Abstract
Due to the diversity of hand gestures uses in human computer interaction and the complexity involved by gestures, many features have been proposed, however each feature has its own drawbacks. Therefore, in this work, we propose a new set of Red, Green, Blue and Depth (RGB-D) feature extraction method based on Image Moment Invariants, named Fast and Accurate Multi-channel Cartesian Jacobi Moment Invariants for Depth (FA-MCJMID), RGB (FA-MCJMIRGB) and RGB-D (FA-MCJMIRGBD) images. We first introduce the fundamental concepts and properties to present the Multi-channel Cartesian Jacobi Moments (MCJMs). Then, we express the MCJMIs using geometric moment invariants under Rotation, Scaling and Translation (RST) transforms. Moreover, we provide the theoretical approach to enhance their numerical accuracy and improve their computational speed. Then we explore the application of our new moment invariants in hand gesture representation and recognition. Accordingly, several experiments are conducted to validate this new set of FA-MCJMI in comparison with some deep learning approches and other existing methods, on several popular hand gesture datasets, with regard to image reconstruction, invariability, numerical stability, computational complexity and recognition. The experiments demonstrate the superiority of the new FA-MCJMI set over the methods commonly used in the literature under geometric distortions, illumination variations and image occlusions.
Similar content being viewed by others
References
Aggarwal A, Sharma S, Singh K, Singh H, Kumar S (2019) A new approach for effective retrieval and indexing of medical images. Biomed Signal Process Control 50:10–34
Amakdouf H, Zouhri A, El Mallahi M, Tahiri A, Chenouni D, Qjidaa H (2021) Artificial intelligent classification of biomedical color image using quaternion discrete radial Tchebichef moments. Multimed Tool Appl 80(2):3173–3192
Anagha P, Baskar A (2021) An automatic histogram detection and information extraction from document images. Int J Speech Tech 24(1):77–85
Benouini R, Batioua I, Elouariachi I, Zenkouar K, Zarghili A (2019) Explicit separable two dimensional moment invariants for object recognition. Procedia Comput Sci 148:409–417
Benouini R, Batioua I, Zenkouar K, Najah S (2021) Fractional-order generalized Laguerre moments and moment invariants for grey-scale image analysis. IET Image Process 15(2):523–541
Benouini R, Batioua I, Zenkouar K, Zahi A, Najah S, Qjidaa H (2019) Fractional-order orthogonal Chebyshev Moments and Moment Invariants for image representation and pattern recognition. Pattern Recogn 86:332–343
Cai J, Luo J, Wang S, Yang S (2018) Feature selection in machine learning: a new perspective. Neurocomputing 300:70–79
Camacho-Bello C, Toxqui-Quitl C, Padilla-Vivanco A, Báez-Rojas J (2014) High-precision and fast computation of Jacobi–Fourier moments for image description. JOSA A 31(1):124–134
Chen B, Qi X, Sun X, Shi Y-Q (2017) Quaternion pseudo-Zernike moments combining both of RGB information and depth information for color image splicing detection. J Vis Commun Image Represent 49:283–290
Cheng H, Chung SM (2016) Orthogonal moment-based descriptors for pose shape query on 3D point cloud patches. Pattern Recogn 52:397–409
Chiang A, Liao SX (2015) Image analysis with legendre moment descriptors. J Comput Sci 11(1):127–136
Dai X, Liu T, Shu H, Luo L (2012) Pseudo-zernike moment invariants to blur degradation and their use in image recognition. In: International conference on intelligent science and intelligent data engineering, Springer, pp 90–97
