Abstract
Among numerous local descriptors persisting in literature, LPQ is one of most influential blur invariant descriptor. But when high content blurring is mixed with light variations (moderate and high) then LPQ and many others fails to achieve required robustness to declare the efficient face descriptor. This gap is filled by introducing advance versions of LPQ so-called Enhanced LPQ1 (ELPQ1) and ELPQ2. Precisely, blurred affected image (with light variations), by using Gaussian low pass filtering, is passed to 2 novel pre-processing approaches before LPQ feature extraction. In former approach edge oriented (enhanced) images are produced by 3 methods i.e. Sobel (magnitude gradient), Image sharpening and Kirsch (magnitude gradient). In latter approach, Sobel (magnitude gradient) is replaced by more robust magnitude gradient, called Sobel + Prewitt (magnitude gradient), produced by using Sobel horizontal gradient and Prewitt vertical gradient. Rest 2 methods remains similar in both the pre-processing approaches. Further LPQ is imposed for feature extraction. As each pre-processing approach contains 3 methods therefore 3 transformed images are produced after LPQ. Histograms under respective category are integrated to build feature size of 2 robust blur invariant representations ELPQ1 and ELPQ2. Compressed feature size is attained from FLDA and classification is assisted from SVMs. Experiments on GT and EYB proves efficacy of ELPQ1 and ELPQ2 against benchmark methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gupta, S., Thakur, K., Kumar, M.: 2D-human face recognition using SIFT and SURF descriptors of face’s feature regions. Vis. Comput. 37(3), 447–456 (2020). https://doi.org/10.1007/s00371-020-01814-8
Revina, I.M., Emmanuel, W.R.S.: A Survey on Human FER Techniques. J. Kin. Sau. Uni. Com. Inf. Sci. 33(6), 619–628 (2021)
Agbo-Ajala, O., Viriri, S.: Deep learning approach for facial age classification: a survey of the state-of-the-art. Artif. Intell. Rev. 54(1), 179–213 (2020). https://doi.org/10.1007/s10462-020-09855-0
Garg, M., Dhiman, G.: A novel content-based image retrieval approach for classification using GLCM features and texture fused LBP variants. Neural Comput. Appl. 33(4), 1311–1328 (2020). https://doi.org/10.1007/s00521-020-05017-z
Ojansivu, V., Heikkila, J.: Blur insensitive texture classification using LPQ. In: ICISP (2008)
Ahonen, T., Rahtu, E., Ojansivu, V., Heikkila, J.: Recognition of blurred faces using LPQ. In: ICPR (2008)
Zhu, Z., Xiao, Y., Li, S., Cao, Z., Fang, Z., Zhou, J.T.: LPQ++: a discriminative blur-insensitive textural descriptor with spatial-channel interaction. Inf. Sci. 548, 191–211 (2021)
Gonzalez, R.C., Woods, R.E.: Digital Image Processing. 2nd Ed. Pearson Edu. (2002)
Ezatian, R., Khaledyan, D., Jafari, K., Heidari, M.: Image quality enhancement in wireless capsule endoscopy with adaptive fraction gamma transformation and unsharp masking filter. In: GHTC, pp. 1–7 (2020)
Naiemi, F., Ghods, V., Khalesi, H.: A novel pipeline framework for multi oriented scene text image detection and recognition. Exp. Syst. App. 170, 1–16 (2021)
Prakash, P.N.S., Rajkumar, N.: Improved LFDA based dimensionality reduction for cancer disease prediction. J. Amb Intel. Hum. Comput. 12, 8083–8098 (2021)
Ma, J., Yang, L., Sun, Q.: Adaptive robust learning framework for twin SVM classification. Know Bas Syst 211, 106536 (2021)
Georghiades, A.S., Belhumeur, P.N., Kriegman, D.J.: From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Tran PAMI 23(6), 643–660 (2001)
