Age estimation via face images: a survey

Angulu, Raphael; Tapamo, Jules-Raymond; Adewumi, Aderemi Oluyinka

doi:10.1186/s13640-018-0278-6

Cited by 114 publications

(70 citation statements)

References 188 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing Age estimation approaches usually consist of two components: an age feature extraction module and an age prediction module. More detailed surveys on age estimation can be found in (Fu et al, 2010;Angulu et al, 2018). One of the early works by Kwon and da Vi-toria Lobo (1999) measured the facial shape changes using geometric of key features to classify faces into three age groups, i.e.…”

Section: Age Progressionmentioning

confidence: 99%

Learning from Longitudinal Face Demonstration—Where Tractable Deep Modeling Meets Inverse Reinforcement Learning

et al. 2019

View full text Add to dashboard Cite

This paper presents a novel Subject-dependent Deep Aging Path (SDAP), which inherits the merits of both Generative Probabilistic Modeling and Inverse Reinforcement Learning to model the facial structures and the longitudinal face aging process of a given subject. The proposed SDAP is optimized using tractable log-likelihood objective functions with Convolutional Neural Networks (CNNs) based deep feature extraction. Instead of applying a fixed aging development path for all input faces and subjects, SDAP is able to provide the most appropriate aging development path for individual subject that optimizes the reward aging formulation. Unlike previous methods that can take only one image as the input, SDAP further allows multiple images as inputs, i.e. all information of a subject at either the same or different ages, to produce the optimal aging path for the given subject. Finally, SDAP allows efficiently synthesizing in-thewild aging faces. The proposed model is experimented in both tasks of face aging synthesis and cross-age face verification. The experimental results consistently show SDAP achieves the state-of-the-art performance on numerous face aging databases, i.e. FG-NET, MORPH, AginG Faces in the Wild (AGFW), and Cross-Age Celebrity Dataset (CACD). Furthermore, we also evaluate the performance of SDAP on large-scale Megaface challenge to demonstrate the advantages of the proposed solution.

show abstract

Section: Age Progressionmentioning

confidence: 99%

Learning from Longitudinal Face Demonstration—Where Tractable Deep Modeling Meets Inverse Reinforcement Learning

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The human face is also affected by facial expression, head profile, occlusion and aging. 3 Because of its individualizing characteristics, the human face is used for identification purposes. 2,4 The human face as a tool for identification has been used in real-world applications.…”

Section: Introductionmentioning

confidence: 99%

“…Due to rapid advances in technologies, age estimation can be proceeded by face image and analysed in smartphone. 3 The interference of smartphone makes the age perception easier, faster and can be used widely in every place. Smartphones' utilization is also part of green dentistry which helps reduces waste, pollutions, and research costs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Age Estimation with Smartphone: Is It Reliable for Forensics Identification?

et al. 2020

View full text Add to dashboard Cite

Age estimation is one of the important components in forensic science used for personal identification, biological profile reconstruction, and help narrowing the search possibilities. Age estimation can be done by various methods and biological evidence, such as the human face. The human face is one of biometrics that provides a variety of information. The purpose of this article is to evaluate the accuracy and reliability of age estimation with face using smartphone for forensic identification based on previous studies and experiences. Age estimation by face is based on age progression that causes attrition and degeneration on soft tissue. With the development of technology, age estimation by face can be done with applications or websites on smartphone. In general, the utilization of smartphone can reduce waste, pollution, research cost and easier to save and share. A lot of applications have been developed and free to download. Unfortunately, the accuracy of its results is unknown. In conclusion, the applications for age estimation on smartphone give quiet good results and can be used as a supporting tool to estimate age in forensic identification.

show abstract

“…Automatic age estimation from still images is intensively studied in Computer Vision [1]- [3] due to its wide range of possible applications, including forensics [4], monitoring and surveillance [5] (e.g., to search for a suspect with a specific age in a database), and recommendation systems [6] (e.g., "how do I perceive to others? "), just to mention a few.…”

Section: Introductionmentioning

confidence: 99%

On the effect of age perception biases for real age regression

Jacques

Özçinar

Marjanović

et al. 2019

2019 14th IEEE International Conference on Automatic Face &Amp; Gesture Recognition (FG 2019)

View full text Add to dashboard Cite

Automatic age estimation from facial images represents an important task in computer vision. This paper analyses the effect of gender, age, ethnic, makeup and expression attributes of faces as sources of bias to improve deep apparent age prediction. Following recent works where it is shown that apparent age labels benefit real age estimation, rather than direct real to real age regression, our main contribution is the integration, in an end-to-end architecture, of face attributes for apparent age prediction with an additional loss for real age regression. Experimental results on the APPA-REAL dataset indicate the proposed network successfully take advantage of the adopted attributes to improve both apparent and real age estimation. Our model outperformed a state-of-the-art architecture proposed to separately address apparent and real age regression. Finally, we present preliminary results and discussion of a proof of concept application using the proposed model to regress the apparent age of an individual based on the gender of an external observer.

show abstract

Age estimation via face images: a survey

Cited by 114 publications

References 188 publications

Learning from Longitudinal Face Demonstration—Where Tractable Deep Modeling Meets Inverse Reinforcement Learning

Learning from Longitudinal Face Demonstration—Where Tractable Deep Modeling Meets Inverse Reinforcement Learning

Age Estimation with Smartphone: Is It Reliable for Forensics Identification?

On the effect of age perception biases for real age regression

Contact Info

Product

Resources

About