ABSTRACT
In spite of the extensive research that has been performed on age detection with a single face image, little attention has been paid to younger face recognition given an image pair. Our paper addresses the problem by proposing a perceptual flow extraction algorithm, followed by a CNN based transfer learning for the recognition purpose. In particular, our algorithm first employs just noticeable difference scheme for filtering face images, so that the noise that cannot be perceived by the human visual system is reduced. Then, by fusing Laplacian stacks into our flow approximation framework, the estimated perceptual flow is able to capture features at multiple scales. Due to the lack of data and the difficulty of collecting and annotating face image pairs, we have also introduced a dataset based on the UTKFace dataset for the purpose. Experiments demonstrate the effectiveness of our approach.
Supplemental Material
Available for Download
Presentation slides
- Aaron F. Bobick and James W. Davis. 2001. The recognition of human movement using temporal templates. IEEE Transactions on pattern analysis and machine intelligence 23, 3(2001), 257–267.Google ScholarDigital Library
- Alexey Dosovitskiy, Philipp Fischer, Eddy Ilg, Philip Hausser, Caner Hazirbas, Vladimir Golkov, Patrick Van Der Smagt, Daniel Cremers, and Thomas Brox. 2015. Flownet: Learning optical flow with convolutional networks. In Proceedings of the IEEE international conference on computer vision. 2758–2766.Google ScholarDigital Library
- Berthold KP Horn and Brian G Schunck. 1981. Determining optical flow. Artificial intelligence 17, 1-3 (1981), 185–203.Google Scholar
- Eddy Ilg, Nikolaus Mayer, Tonmoy Saikia, Margret Keuper, Alexey Dosovitskiy, and Thomas Brox. 2017. Flownet 2.0: Evolution of optical flow estimation with deep networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2462–2470.Google ScholarCross Ref
- Ranjan Jana and Abhishek Basu. 2017. Automatic age estimation from face image. In 2017 International Conference on Innovative Mechanisms for Industry Applications (ICIMIA). IEEE, 87–90.Google ScholarCross Ref
- Gil Levi and Tal Hassner. 2015. Age and gender classification using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 34–42.Google ScholarCross Ref
- Anmin Liu, Weisi Lin, Manoranjan Paul, Chenwei Deng, and Fan Zhang. 2010. Just noticeable difference for images with decomposition model for separating edge and textured regions. IEEE Transactions on Circuits and Systems for Video Technology 20, 11(2010), 1648–1652.Google ScholarDigital Library
- Ce Liu, Jenny Yuen, and Antonio Torralba. 2010. Sift flow: Dense correspondence across scenes and its applications. IEEE transactions on pattern analysis and machine intelligence 33, 5(2010), 978–994.Google Scholar
- David G Lowe. 2004. Distinctive image features from scale-invariant keypoints. International journal of computer vision 60, 2 (2004), 91–110.Google ScholarDigital Library
- Jiayi Ma, Chen Chen, Chang Li, and Jun Huang. 2016. Infrared and visible image fusion via gradient transfer and total variation minimization. Information Fusion 31(2016), 100–109.Google ScholarDigital Library
- Jerome Revaud, Philippe Weinzaepfel, Zaid Harchaoui, and Cordelia Schmid. 2015. Epicflow: Edge-preserving interpolation of correspondences for optical flow. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1164–1172.Google ScholarCross Ref
- Rasmus Rothe, Radu Timofte, and Luc Van Gool. 2018. Deep expectation of real and apparent age from a single image without facial landmarks. International Journal of Computer Vision 126, 2 (2018), 144–157.Google ScholarDigital Library
- Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1–9.Google ScholarCross Ref
- Oliver Van Kaick, Hao Zhang, Ghassan Hamarneh, and Daniel Cohen-Or. 2011. A survey on shape correspondence. In Computer graphics forum, Vol. 30. Wiley Online Library, 1681–1707.Google Scholar
- Liangliang Wang, Ruifeng Li, and Yajun Fang. 2016. Energy flow: image correspondence approximation for motion analysis. Optical Engineering 55, 4 (2016), 043109.Google ScholarCross Ref
- Philippe Weinzaepfel, Jerome Revaud, Zaid Harchaoui, and Cordelia Schmid. 2013. DeepFlow: Large displacement optical flow with deep matching. In Proceedings of the IEEE international conference on computer vision. 1385–1392.Google ScholarDigital Library
- Zhifei Zhang, Yang Song, and Hairong Qi. 2017. Age progression/regression by conditional adversarial autoencoder. In Proceedings of the IEEE conference on computer vision and pattern recognition. 5810–5818.Google ScholarCross Ref
Recommendations
Age-Invariant Face Recognition
One of the challenges in automatic face recognition is to achieve temporal invariance. In other words, the goal is to come up with a representation and matching scheme that is robust to changes due to facial aging. Facial aging is a complex process that ...
Face recognition under varying illumination using gradientfaces
In this correspondence, we propose a novel method to extract illumination insensitive features for face recognition under varying lighting called the Gradientfaces. Theoretical analysis shows Gradientfaces is an illumination insensitive measure, and ...
Comments