Abstract
Transfer learning has gained more attention recently by utilizing knowledge acquired from one domain to advance a learning performance in another domain. Existing homogeneous transfer learning methods have progressed to a point where feature spaces are common in training and testing domains. However, heterogeneous transfer learning is still in its nascent stage where features of training and testing domains are different. Taking this into account, Bregman Divergence Regularization is used to minimize the probability distribution difference between training and testing domains and to take them together to a shared subspace. To discriminate data within individual domains, a projection matrix is obtained using Fisher Linear Discriminant Analysis subspace learning algorithm. Experimentation is performed on two efficiently used biometrics: the face and fingerprint. Two types of cross-domain settings are used: (1) Face + Finger2Finger where training samples come from face (labeled samples) and fingerprint (unlabeled samples) data sets, while testing is performed on a fingerprint dataset. (2) Finger + Face2Face where training samples come from fingerprint (labeled samples) and face (unlabeled samples) data sets while testing is performed on a face dataset. This paper proposes a cross domain association between face and fingerprint that finds utility in forensic applications.
Similar content being viewed by others
References
Obozinski G, Taskar B, Jordan MI (2006) Multi-task feature selection, technical report, Dept. of Statistics, Uni. of California, Berkeley
Blitzer J, McDonald R, Pereira F (2006) Domain adaptation with structural correspondence learning. In: Proc. of the Conf. on Empirical Methods in Natural Language, pp 120–128
Blitze J, Crammer K, Kulesza A, Pereira F et al (2008) Learning bounds for domain adaptation. Adv Neural Inf Process Syst 21:129–136
Pan SJ, Kwok JT, Yang Q (2008) Transfer Learning via dimensionality reduction. In: Proc. 23rd National Conf. Artificial Intelligence pp. 677–682
Si S, Tao D, Geng B (2010) Bregman Divergence-based regularization for transfer subspace learning. IEEE Trans Knowl Data En 22(7):929–942
Belkin M, Niyogi P, Sindhwani V, Regularization M (2006) A geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7:2399–2434
Cai D, He X, Han J (2007) Semi-supervised discriminant analysis. In: IEEE Int Conf. Computer Vision, pp 1–7
Zhang T, Tao D, Yang J (2008) Discriminative locality alignment. In: Proc. 10th European Conf. computer vision, pp 725–738
Caruana R (1997) Multitask learning. Mach Learn 28(1):41–75
Whitbrook AM, Aickelin U, Garibaldi JM (2010) Real-world transfer of evolved artificial immune system behaviours between small and large scale robotic platforms. Evol Intel 3:123–136
Zadrozny B (2004) Learning and evaluating classifiers under sample selection bias. In: International Conf. Machine Learning, pp 114–121
Smith RE, Jiang MK, Bacardit J et al (2010) A learning classifier system with mutual-information-based fitness. Evol Intel 3(1):31–50
Do CB, Ng AY (2006) Transfer learning for text classification. Adv Neural Inf Process Syst 2006:299–306
Farhadi A, Forsyth D, White R (2007) Transfer learning in sign language. In: Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, pp 1–8
Gong B, Grauman K, Sha F (2014) Learning kernels for unsupervised domain adaptation with applications to visual object recognition. Int J Comput Vis 109:3–27
Nguyen TT, Silander T, Li Z et al (2017) Scalable transfer learning in heterogeneous, dynamic environments. Artif Intell 247:70–94
Zhao L, Pan SJ, Yang Q (2017) A unified framework of active transfer learning for cross-system recommendation. Artif Intell 245:38–55
Pan W, Yang Q (2013) Transfer learning in heterogeneous collaborative filtering domains. Artif Intell 197:39–55
Zhao P, Hoi SCH, Wang J, Li B (2014) Online transfer learning. Artif Intell 216:76–102
Kute RS, Vyas V (2016) Biometric association using transfer subspace learning. In: IEEE Region 10 Conf. (TENCON), pp 1384–1387
Kute RS, Vyas V, Anuse A (2019) Component-based face recognition under transfer learning for forensic applications. Inf Sci 476:176–191
Lim D, Ong YS, Gupta A et al (2016) Towards a new praxis in optinformatics targeting knowledge re-use in evolutionary computation: simultaneous problem learning and optimization. Evol Intel 9(4):203–220
