional network achieves better results on images pre-filtered by a Gabor filter.

Domaines: Informatique [cs]; Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Dennis Núñez Fernández, Bogdan Kwolek. Hand Posture Recognition Using Convolutional Neural Networks. LatinX in AI Research at ICML 2019, Jun 2019, Long Beach, United States. ⟨hal-02263891v2⟩