Abstract
This paper proposes a novel deep network Att-PyNet: an attention pyramidal feature network for hand gesture recognition. The proposed Att-PyNet comprises three feature streams: multi-scale feature extractor (MSFE), attention pyramid module, and locally connected (LC) layer. The MSFE is introduced to enrich the proposed Att-PyNet model with features of macro- and micro-edges by learning the complementary features of multi-receptive fields. The attention pyramid module is designed to carry forward the high-level features to the lower layer by maintaining the distinctive quality. The locally connected layer is adopted to enhance the discriminative capability of the proposed network by preserving the pertinent context information. The Att-PyNet is a computationally effective model as it holds very less 565K parameters than state-of-the-art models and can be easily deployed in a resource-constrained platform. The effectiveness of the proposed Att-PyNet is evaluated on three standard datasets: MUGD, Triesch, and ASL FingerSpelling. The quantitative and qualitative results validate that Att-PyNet outperforms the state-of-the-art hand gesture approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pisharady PK, Saerbeck M (2015) Recent methods and databases in vision-based hand gesture recognition: a review. Comput Vis Image Underst 141:152–165
Muthukumar K, Poorani S, Gobhinath S (2017) Vision based hand gesture recognition for Indian sign languages using local binary patterns with support vector machine classifier. Adv Nat Appl Sci 11(6, SI):314–322
Misra A, Abe T, Deguchi K 2011 Hand gesture recognition using histogram of oriented gradients and partial least squares regression. In: MVA, pp 479–482
Bhaumik G, Verma M, Govil MC, Vipparthi SK (2020) EXTRA: an extended radial mean response pattern for hand gesture recognition. In: 2020 international conference on communication and signal processing (ICCSP), Chennai, India, 2020, pp 0640–0645. https://doi.org/10.1109/ICCSP48568.2020.9182207
Yamashita T, Watasue T (2014) Hand posture recognition based on bottom-up structured deep convolutional neural network with curriculum learning. In: 2014 IEEE international conference on image processing (ICIP), 2014. IEEE
Paul S, Bhattacharyya A, Mollah AF, Basu S, Nasipuri M (2020) Hand segmentation from complex background for gesture recognition. In: Emerging technology in modelling and graphics. Springer, Singapore, pp 775–782
Neethu PS, Suguna R, Sathish D (2020) An efficient method for human hand gesture detection and recognition using deep learning convolutional neural networks. Soft Comput 1–10
Zhang T, Lin H, Ju Z, Yang C (2020) Hand gesture recognition in complex background based on convolutional pose machine and fuzzy Gaussian mixture models. Int J Fuzzy Syst 1-12
Hu B, Wang J (2020) Deep learning based hand gesture recognition and UAV flight controls. Int J Autom Comput 17–29
Huang H, Chong Y, Nie C, Pan S (2019) Hand gesture recognition with skin detection and deep learning method. J Phys: Conf Ser 1213(2)
Nguyen XS, Brun L, Lezoray O, Bougleux S (2019) A neural network based on SPD manifold learning for skeleton-based hand gesture recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2019
Nuzzi C et al. (2019) Deep learning-based hand gesture recognition for collaborative robots. IEEE Instrum Meas Mag 22(2), 44–51
Wu XY (2019) A hand gesture recognition algorithm based on DC-CNN. Multimed Tools Appl 1–13
Pinto RF, Borges CDB, Almeida Antonio MA, Paula IC (2019) Static hand gesture recognition based on convolutional neural networks. J Electr Comput Eng
Barczak ALC, Reyes NH, Abastillas M, Piccio A, Susnjak T (2011) A new 2D static hand gesture colour image dataset for ASL gestures
Nicolas Pugeault RB ASL finger spelling dataset. http://personal.ee.surrey.ac.uk/Personal/N.Pugeault/index.php
Triesch J, von der Malsburg C (1996) Robust classification of hand postures against complex backgrounds. In: Proceedings of the second international conference on automatic face and gesture recognition. IEEE Computer Society Press, Killington, Vermont, USA, 14–16 Oct 1996, pp 170–175
Wang Y, Long M, Wang J, Yu PS (2017) Spatiotemporal pyramid network for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1529–1538
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence, 2017
Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8697–8710
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826
Zhan F (2019) Hand gesture recognition with convolution neural networks. In: 2019 IEEE 20th international conference on information reuse and integration for data science (IRI). IEEE, pp 295–298
Mohanty A, Rambhatla SS, Sahay RR (2017) Deep gesture: static hand gesture recognition using CNN. In: Proceedings of international conference on computer vision and image processing. Springer, pp 449–461
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bhaumik, G., Verma, M., Govil, M.C., Vipparthi, S.K. (2022). Att-PyNet: An Attention Pyramidal Feature Network for Hand Gesture Recognition. In: Patgiri, R., Bandyopadhyay, S., Borah, M.D., Emilia Balas, V. (eds) Edge Analytics. Lecture Notes in Electrical Engineering, vol 869. Springer, Singapore. https://doi.org/10.1007/978-981-19-0019-8_35
Download citation
DOI: https://doi.org/10.1007/978-981-19-0019-8_35
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-0018-1
Online ISBN: 978-981-19-0019-8
eBook Packages: EngineeringEngineering (R0)