Abstract
The transfer learning and deep convolutional neural network-based recognition models have been merged to develop an efficient model in the contemporary time. The ear recognition system has major challenges in terms of the number of sample images, illumination changes, and other environmental challenges. To make the recognition system free from these challenges, the authors utilized the strength of both the existing three pre-trained models (e.g. VGG19, VGG16, DenseNet201) and three simple light-weight Convolutional Neural (CNN) models. The proposed method encompasses the transfer learning as well as simple deep convolution neural network model to design the ensemble model. The first three models are based on the transfer learning approach which uses VGG19, VGG16, and DenseNet201 whereas the last three models are light-weight Convolution Neural Networks (CNNs) that consist of comparatively less number of convolutional layers. The use of transfer learning in the proposed approach overcomes the limitation of small datasets whereas the use of lightweight CNN models reduces the overhead of the training time of the model. The proposed model is validated with the IITD-II ear dataset in which we achieved recognition accuracy of 95.96% and 93.08% through weighted ensemble and average ensemble techniques. The combined approach of transfer learning and deep CNN show improvements in performance accuracy by 2–4% when compared to individual models. It achieves a precision of 96.74, recall of 96.37, and f-score of 95.96 using the weighted ensemble method which is an improvement over the other state-of-the-art methods.
Similar content being viewed by others
Data availability
The datasets used in the current study are available from the corresponding author upon reasonable request. The link for the dataset is provided in the reference section.
References
Ahila Priyadharshini R, Arivazhagan S, Arun M (2021) A deep learning approach for person identification using ear biometrics. Appl Intell 51(4):2161–2172
Alshazly H, Linse C, Barth E, Martinetz T (2019) Ensembles of deep learning models and transfer learning for ear recognition. Sensors 19(19):4139
Barra S, De Marsico M, Nappi M, Riccio D (2014) Unconstrained ear processing: what is possible and what must be done. Signal and image processing for biometrics. Springer, Berlin, Heidelberg, pp 129–190
Chang K, Bowyer KW, Sarkar S, Victor B (2003) Comparison and combination of ear and face images in appearance-based biometrics. IEEE Trans Pattern Anal Mach Intell 25(9):1160–1165
Chowdhury DP, Bakshi S, Guo G, Sa PK (2018) On the applicability of tunable filter bank based feature for ear biometrics: a study from constrained to unconstrained. J Med Syst 42(1):1–20
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, IEEE. pp 248–255
El-Naggar S, Abaza A, Bourlai T (2018) Ear detection in the wild using faster R-CNN deep learning. In: 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), IEEE. pp 1124–1130
Emeršič Ž, Štruc V, Peer P (2017a) Ear recognition: more than a survey. Neurocomputing 255:26–39
Emeršič Ž, Štepec D, Štruc V, Peer P (2017b) Training convolutional neural networks with limited training data for ear recognition in the wild. arXiv preprint arXiv:1711.09952
Emeršič Ž, Štepec D, Štruc V, Peer P, George A, Ahmad A, Omar E, Boult TE, Safdaii R, Zhou Y, Zafeiriou S (2017c) The unconstrained ear recognition challenge. In 2017 IEEE International Joint Conference on biometrics (IJCB), IEEE. pp 715–724
Emeršič Ž, Gabriel LL, Štruc V, Peer P (2017d) Pixel-wise ear detection with convolutional encoder-decoder networks. arXiv preprint arXiv:1702.00307
Emeršič Ž, SV AK, Harish BS, Gutfeter W, Khiarak JN, Pacut A, Hansley E, Segundo MP, Sarkar S, Park HJ, Nam GP (2019) The Unconstrained Ear Recognition Challenge 2019. In 2019 International Conference on Biometrics (ICB), IEEE. pp 1–15
Emeršič Ž, Meden B, Peer P, Štruc V (2020) Evaluation and analysis of ear recognition models: performance, complexity and resource requirements. Neural Comput Appl 32(20):15785–15800
Eyiokur FI, Yaman D, Ekenel HK (2018) Domain adaptation for ear recognition using deep convolutional neural networks. IET Biom 7(3):199–206
Garcia-Gasulla D, Vilalta A, Parés F, Ayguadé E, Labarta J, Cortés U, Suzumura T (2018) An out-of-the-box full-network embedding for convolutional neural networks. In: 2018 IEEE International Conference on Big Knowledge (ICBK), IEEE. pp 168–175
Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 580–587
Guo G, Zhang N (2018) What is the challenge for deep learning in unconstrained face recognition? In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), IEEE. pp 436–442
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4700–4708
Hurley DJ, Nixon MS, Carter JN (2000) Automatic ear recognition by force field transformations. In IEE colloquium on visual biometrics (Ref. No. 2000/018), IET. pp 1–7
Hurley DJ, Nixon MS, Carter JN (2005) Force field energy functional for ear biometrics. Comput vis Image Underst 98(3):491–512
Kacar U, Kirci M (2019) ScoreNet: deep cascade score level fusion for unconstrained ear recognition. IET Biom 8(2):109–120
Khaldi Y, Benzaoui A (2021) A new framework for gray-scale ear image recognition using generative adversarial networks under unconstrained conditions. Evol Syst 12(4):923–934
Kolesnikov A, Beyer L, Zhai X, Puigcerver J, Yung J, Gelly S, Houlsby N (2020) Big transfer (bit): general visual representation learning. In: European conference on computer vision. Springer, Cham. pp 491–507
Kornblith S, Shlens J, Le QV (2019) Do better imagenet models transfer better? In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 2661–2671
