Abstract
Literature reports numerous local descriptors based on extracting rich information from color space formats. The color scale format provides more robustness as compared to grayscale counterparts. This work introduces such descriptors called Color Multiscale Block-ZigZag LBP (CMB-ZZLBP) for Face Recognition (FR). CMB-ZZLBP is the advanced method of MB-ZZLBP. In MB-ZZLBP, first mean patch is generated (from 9 regions of the 6 × 6 patch) and then zigzag pixels are compared to develop MB-ZZLBP code. MB-ZZLBP forms the histogram representation of 256, by computing MB-ZZLBP code in each position. The major issue with MB-ZZLBP is that it restricts its robustness due to grayscale feature extraction. By introducing CMB-ZZLBP, this issue is resolved effectively. In CMB-ZZLBP, the MB-ZZLBP feature extraction is done from each component of the RGB color space format. Further, all three channel features are integrated to build the CMB-ZZLBP feature size. FLDA is used to achieve compressed feature representation, and classification is performed from SVM and NN. Experiments justify the effectiveness of CMB-ZZLBP against MB-ZZLBP on Georgia Technology Face Dataset (GTFD). CMB-ZZLBP proves its dominance against various literature techniques also. CMB-ZZLBP secures the best ACC of 96.66% on a training size of 9.
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
Similar content being viewed by others
References
Karanwal, S.: Robust LBP for face recognition in different challenges. Multi. Tool Appl. 81, 29405–29421 (2022)
Saidi, I.A., Rziza, M., Debayle, J.: A novel texture descriptor: circular parts LBP. Img. Ana. Ster. 40(2), 105–114 (2021)
Kar, C., Banerjee, S.: Tropical cyclones classification from satellite images using BLBP and histogram analysis. In: SCTA, pp. 399–407 (2021)
Kartheek, M.N., Prasad, M.V.N.K., Bhukya, R.: RMP: a handcrafted feature descriptor for FER. J. Ambient. Intell. Humanized Comput. (2021)
Song, T., Xin, L., Gao, C., Zhang, T., Huang, Y.: QELBP with adaptive structural pyramid pooling for color image representation. Pattern Recognit. (2021)
Bhattacharjee, D., Roy, H.: PLGF: a novel local image descriptor. IEEE Trans. Pattern Ana. Mac. Intell. 43(2), 595–607 (2021)
Karanwal, S., Diwakar, M.: MB-ZZLBP: multiscale block ZigZag LBP for face recognition. In: MARC, pp. 613–622 (2021)
Qin, X., Wang, S., Chen, B., Zhang, K.: R-FLDA with GCLF. In: CAC (2020)
Junior, P.R.M., Boult, T.E., Wainer, J., Rocha, A.: Open-set SVM. IEEE Trans. Syst. Man Cyb.: Syst. 1–14 (2021)
Rastin, N., Jahromi, M.Z., Taheri, M.: A GWD k-NN for multi-label problems. Pattern Recognit. 114 (2021)
Shu, X., Song, Z., Shi, J., Huang, S., Wu, X.J.: Multiple channels LBP for color texture representation and classification. Sig. Proc. Img. Com. 98 (2021)
Agarwal, M., Maheshwari, R.P.: MLTCP for CBIR. Ira. J. Sci. Tech. 44, 495–504 (2020)
Tiecheng, S., Jie, F., Shuang, L., Tianqi, Z.: Color CBP using progressive bit correction for image classification. Chi. J. Electron. 30(3), 471–481 (2021)
Karanwal, S.: DCD by the fusion of 3 novel color descriptors. Optik 244 (2021)
Vipparthi, S.K., Nagar, S.K.: CD-LQP for CBIR. Hum. Cent. Comp. Inf. Sci. 4(6) (2014)
Karanwal, S., Diwakar, M.: Two novel color local descriptors for face recognition. Optik 1–15 (2021)
Jebali, H., Richard, N., Naouai, M.: LBQRP for CTR. In: ICPR, pp. 3698–3705 (2021)
Sotoodeh, M., Moosavi, M.R., Boostani, R.: A novel adaptive LBP-based descriptor for color image retrieval. Expert. Syst. Appl. 127, 342–352 (2019)
Agarwal, M., Singhal, A., Lall, B.: Multi-channel LTP for CBIR. Pattern Anal. Appl. 22, 1585–1596 (2019)
Umer, S., Dhara, B.C., Chanda, B.: Biometric recognition system for challenging faces. In: NCVPRIPG (2015)
Umer, S., Dhara, B.C., Chanda, B.: Face recognition using fusion of FLT. Measurement 146, 43–54 (2019)
Ran, R., Feng, J., Zhang, S., Fang, B.: A GMF DR framework and extension for manifold learning. IEEE Trans. Cyb. 1–12 (2020)
Karanwal, S.: Graph based structure binary pattern for face analysis. Optik 241 (2021)
Wang, S., Ge, H., Yang, J., Tong, Y.: Relaxed group low rank regression model for multi-class classification. Multimed. Tools Appl. 80, 9459–9477 (2021)
Fan, Z., Wei, C.: Fast kernel SRC for undersampling problem in face recognition. Multimed. Tools Appl. 79, 7319–7337 (2020)
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
Karanwal, S. (2022). Color Multiscale Block-ZigZag LBP (CMB-ZZLBP): An Efficient and Discriminant Face Descriptor. In: Rushi Kumar, B., Ponnusamy, S., Giri, D., Thuraisingham, B., Clifton, C.W., Carminati, B. (eds) Mathematics and Computing. ICMC 2022. Springer Proceedings in Mathematics & Statistics, vol 415. Springer, Singapore. https://doi.org/10.1007/978-981-19-9307-7_1
Download citation
DOI: https://doi.org/10.1007/978-981-19-9307-7_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-9306-0
Online ISBN: 978-981-19-9307-7
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)