Abstract
Automatic Face Recognition (AFR) plays an important role in wide range of applications such as, smart cities, consumer-level and organizational-level applications. AFR is one of the formidable tasks because the face images are susceptible to various degradations by illumination, noise and pose variations. Significant efforts have been manifested in biometric (single/multiple) fusion methods. Prior works on Dempster-Shafer (D-S) evidence theory based fusion show encouraging results in biometric systems. However, most of them fails to handle the inherent uncertainty appropriately. To redress this shortcoming, a new fuzzy belief factor weighted evidence theory-based decision fusion (FBFEve) method is presented in this paper. Three feature extraction methods such as, FG-2DFLD, G2DLDA, Modular-LBP are employed to generate feature vector corresponding to a face image which are fed into the neural network to obtain belief factor. These belief factors based on different feature vectors are fused together to calculate a merit for each class. We have introduced a vanishing-penalty in terms of fuzzy weight, imposed on the missing winning class which is absent in the output set of anyone of three methods. These vanishing-penalty fuzzy weights are used in decision fusion-based face recognition. The proposed method is evaluated by means of two different classifiers namely, radial basis function (RBF) neural network, and support vector machines (SVM). We have validated our method on four benchmark datasets such as, AR, AT&T, FERET, and UMIST. The empirical results show that our FBFEve method attains superior recognition accuracy over some classical sensor-, evidence theory and other related fusion-based techniques.
Similar content being viewed by others
Data availability
All data analysed are included in this paper.
References
Abaza A, Ross A, (2009) Quality-based rank level fusion in biometrics, in: IEEE international conference on biometrics: theory, applications and systems, pp. 1–6
Abozaid A, Haggag A, Kasban H (2019) Eltokhy M multimodal biometric scheme for human authentication technique based on voice and face recognition fusion. Multimed Tools Appl 78:16345–16361
Ahmad S, Pal R, Ganivada A (2022) Rank level fusion of multimodal biometrics using genetic algorithm. Multimed Tools Appl 81:40931–40958
Chang L, Zhang L, Xu X (2021) Correlation-oriented complex system structural risk assessment using copula and belief rule base. Inf Sci 564:220–236
Chang L, Zhang L, Fu C, Chen Y (2022) Transparent digital twin for output control using belief rule base. IEEE Trans Cybern 52(10):10364–10378. https://doi.org/10.1109/TCYB.2021.3063285
Chowdhury S, Sing JK, Basu DK, Nasipuri M (2011) Face recognition by generalized two-dimensional FLD method and multi-class support vector machines. Appl Soft Comput 11(7):4282–4292
Dempster AP (1967) Upper and lower probabilities induced by a multivalued mapping. Ann Math Stat 38(2):325–339
Dey A, Chowdhury S (2020) Probabilistic weighted induced multi-class support vector Machines for Face Recognition. Informatica Si 44:345–353
Dey A, Ghosh M (2019) A novel approach to fuzzy-based facial feature extraction and face recognition. Informatica Si 43(4):535–543
Dey A, Sing JK, Chowdhury S (2017) Weighted fuzzy generalized 2DFLD: a fuzzy feature extraction technique for face recognition. Int J Mach Learn Comput 7(6):223–231
Dey A, Chowdhury S, Ghosh M (2017) Face recognition using ensemble support vector machine. Proceed ICRCICN 2017:46–50
Dey A, Dey SK, Roy AK, Ghosh M, Chakraborty S, Kundu D (2019) Confidence belief function weighted parallel rank-level fusion for face recognition. Proceeding of the IEMENTech 2019:1–6
Dwivedi R, Dey S (2019) A novel hybrid score level and decision level fusion scheme for cancelable multi-biometric verification. Appl Intell 49:1016–1035
Feng J, Xu X, Liu P, Ma F, Ma C, Tao Z (2021) Slope sliding force prediction via belief rule-based inferential methodology. Int J Comput Intell Syst 14(1):965–977
Fu Q, Song Y, Fan C, Lei L, Wang X (2020) Evidential model for intuitionistic fuzzy multi-attribute group decision making. Soft Comput 24(10):7615–7635
Fu C., M. Xue, W. Chang, D. Xu, and S. Yang, “An evidential reasoning approach based on risk attitude and criterion reliability,” Knowl Based Syst, vol. 199, 2020, Art. no. 105947.
