Abstract
In Sign Language fingerspelling systems, letters of the alphabet are presented by a diverse form or/and movement of the fingers. In this study, the presented work focus on developing a real-time translation framework of static fingerspelling alphabets. At first an adaptive k-means based cluster method for depth segmentation is proposed, where a flexible cluster number n is used instead of the pre-defined definitive one. Based on the segmentation step, a recognition framework using intensity and depth information is proposed and compared with some distinctive works. Discriminative features extracted from Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), and Zernike moments are used due to their simplicity and good performance. The experiments are executed on a public fingerspelling dataset, which consisted of 120,000 images representing 24 alphabet letters over five different users. The results show that the presented framework is efficient, easy implementation, and performs better than the compared approaches.
Similar content being viewed by others
References
Alassaf N, Alkazemi B, Gutub A (2017) Applicable light-weight cryptography to secure medical data in IoT systems. Journal of Research in Engineering and Applied Sciences (JREAS) 2(2):50–58
Alharthi N, Gutub A (2017) Data visualization to explore improving decision-making within hajj services. Scientific Modelling and Research 2(1):9–18. https://doi.org/10.20448/808.2.1.9.18
Al-Otaibi NA, Gutub AA (2014) 2-Leyer security system for hiding sensitive text data on personal computers. LNIT 2(2):151–157
ASL Finger Spelling Dataset (2017) http://personal.ee.surrey.ac.uk/Personal/N.Pugeault/index.php?section=FingerSpellingDataset. Accessed on 12 Feb. 2017
Badi H (2016) A survey on recent vision-based gesture recognition. Intelligent Industrial Systems 2(2):179–191. https://doi.org/10.1007/s40903-016-0046-9
Chang CC, Lin CJ (2001) LIBSVM: a library for support vector machines. Software available at: http://www.csie.ntu.edu.tw/~cjlin/libsvm. Accessed on 12 Feb 2017
Dahmani D, Larabi S (2014) User-independent system for sign language finger spelling recognition. J Vis Commun Image Represent 25(5):1240–1250. https://doi.org/10.1016/j.jvcir.2013.12.019
Dalal N, Triggs B Histograms of oriented gradients for human detection (2005) International Conference on Computer Vision & Pattern Recognition (CVPR'05), San Diego, CA, USA, 20-26 June 2005; IEEE Computer Society, vol. 2, pp. 886–893
Gutub AA (2010) Pixel indicator technique for RGB image steganography. Journal of Emerging Technologies in Web Intelligence (JETWI) 2(1):56–64
Hrúz M, Trojanová J, Železný M (2012) Local binary pattern based features for sign language recognition. Pattern Recogn Image Anal 22(4):519–526. https://doi.org/10.1134/S1054661812040062
Krishnaveni M, Radha DV (2011) Improved histogram based thresholding segmentation using PSO for sign language recognition. Int J Eng Sci Technol 3(2):1014–1020
Lun R, Zhao W (2015) A survey of applications and human motion recognition with Microsoft Kinect. Int J Pattern Recognit 29(5):1–49. https://doi.org/10.1142/S0218001415550083
Ojala T, Pietikainen M, Maenpaa T (2002) Multi-resolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal 24(7):971–987. https://doi.org/10.1109/TPAMI.2002.1017623
Otiniano-Rodriguez K, Cayllahua-Cahuina E et al (2015) Finger spelling recognition using kernel descriptors and depth images. 28th SIBGRAPI Conference on Graphics, Patterns and Images, Salvador, Bahia, Brazil, August 26–29, 2015. IEEE Computer Society, pp 72–79
Otiniano-Rodriguez KC, Cáamara-Chávez G, Menotti D Hu and Zernike moments for sign language recognition (2012) The 2012 International conference on image processing, computer vision, and pattern recognition (IPCV’12), Las Vegas, Nevada, USA, July 16–19 2012; IEEE Computer Society, pp. 1–5
Pisharady PK, Saerbeck M (2015) Recent methods and databases in vision-based hand gesture recognition: a review. Comput Vis Image Underst 141:152–165. https://doi.org/10.1016/j.cviu.2015.08.004
Prada F, Cruz L, Velho L Object extraction in RGBD Images (2012) 25th SIBGRAPI Conference on Graphics, Patterns and Images, Ouro Preto, Brazil, Aug. 22–25 2012; IEEE Computer Society
Prada F, Cruz L, Velho L Improving object extraction with depth-based methods (2013) XXXIX Latin American Computing Conference (CLEI), Naiguata, Venezuela, 7–11 October 2013; IEEE, pp. 1–9
Pugeault N, Bowden R Spelling it out: real-time ASL fingerspelling recognition (2011) Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCV Workshops), Barcelona, Spain, 6–13 November 2011; IEEE, pp 1114–1119
Rioux-Maldague L, Giguere P Sign language fingerspelling classification from depth and color images using a deep belief network (2014) Canadian Conference on Computer and Robot Vision (CRV), Montreal, QC, Canada, May 6–9, 2014; IEEE Computer Society, pp. 92–97
Thippur A, Ek CH, Kjellstrom H Inferring hand pose: a comparative study of visual shape features (2013) 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), Shanghai, China, April 22–26 2013; IEEE Computer Society, pp. 1–8
Uebersax D, Gall J, den Bergh et al Real-time sign language letter and word recognition from depth data (2011) Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCV Workshops), Barcelona, Spain, 6–13 November 2011. IEEE, pp 383–390
Von Agris U, Zieren J, Canzler U et al (2008) Recent developments in visual sign language recognition. Univ Access Inf 6(4):323–362. https://doi.org/10.1007/s10209-007-0104-x
Yang HD (2015) Sign language recognition with the kinect sensor based on conditional random fields. Sensors 15(1):135–147. https://doi.org/10.3390/s150100135.
Zhu X, Wong K-YK Single-frame hand gesture recognition using color and depth kernel descriptors (2012) Proceedings of the 21st IEEE International Conference on Pattern Recognition (ICPR), Tsukuba Science City, Japan, November 11–15, 2012; IEEE, pp 2989–2992
Acknowledgments
This work is supported by Top-notch Academic Programs Project of Jiangsu Higher Education Institutions (TAPP).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
As the author of this manuscript, I confirmed that there is no any possible conflict of interests in the manuscript. The mentioned funding in the “Acknowledgments” did not lead to any conflict of interests regarding the publication of this manuscript.
Rights and permissions
About this article
Cite this article
Hu, Y. Finger spelling recognition using depth information and support vector machine. Multimed Tools Appl 77, 29043–29057 (2018). https://doi.org/10.1007/s11042-018-6102-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6102-6