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems, 25
Kumar A, Wu C (2007) IITD-II: Ear database. http://www4.comp.polyu.edu.hk/~csajaykr/myhome/database_request/ear/
Kumar A, Zhang D (2007) Ear authentication using log-gabor wavelets. In: Biometric technology for human identification IV, vol 6539. SPIE, pp 92–96
Kumar Singh K, Kumar S, Antonakakis M, Moirogiorgou K, Deep A, Kashyap KL, Bajpai MK, Zervakis M (2022) Deep learning capabilities for the categorization of microcalcification. Int J Environ Res Public Health 19(4):2159
Mehta R, Singh KK (2022) Ear recognition system using averaging ensemble technique. In: International Conference on Machine Learning, Image Processing, Network Security and Data Sciences. Springer Nature Switzerland, Cham. pp 220–229
Mehta R, Singh KK (2023a) An efficient ear recognition technique based on deep ensemble learning approach. Evol Syst. https://doi.org/10.1007/s12530-023-09505-0
Mehta R, Singh KK (2023b) Deep convolutional neural network-based effective model for 2D ear recognition using data augmentation. Imaging Sci J. https://doi.org/10.1080/13682199.2023.2206763
Mehta R, Singh KK (2023c) 2D ear recognition using data augmentation and deep CNN. In: Machine vision and augmented intelligence: select proceedings of MAI 2022. Springer Nature Singapore, Singapore. pp 467–474
Mehta R, Singh KK (2023d) A comparative analysis of 2D ear recognition for constrained and unconstrained dataset using deep learning approach. In: Machine Vision and Augmented Intelligence: Select Proceedings of MAI 2022. Springer Nature Singapore, Singapore. pp 337–343
Mehta R, Garain J, Singh KK (2022) Cohort selection using Mini-batch K-means clustering for ear recognition. Advances in intelligent computing and communication. Springer, Singapore, pp 273–279
Mehta R, Ujjwal G, Shilpa SJ, Vityazev S, Singh KK (2023a) Rotation invariant 2D ear recognition using gabor filters and ensemble of pre-trained deep convolutional neural network model. In: 2023, 25th International Conference on Digital Signal Processing and its Applications (DSPA), IEEE. pp 1–6
Mehta R, Sheikh-Akbari A, Singh KK (2023b) A noble approach to 2D ear recognition system using hybrid transfer learning. In: 2023 12th Mediterranean Conference on Embedded Computing (MECO), IEEE. pp 1–5
Mehta R, Shukla S, Pradhan J, Singh KK, Kumar A (2023c) A vision transformer-based automated human identification using ear biometrics. J Inf Secur Appl 78:103599
Nejati H, Zhang L, Sim T, Martinez-Marroquin E, Dong G (2012) Wonder ears: Identification of identical twins from ear images. In: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012). IEEE, pp 1201–1204
Nosrati MS, Faez K, Faradji F (2007) Using 2D wavelet and principal component analysis for personal identification based on 2D ear structure. In: 2007 International Conference on Intelligent and Advanced Systems, IEEE. pp 616–620
Omara I, Wu X, Zhang H, Du Y, Zuo W (2018) Learning pairwise SVM on hierarchical deep features for ear recognition. IET Biom 7(6):557–566
Oquab M, Bottou L, Laptev I, Sivic J (2014) Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 1717–1724
Pan S, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Discov Data Eng 22(10):1345–1359
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC (2015) Imagenet large-scale visual recognition challenge. Int J Comput vis 115(3):211–252
Saikia T, Kumar R, Kumar D, Singh KK (2022) An automatic lung nodule classification system based on hybrid transfer learning approach. SN Comput Sci 3(4):1–10
Saikia T, Singh KK, Vityazev S, Sheikh Akbari A (2023) Introduction to various optimization techniques. IETE Technical Review, pp 1–13
Shilpa SJ, Mehta R, Vityazev S, Singh KK (2023) Epileptic seizure prediction using 1D-MobileNet. In: 2023 25th International Conference on Digital Signal Processing and its Applications (DSPA), IEEE. pp 1–5
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Singh O, Singh KK (2023) An approach to classify lung and colon cancer of histopathology images using deep feature extraction and an ensemble method. Int J Inf Technol 15(8):4149–4160
Unar JA, Seng WC, Abbasi A (2014) A review of biometric technology along with trends and prospects. Pattern Recogn 47(8):2673–2688
Upadhyay RR, Mehta R, Singh KK (2023) Multi-dilation convolutional neural network for automatic handwritten signature verification. SN Comput Sci 4(5):476
Wang Z, Yang J, Zhu Y (2021) Review of ear biometrics. Arch Comput Methods Eng 28(1):149–180
Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big Data 3(1):1–40
Zarachoff M, Sheikh-Akbari A, Monekosso D (2018) 2D multi-band PCA and its application for ear recognition. In: 2018 IEEE International Conference on Imaging Systems and Techniques (IST), IEEE. pp 1–5
Zarachoff M, Sheikh-Akbari A, Monekosso D (2019) Single image ear recognition using wavelet-based multi-band PCA. In: 2019 27th European Signal Processing Conference (EUSIPCO), IEEE. pp 1–4
Zarachoff MM, Sheikh-Akbari A, Monekosso D (2021) Non-decimated wavelet based multi-band ear recognition using principal component analysis. IEEE Access 10:3949–3961
Zhang Y, Mu Z, Yuan L, Yu C (2018) Ear verification under uncontrolled conditions with convolutional neural networks. IET Biom 7(3):185–198
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
Mehta, R., Singh, K.K. Ensemble of transfer learning and light-weight convolutional neural network model for an effective ear recognition system. Evolving Systems 15, 115–131 (2024). https://doi.org/10.1007/s12530-023-09561-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12530-023-09561-6