Devulapalli S, Krishnan R (2021) Remote sensing image retrieval by integrating automated deep feature extraction and handcrafted features using curvelet transform. J Appl Remote Sens 15(1):016504
Dickey JM (1983) Multiple functions: hypergeometric Probabilistic interpretations and statistical uses. J Am Stat Assoc 78(383):628–637
El Mallahi M, El Mekkaoui J, Zouhri A, Amakdouf H, Qjidaa H (2018) Rotation scaling and translation invariants of 3D radial shifted Legendre moments. Int J Autom Comput 15(2):169–180
El Ouariachi I, Benouini R, Zenkouar K, Zarghili A, El Fadili H (2022) Sign language recognition with quaternion moment invariants: a comparative study. In: Networking, intelligent systems and security, Springer, pp 737–748
Elouariachi I, Benouini R, Zenkouar K, Zarghili A (2020) Robust hand gesture recognition system based on a new set of quaternion Tchebichef moment invariants. Pattern Anal Applic, 1–17
Elouariachi I, Benouini R, Zenkouar K, Zarghili A, El Fadili H (2021) Explicit quaternion krawtchouk moment invariants for finger-spelling sign language recognition. In: 2020 28Th european signal processing conference (EUSIPCO), IEEE, pp 620–624
Flusser J, Suk T, Zitová B (2016) 2D and 3D image analysis by moments. Wiley, Hoboken
Guo L-Q, Zhu M (2011) Quaternion Fourier–Mellin moments for color images. Pattern Recogn 44(2):187–195
Hao Y, Li Q, Mo H, Zhang H, Li H (2018) AMI-Net: convolution neural networks with affine moment invariants. IEEE Signal Process Lett 25(7):1064–1068
Hosny KM (2007) Exact and fast computation of geometric moments for gray level images. Appl Math Comput 189(2):1214–1222
Hosny KM (2014) New set of Gegenbauer moment invariants for pattern recognition applications. Arab J Sci Eng 39(10):7097–7107
Hosny KM, Darwish MM (2019) New set of multi-channel orthogonal moments for color image representation and recognition. Pattern Recogn 88:153–173
Hosny KM, Darwish MM, Aboelenen T (2020) New fractional-order Legendre-Fourier moments for pattern recognition applications. Pattern Recogn 103:107324
Huang D-Y, Hu W-C, Chang S-H (2011) Gabor filter-based hand-pose angle estimation for hand gesture recognition under varying illumination. Expert Syst Appl 38(5):6031–6042
Karakasis EG, Papakostas GA, Koulouriotis DE, Tourassis VD (2013) Generalized dual Hahn moment invariants. Pattern Recogn 46(7):1998–2014
Koekoek R, Swarttouw RF The Askey-scheme of hypergeometric orthogonal polynomials and its q-analogue, arXiv: arXiv:math/9602214
Lakshmi NSR, Manoharan C (2011) An automated system for classification of micro calcification in mammogram based on Jacobi moments. Int J Comput Theory Eng 3(3):431–434
Li D, Kong F, Liu J, Wang Q Superpixel-Based Multiple Statistical Feature Extraction Method for Classification of Hyperspectral Images, IEEE Trans Geosci Remote Sens
Lin J, Ding Y (2013) A temporal hand gesture recognition system based on hog and motion trajectory. Optik 124(24):6795–6798
Monge-Alvarez J, Hoyos-Barceló C, Dahal K, Casaseca-de-la Higuera P (2018) Audio-cough event detection based on moment theory. Appl Acoust 135:124–135
Mukundan R, Ong S, Lee PA (2001) Image analysis by Tchebichef moments. IEEE Trans Image Process 10(9):1357–1364
Mukundan R, Ramakrishnan K (1995) Fast computation of Legendre and Zernike moments. Pattern Recogn 28(9):1433–1442
Nwali M, Liao S (2019) A new fast algorithm to compute continuous moments defined in a rectangular region. Pattern Recogn 89:151–160
Oyedotun OK, Khashman A (2017) Deep learning in vision-based static hand gesture recognition. Neural Comput Applic 28(12):3941–3951
Ozcan T, Basturk A (2020) Static facial expression recognition using convolutional neural networks based on transfer learning and hyperparameter optimization. Multimed Tool Appl 79(35):26587–26604
