Hand Posture Recognition Using Convolutional Neural Network

Abstract : 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.
Complete list of metadatas

Cited literature [2 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02263891
Contributor : Dennis Núñez Fernández <>
Submitted on : Tuesday, August 6, 2019 - 9:28:10 AM
Last modification on : Tuesday, August 6, 2019 - 9:33:12 AM

File

Núñez_poster_LXAI_ICML2019.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02263891, version 1

Citation

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

Share

Metrics

Record views

32

Files downloads

18