Do Alzheimer’s Patients Appear Younger than Their Ageƒ A Study with Automatic Facial Age Estimation

Facial age estimation from images is a challenging task, especially if the subjects are older, since idiosyncratic variations increase with age, and lifestyle factors have an impact on the appearance. In this paper, we test the hypothesis that the Alzheimer’s patients appear younger than their real age. To do this objectively, and to be able to analyze the factors in case the hypothesis holds true, we use automatic age estimation methods for this task. We first propose training and normalization regimes to improve deep learning based facial age estimation. We fine-tune a pre-trained ImageNet model using first the APPA-REAL database and then the UTKFACE database. The experimental results show that the proposed approach predicts older faces more accurately compared to other studies, and improves the mean absolute error for the FG-NET database to 8.14 for the age group 60-69. We then run our approach on a special database collected from Alzheimer’s patients and healthy controls, to test our main hypothesis. The database we collected for this purpose contains video recordings of 96 subjects with an age range between 64 and 87. Our findings show that automatic age estimation indeed underestimates the age of AD patients significantly more than the healthy subjects.

[1]  Ville Ojansivu,et al.  Blur Insensitive Texture Classification Using Local Phase Quantization , 2008, ICISP.

[2]  Albert Ali Salah,et al.  Combining Facial Dynamics With Appearance for Age Estimation , 2015, IEEE Transactions on Image Processing.

[3]  Jhony K. Pontes,et al.  A flexible hierarchical approach for facial age estimation based on multiple features , 2016, Pattern Recognit..

[4]  Tao Xiang,et al.  Interestingness Prediction by Robust Learning to Rank , 2014, ECCV.

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Bappaditya Mandal,et al.  Spontaneous Versus Posed Smiles - Can We Tell the Difference? , 2016, CVIP.

[7]  Luc Van Gool,et al.  Deep Expectation of Real and Apparent Age from a Single Image Without Facial Landmarks , 2016, International Journal of Computer Vision.

[8]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[9]  Yun Fu,et al.  Locally Adjusted Robust Regression for Human Age Estimation , 2008, 2008 IEEE Workshop on Applications of Computer Vision.

[10]  A. Gunay,et al.  Automatic age classification with LBP , 2008, 2008 23rd International Symposium on Computer and Information Sciences.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  Jian-Jiun Ding,et al.  Facial age estimation based on label-sensitive learning and age-oriented regression , 2013, Pattern Recognit..

[13]  S. N. Kohail,et al.  Using artificial neural network for human age estimation based on facial images , 2012, 2012 International Conference on Innovations in Information Technology (IIT).

[14]  A. Vighetto,et al.  Impaired Social Cognition in Mild Alzheimer Disease , 2009, Journal of geriatric psychiatry and neurology.

[15]  Albert Ali Salah,et al.  A smile can reveal your age: enabling facial dynamics in age estimation , 2012, ACM Multimedia.

[16]  Cuixian Chen,et al.  Face age estimation using model selection , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[17]  Yang Song,et al.  Age Progression/Regression by Conditional Adversarial Autoencoder , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Xiaolin Hu,et al.  Joint Training of Cascaded CNN for Face Detection , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Seyyid Ahmed Medjahed.  A Comparative Study of Feature Extraction Methods in Images Classification , 2015 .

[20]  Kinjal Mistree,et al.  Feature extraction for facial age estimation: A survey , 2016, 2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET).

[21]  Jules-Raymond Tapamo,et al.  Age estimation via face images: a survey , 2018, EURASIP Journal on Image and Video Processing.

[22]  David P. Salmon,et al.  Recognition and naming of famous faces in Alzheimer's disease: A cognitive analysis , 1993, Neuropsychologia.

[23]  Bappaditya Mandal,et al.  Spontaneous vs. Posed smiles - can we tell the difference? , 2016, ArXiv.

[24]  Yun Fu,et al.  Age Synthesis and Estimation via Faces: A Survey , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Zhi-Hua Zhou,et al.  Facial Age Estimation by Learning from Label Distributions , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Motaz El-Saban,et al.  Human age estimation using enhanced bio-inspired features (EBIF) , 2010, 2010 IEEE International Conference on Image Processing.

[27]  A. Kaszniak,et al.  Emotional Experience and Facial Expression in Alzheimer's Disease , 2006, Neuropsychology, development, and cognition. Section B, Aging, neuropsychology and cognition.

[28]  R. Chellappa,et al.  Age progression in Human Faces : A Survey , 2008 .

[29]  Bill Triggs,et al.  Visual Recognition Using Local Quantized Patterns , 2012, ECCV.

[30]  Ching Y. Suen,et al.  Spectral Regression based age determination , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[31]  Shuo Yang,et al.  Faceness-Net: Face Detection through Deep Facial Part Responses , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Xavier Baró,et al.  Apparent and Real Age Estimation in Still Images with Deep Residual Regressors on Appa-Real Database , 2017, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[33]  Kha Gia Quach,et al.  Fine Tuning Age-estimation with Global and Local Facial Features , 2011 .

[34]  A. Albert,et al.  A review of the literature on the aging adult skull and face: implications for forensic science research and applications. , 2007, Forensic science international.

[35]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

[36]  Yun Fu,et al.  Human age estimation using bio-inspired features , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Tal Hassner,et al.  Facial Landmark Detection with Tweaked Convolutional Neural Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Irena Balciuniene,et al.  Factors influencing face aging. Literature review. , 2011, Stomatologija.

[39]  C. Christodoulou,et al.  Comparing different classifiers for automatic age estimation , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[40]  Josephine Sullivan,et al.  One millisecond face alignment with an ensemble of regression trees , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[41]  Maja Pantic,et al.  A Dynamic Appearance Descriptor Approach to Facial Actions Temporal Modeling , 2014, IEEE Transactions on Cybernetics.

[42]  Xiaoming Liu,et al.  Demographic Estimation from Face Images: Human vs. Machine Performance , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  Rama Chellappa,et al.  HyperFace: A Deep Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.