Fu C., M. Xue, W. Liu, D. Xu, and J. Yang, “Data-driven preference learning in multiple criteria decision making in the evidential reasoning context,” Appl Soft Comput, vol. 102, 2021, Art. no. 107109.
Ghosh M, Dey A (2023) Fractional-weighted entropy-based fuzzy G-2DLDA algorithm: a new facial feature extraction method. Mutimed Tools Appl Vol. 82(2):2689–2707
Ghosh M, Dey A, Kahali S (2022) A Type-2 fuzzy blended D-S evidence theory based decision fusion method and its application to face recognition. Appl Soft Comput 125:109179
Graham DB, Allinson NM, Wechsler H, Phillips PJ, Bruce V, Fogelman-Soulie F, Huang TS (eds) (1998) Characterizing virtual eigen signatures for general purpose face recognition: from theory to applications. NATO ASI Ser F Comput Syst Sci 163:446–456
Guo K. and L. Zhang, “Multi-source information fusion for safety risk assessment in underground tunnels,” Knowl-Based Syst, vol. 227, 2021, Art. no. 107210.
Hamache A, Boudaren MEY, Pieczynski W (2022) Kernel smoothing classification of multiattribute data in the belief function framework: application to multichannel image segmentation. Multimed Tools Appl 81:29587–29608
Ho T, Hull J, Srihari S (1994) Decision combination in multiple classifier systems. IEEE Trans Pattern Anal Mach Intell 16(1):66–75
Huang D, Shan C, Ardabilian M, Wang Y, Chen L (2011) Local binary patterns and its application to facial image analysis: a survey. IEEE Trans Syst Man Cybern—Part C: Appl Rev 41(6):765–781
Kabir W., M. O. Ahmad and M. N. S. Swamy, "Normalization and weighting techniques based on genuine-impostor score fusion in multi-biometric systems," in IEEE Trans Inf Forensi Secur, vol. 13, no. 8, pp. 1989–2000, Aug. 2018.
Keller JM, Gray MR, Givens JA (1985) A fuzzy k-nearest neighbor algorithm. IEEE Trans Syst Man Cybernet 15:580–585
Kumar A, Shekhar S (2010) Person identification using multi biometric rank- level fusion. IEEE Trans Syst Man Cybern 41(5):922–927
Lai JW, Chang J, Ang LK, Cheong KH (2020) Multi-level information fusion to alleviate network congestion. Inf Fus 63:248–255
Lu S, Li P, Li M, (2020) An Improved Multi-modal Data Decision Fusion Method Based on DS Evidence Theory. In proc. IEEE 4th information technology, networking, electronic and automation control conference (ITNEC), pp. 1684-1690
Lumini A, Nanni L (2017) Overview of the combination of biometric matchers. Inform Fus 33:71–85
Martinez AM, Benavente R (1998) The AR face database, CVC technical Report. #24
Martinez AM, Benavente R (n.d.) The AR face database, http://rvll.ecn.purdue.adu/~aleix/aleix_face_DB.html
Menga T, Jinga X, Yana Z, Pedrycz W (2020) A survey on machine learning for data fusion. Inf Fus 57:115–129
Mi X. and B. Kang, “On the belief universal gravitation (BUG),” Comput Ind Eng, vol. 148, 2020, Art. no. 106685.
