Small Sample Face Recognition Algorithm based on Novel Siamese Network
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn’t need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFace1, which uses pairs of face images as inputs and maps them to target space so that the L2 norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition.
Abstract
In face recognition, sometimes the number of available training samples for single category is insufficient. Therefore, the performances of models trained by convolutional neural network are not ideal. The small sample face recognition algorithm based on novel Siamese network is proposed in this paper, which doesn’t need rich samples for training. The algorithm designs and realizes a new Siamese network model, SiameseFace1, which uses pairs of face images as inputs and maps them to target space so that the L2 norm distance in target space can represent the semantic distance in input space. The mapping is represented by the neural network in supervised learning. Moreover, a more lightweight Siamese network model, SiameseFace2, is designed to reduce the network parameters without losing accuracy. We also present a new method to generate training data and expand the number of training samples for single category in AR and labeled faces in the wild (LFW) datasets, which improves the recognition accuracy of the models. Four loss functions are adopted to carry out experiments on AR and LFW datasets. The results show that the contrastive loss function combined with new Siamese network model in this paper can effectively improve the accuracy of face recognition.
참고문헌 (31)
- Stephen. ID, "Facial Shape Analysis Identifies Valid Cues to Aspects of Physiological Health in Caucasian, Asian, and African Populations", Frontiers in psychology, 8 (2017)
- Blanco-Gonzalo R, "Time evolution of face recognition in accessible scenarios", Human-centric Computing and Information Sciences, 5(1), pp.24~24 (2015)
- Maze. B, "IARPA Janus Benchmark–C: Face Dataset and Protocol", Proceedings of the 11th IAPR International Conference on Biometrics (2018)
- Liu. F, "Local similarity based linear discriminant analysis for face recognition with single sample per person", Asian Conference on Computer Vision (2014)
- Tsalakanidou. F, "Use of depth and colour eigenfaces for face recognition", Pattern Recognition Letters, 24(9-10), pp.1427~1435 (2003)
- He. X, "Face recognition using laplacianfaces", IEEE transactions on pattern analysis and machine intelligence, 27(3), pp.328~340 (2005)
- Ya. Tu, "Semi-supervised Learning with Generative Adversarial Networks on Digital Signal Modulation Classification", Computers Materials Continua, 55(2), pp.243~254 (2018)
- Ning Yu, "Deep Learning in Genomic and Medical Image Data Analysis: Challenges and Approaches", JIPS(Journal of Information Processing Systems), 13(2), pp.204~214 (2017), 한국정보처리학회[DOI]
- Koo K M, "Image recognition performance enhancements using image normalization", Human-centric Computing and Information Sciences, 7(1), pp.33~33 (2017)
- Sainath. T. N, "Multichannel signal processing with deep neural networks for automatic speech recognition", IEEE Transactions on AudioSpeech, and Language Processing, 25(5), pp.965~979 (2017)
- 이상걸, "Variations of AlexNet and GoogLeNet to Improve Korean Character Recognition Performance", JIPS(Journal of Information Processing Systems), 14(1), pp.205~217 (2018), 한국정보처리학회[DOI]
- Chopra. S, "Learning a similarity metric discriminatively, with application to face verification", IEEE Conference on Computer Vision and Pattern Recognition (2005)
- Wright. J, "Robust face recognition via sparse representation", IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(2), pp.210~227 (2009)
- Yang. M, "Gabor feature based sparse representation for face recognition with gabor occlusion dictionary", European Conference on Computer Vision (2010)
- Zhang. L, "Sparse representation or collaborative representation: Which helps face recognition?", IEEE International Conference on Computer Vision (2011)
- Vo. D. M, "Robust face recognition via hierarchical collaborative representation", Information Sciences, 432, pp.332–346~332–346 (2018)
- Chen Li, "Face Recognition Based on the Combination of Enhanced Local Texture Feature and DBN under Complex Illumination Conditions", JIPS(Journal of Information Processing Systems), 14(1), pp.191~204 (2018), 한국정보처리학회[DOI]
- Whitelam. C, "IARPA Janus Benchmark-B Face Dataset", Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops (2017)
- Tran. L, "Disentangled representation learning gan for pose-invariant face recognition", Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition (2017)
- CHEN. Dong, "Blessing of dimensionality: high dimensional feature and its efficient compression for face verification", Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition (2013)
- Simonyan. K, "Fisher Vector Faces in the Wild", Proceedings of 2013 British Machine Vision Conference (2013)
- Zhu. Z, "Recover canonical-view faces in the wild with deep neural networks", arXiv 2014arXiv:1404.3543, ~
- Taigman. Y, "DeepFace: closing the gap to human-level performance in face verification", Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition (2014)
- Yi. Sun, "Deep learning face representation from predicting 10,000 classes", Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition (2014)
- Yi. Sun, "Deep learning face representation by joint identification-verification", Proceedings of the 28th Annual Conference on Neural Information Processing Systems (2014)
- Parchami. M, "Video-based face recognition using ensemble of haar-like deep convolutional neural networks", International Joint Conference on Neural Networks (2017)
- Schroff. F, "FaceNet: A unified embedding for face recognition and clustering", Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (2015)
- Chen. D, "Bayesian face revisited: A joint formulation", European Conference on Computer Vision (2012)
- Barkan. O, "Fast high dimensional vector multiplication face recognition", IEEE International Conference on Computer Vision (2013)
- Berlemont. S, "Class-balanced siamese neural networks", Neurocomputing, 273, pp.47~56 (2018)
- Shaham. U, "Learning by coincidence: siamese networks and common variable learning", Pattern Recognition, 74, pp.52~63 (2018)