Xia S, Shao M (2012) Jiebo, Understanding kin relationship in a photo. IEEE Trans Multimedia 14(4):1046–1056
Su Y, Fu Y, Tian Q, Gao X (2010) Cross-database age estimation based on transfer learning. In: Proc. of IEEE Int. Conf. on Acoustics, Speech and Signal Processing, pp 1270–1273
Yan H, Marcelo H, Poo A (2011) Cross-dataset facial expression recognition. In: Proc. of IEEE Int. Conf. on Robotics and Automation, pp 5985–5990
Si S, Tao D, Chan (2010) Evolutionary cross-domain discriminative hessian eigenmaps. IEEE Trans Image Process 19(4):1075–1086
Si S, Tao D, Wang M et al (2010) Social image annotation via crossdomain subspace learning. Springer Publ Multimedia Tools Appl 56:91–108
Galea C, Farrugia A (2017) Matching software-generated sketches to face photos with a very deep CNN, morphed faces, and transfer learning. IEEE Trans Inf Forensics Secur 99:1556–6013
Kang S (2018) On effectiveness of transfer learning approach for neural network-based virtual metrology modeling. IEEE Trans Semicond Manuf 31(1):149–155
Masood S, Luthra T, Sundriyal H et al (2017) Identification of diabetic retinopathy in eye images using transfer learning. Int Conf Comput Commun Autom 2017:1183–1187
Chang J, Yu J, Han T et al (2017) A method for classifying medical images using transfer learning: a pilot study on histopathology of breast cancer. In: IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom), pp 1–4
Hon M, Khan NM (2017) Towards Alzheimer’s disease classification through transfer learning. IEEE Int Conf Bioinf Biomed 2017:1166–1169
Wang J, Wang G, Zhou M (2018) Bimodal vein data mining via cross-selected domain knowledge transfer. IEEE Trans Inf Forensics Secur 13(3):733–744
Sentas A, Tashiev I, Kucukayvaz F et al (2018) Performance evaluation of support vector machine and convolutional neural network algorithms in real-time vehicle type and color classification. Evol Intel 2018:1–9
Anuse A, Vyas V (2016) A novel training algorithm for convolutional neural network. Complex Intell Syst 2(3):221–234
Belhumeur PN, Hespanha JP, Kriegman DJ (1997) Eigenfaces versus fisherfaces: recognition using class specific linear projection. IEEE Trans Pattern Anal Mach Intell 19(7):711–720
He X, Cai D, Han J (2008) Learning a maximum margin subspace for image retrieval. IEEE Trans Knowl Data Eng 20(2):189–201
Neerja E, Walia (2008) Face recognition using improved fast CA algorithm. Congr Image Sign Process 1:554–558
Zhujie Y, Yu l (1994) Face recognition with eigenfaces. In: IEEE Int. Conf. on Industrial Technology, pp 434–438
Sharkas M, AbouElenien M (2008) Eigenfaces vs. fisherfaces vs. ICA for face recognition: a comparative study, 9th Int. Conf. on Signal Processing, pp 914–919
Huang P, Caikou C (2009) Enhanced marginal fisher analysis for face recognition. Int Conf Artif Intell Comput Intell 2:403–407
Ashalatha ME et al (2014) Face recognition using local features by LPP approach. Int. Conf. on Circuits, Communication, Control and Computing, pp 382–386
Zhang T et al (2008) Discriminative ocality alignment, lecture notes in computer science computer vision, pp 725–738
Liu F, Zhang G, Lu J (2017) Heterogeneous transfer learning: an unsupervised approach. IEEE Int. Conf. on fuzzy systems (FUZZ-IEEE), pp 1–6
Grm K, Struc V et al (2018) Strengths and weaknesses of deep learning models for face recognition against image degradations. IET Biometrics 7(1):81–89
Sonkamble S, Thool DR (2010) Survey of biometric recognition systems and their applications. J Theor Appl Inf Technol 2010:11
Mahafzah Al, Rwashdeh Al (2012) A survey of multibiometric systems, arXiv preprint
Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugenics 7:179–188
Samaria FS, Harter AC (1994) Parameterisation of a stochastic model for human face identification. IEEE Workshop on Applications of Computer Vision, pp 138–142
Author information
Authors and Affiliations
Corresponding author
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
Kute, R.S., Vyas, V. & Anuse, A. Cross domain association using transfer subspace learning. Evol. Intel. 12, 201–209 (2019). https://doi.org/10.1007/s12065-019-00211-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12065-019-00211-y