Monwar M, Gavrilova ML (2009) Multimodal biometric system using rank-level fusion approach. IEEE Trans Syst Man Cybern— Part B: Cybern 39(4):867–878
Moral-García S, Abellán J (2020) Maximum of entropy for belief intervals under evidence theory. IEEE Access 8:118017–118029
Nguyen K., S. Denman, S. Sridharan and C. Fookes, "Score-Level Multibiometric Fusion Based on Dempster–Shafer Theory Incorporating Uncertainty Factors," in IEEE Trans Human-Mach Syst, vol. 45, no. 1, pp. 132–140, Feb. 2015
Phillips PJ, Moon H, Rizvi S, Rauss P (1998) The FERET Evaluation. In: Wechsler H, Phillips PJ, Bruce V, Soulié FF, Huang TS (eds) Face Recognition. NATO ASI Series, vol 163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-72201-1_13
Phillips PJ, Moon H, Rizvi SA, Rauss PJ (2000) The FERET evaluation methodology for face-recognition algorithms. IEEE Trans Pattern Anal Mach Intell 22:1090–1104
Qiu S, Zhao H, Jiang N, Wang Z, Liu L, An Y, Zhao H, Miao X, Liu R, Fortino G (2022) Multi-sensor information fusion based on machine learning for real applications in human activity recognition: state-of-the-art and research challenges. Inf Fus 80:241–265
Rivadeneira L., J.-B. Yang, and M. López-Ibáñez, “Predicting tweet impact using a novel evidential reasoning prediction method,” Expert Syst Appl, vol. 169, 2021, Art. no. 114400.
Sarangi PP, Nayak DR, Panda M, Majhi B (2022) A feature-level fusion based improved multimodal biometric recognition system using ear and profile face. J Ambient Intell Humaniz Comput 13:1867–1898
Shafer GA (1976) Mathematical theory of evidence. Princeton University Press, Princeton
Sing JK, Dey A, Ghosh M (2019) Confidence factor weighted Gaussian function induced parallel fuzzy rank-level fusion for inference and its application to face recognition. Inf Fus 47:60–71
Su X, Li L, Qian H, Mahadevan S, Deng Y (2019) A new rule to combine dependent bodies of evidence. Soft Comput 23(20):9793–9799
Szczuko P, Harasimiuk A, Czyżewski A (2022) Evaluation of decision fusion methods for multimodal biometrics in the banking application. Sens 22(6):2356
The ORL face database (n.d.) http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
Tiong LCO, Kim ST, Ro YM (2019) Implementation of multimodal biometric recognition via multi-feature deep learning networks and feature fusion. Multimed Tools Appl 78:22743–22772
Tong Z, Xu P, Denœux T (2021) An evidential classifier based on Dempster-Shafer theory and deep learning. Neurocomputing 450:275–293
Walia GS, Singh T, Singh K, Verma N (2019) Robust multimodal biometric system based on optimal score level fusion model. Expert Syst Appl 116:364–376
Weixing W, Limin L, Zhen Z (2022) Road extraction in vague images on gray scale consistency and improved MSR and D-S evidence. Multimed Tools Appl 81:43657–43678
Xiao F (2020) A new divergence measure for belief functions in D–S evidence theory for multisensor data fusion. Inf Sci 514:462–483
Xiao F (2021) CED: a distance for complex mass functions. IEEE Trans Neural Netw Learn Syst 32(4):1525–1535
Xiao F, Cao Z, Jolfaei A (2021) A novel conflict measurement in decision-making and its application in fault diagnosis. IEEE Trans Fuzzy Syst 29(1):186–197
Yin HF, Wu XJ, Song X (2022) Competitive non-negative representation with image gradient orientations for face recognition. Neural Process Lett 54:657–675
Zhou C, Huang J, Yang F, Liu Y (2020) A hybrid fusion model of iris, palm vein and finger vein for multi-biometric recognition system. Multimed Tools Appl 79:29021–29042
Zhou M., Y. Chen, X. Liu, B. Cheng, and J. Yang, “Weight assignment method for multiple attribute decision making with dissimilarity and conflict of belief distributions,” Comput Ind Eng, vol. 147, 2020, Art. no. 106648.
Zhu C, Qin B, Xiao F, Cao Z, Pandey HM (2021) A fuzzy preference-based Dempster-Shafer evidence theory for decision fusion. Inf Sci 570:306–322
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have 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
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ghosh, M., Dey, A. & Kahali, S. A weighted fuzzy belief factor-based D-S evidence theory of sensor data fusion method and its application to face recognition. Multimed Tools Appl 83, 10637–10659 (2024). https://doi.org/10.1007/s11042-023-16037-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-16037-x