Zhao, C., Li, X., Dong, Y.: Learning blur invariant binary descriptor for face recognition. Neucomp 404, 34–40 (2020)
Sadeghi, B., Jamshidi, K., Vafaei, A., Monadjemi, S.A.: A local image descriptor based on radial and angular gradient intensity histogram for blurred image matching. Vis. Comput. 35(10), 1373–1391 (2018). https://doi.org/10.1007/s00371-018-01616-z
Xiao, Y., Cao, Z.: LPQ+: A principled method for embedding LPQ into FV for blurred image recognition. Inf Sci 420, 77–95 (2017)
Kherchaoui, S., Houacine, A.: FE identification using gradient LP. Mult. Too App. (2019)
Tamrakar, D., Khanna, P.: Blur and occlusion invariant palmprint recognition with block-wise LPQH. Jou Elec Img 24(4), 1–19 (2015)
Zhu, M., Cao, Z., Xiao, Y., Xie, X.: Blurred face recognition by fusing blur-invariant texture and structure features. In: AOPC, pp. 1–6 (2015)
Ojala, T., Pietikainen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Patt Recog 29(1), 51–59 (1996)
Nguyen, H.T., Caplier, A.: Elliptical LBPs for face recognition. In: ACCV (2012)
Liu, L., Zhao, L., Long, Y., Kuang, G., Fieguth, P.: Extended LBP for texture classification. Img Vis Com 30(2), 86–99 (2012)
Liao, S., Zhu, X., Lei, Z., Zhang, L., Li, S.Z.: Learning multi-scale block LBP for face recognition. In: ICB, pp. 828–837 (2007)
Ran, R., Ren, Y., Zhang, S., Fang, B.: A novel discriminant LPP method. Jour Math Img Vis 63, 541–554 (2021)
Dalal, S., Vishwakarma, V.P.: Optimization of weights in ELM for face recognition. Jour Inf Opt Sci 42(6), 1337–1352 (2021)
Karanwal, S.: Discriminative color descriptor by the fusion of 3 novel color descriptors. Opt 244, 167556 (2021)
Ranade, S.K., Anand, S.: Color face recognition using normalized-discriminant hybrid color space and QMV features. Mult Too App 80, 10797–10820 (2021)
Ahuja, B., Vishwakarma, V.P.: Deterministic MKELM with fuzzy feature extraction for pattern classification. Mult. Too App. (2021)
Karanwal, S., Diwakar, M.: OD-LBP: orthogonal difference LBP for face recognition. Dig Sig Proc 110, 102948 (2021)
Zhang, Y., Zheng, S., Zhang, X., Cui, Z.: Multi-resolution DL method based on sample expansion and its application in face recognition. Sig Img Vid Proc 15, 307–313 (2021)
Zhou, W., Gong, Z., Guo, W., Han, N., Qiao, S.: Robust graph Structure learning for multimedia data analysis. Wir. Comm. Mob. Comp. 1–12 (2021)
Meng, M., Liu, Y., Wu, J.: Robust Discriminant Projection Via Joint Margin and LSP. Neu Proc Let 53, 959–982 (2021). https://doi.org/10.1007/s11063-020-10418-1
Zaaraoui, H., Kaddouhi, S.E., Saaidi, A., Abarkan, M.: Face recognition with a new local descriptor based on SSV. Mult Too App 80, 27017–27044 (2021)
Karanwal, S.: A comparative study of 14 state of art descriptors for face recognition. Mult Too App 80(8), 12195–12234 (2021)
Song, T., Feng, J., Luo, L., Gao, C., Li, H.: Robust texture description using LGOP and Non-LBP. IEEE Tran. Cir. Sys. Vid. Tech. 31(1), 189–202 (2021)
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 Switzerland AG
About this paper
Cite this paper
Karanwal, S., Diwakar, M. (2022). Enhanced LPQ Based Two Novel Blur Invariant Face Descriptors in Light Variations. In: Abraham, A., et al. Proceedings of the 13th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2021). SoCPaR 2021. Lecture Notes in Networks and Systems, vol 417. Springer, Cham. https://doi.org/10.1007/978-3-030-96302-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-96302-6_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96301-9
Online ISBN: 978-3-030-96302-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)