Papakostas GA, Boutalis YS, Papaodysseus C, Fragoulis DK (2006) Numerical error analysis in Zernike moments computation. Image Vis Comput 24 (9):960–969
Patil SB, Sinha G (2017) Distinctive feature extraction for Indian Sign Language (ISL) gesture using scale invariant feature Transform (SIFT). J Instit Eng (India): Ser B 98(1):19–26
Pugeault N, Bowden R (2011) Spelling it out: Real-time ASL fingerspelling recognition. In: 2011 IEEE International conference on computer vision workshops (ICCV workshops), IEEE, pp 1114–1119
Ren Z, Yuan J, Meng J, Zhang Z (2013) Robust part-based hand gesture recognition using kinect sensor. IEEE Trans Multimed 15(5):1110–1120
Roitberg A, Pollert T, Haurilet M, Martin M, Stiefelhagen R (2019) Analysis of deep fusion strategies for multi-modal gesture recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 0–0
Schoutens W (2000) The Askey scheme of orthogonal polynomials. In: Stochastic processes and orthogonal polynomials, Springer, pp 1–13
Shanmuganathan V, Yesudhas HR, Khan MS, Khari M, Gandomi AH (2020) R-CNN and wavelet feature extraction for hand gesture recognition with EMG signals. Neural Comput Applic 32(21):16723–16736
Singh C, Singh J (2018) Multi-channel versus quaternion orthogonal rotation invariant moments for color image representation. Digital Signal Process 78:376–392
Singh C, Singh J (2018) Quaternion generalized Chebyshev-Fourier and pseudo-Jacobi-Fourier moments for color object recognition. Optic Laser Technol 106:234–250
Singh C, Upneja R (2014) Accurate calculation of high order pseudo-Zernike moments and their numerical stability. Digital Signal Process 27:95–106
Suarez J, Murphy RR (2012) Hand gesture recognition with depth images: a review. In: 2012 IEEE RO-MAN: The 21st IEEE international symposium on robot and human interactive communication, IEEE, pp 411–417
Sykora P, Kamencay P, Hudec R (2014) Comparison of SIFT and SURF methods for use on hand gesture recognition based on depth map. Aasri Procedia 9:19–24
Teague MR (1980) Image analysis via the general theory of moments. JOSA 70(8):920–930
Wang C, Liu Z, Chan S-C (2014) Superpixel-based hand gesture recognition with kinect depth camera. IEEE Trans Multimed 17(1):29–39
Yang T, Ma J, Miao Y, Wang X, Xiao B, He B, Meng Q (2019) Quaternion weighted spherical Bessel-Fourier moment and its invariant for color image reconstruction and object recognition. Inf Sci 505:388–405
Yap P-T, Paramesran R (2004) Jacobi moments as image features. In: 2004 IEEE Region 10 conference TENCON 2004, IEEE, pp 594–597
Zhang F, Liu Y, Zou C, Wang Y (2018) Hand gesture recognition based on HOG-LBP feature. In: 2018 IEEE International instrumentation and measurement technology conference (i2MTC), IEEE, pp 1–6
Zhu H, Liu M, Ji H, Li Y (2010) Combined invariants to blur and rotation using Zernike moment descriptors. Pattern Anal Applic 13(3):309–319
Acknowledgments
The authors thankfully acknowledge the Laboratory of Intelligent Systems and Applications (LSIA) for his support to achieve this work.
Funding
This work is supported by the Moroccan National Center for Scientific and Technical Research (CNRST) under the Excellence Research Scholarships Program.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
El Ouariachi, I., Benouini, R., Zenkouar, K. et al. RGB-D feature extraction method for hand gesture recognition based on a new fast and accurate multi-channel cartesian Jacobi moment invariants. Multimed Tools Appl 81, 12725–12757 (2022). https://doi.org/10.1007/s11042-022-12161-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12161-2