A Survey on Age Estimation Techniques

Soman, Somy; Austine, Amel

doi:10.5120/ijca2017913176

Cited by 2 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…b) Biometrics and Demographics Analysis: Age estimation from faces has seen most impressive progress in recent years, mostly due to the application of deep learning methodology. [7] provides a concise overview and [8] can be seen as one of the most recent state-of-the-art solutions. Overall, state-of-the-art technology appears to be well capable of estimating the age of people from their faces in the range a Mean Absolute Error (MAE) of less than 3 years on publicly available datasets.…”

Section: Scientific Contextmentioning

confidence: 99%

Getting to Know Your Robot Customers: Automated Analysis of User Identity and Demographics for Robots in the Wild

Herrero¹,

Fentanes

Hanheide

2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Long-term studies with autonomous robots "in the wild" (deployed in real-world human-inhabited environments) are among the most laborious and resource-intensive endeavours in Human-Robot Interaction. Even if a robot system itself is robust and well-working, the analysis of the vast amounts of user data one aims to collect and analyse poses a significant challenge. This paper proposes an automated processing pipeline, using state-of-the-art computer-vision technology to estimate demographic factors from users' faces and re-identify them to establish usage patterns. It overcomes the problem of explicitly recruiting participants and having them fill questionnaires about their demographic background, and allows to study completely unsolicited and non-primed interactions over long periods of time. The paper offers a comprehensive assessment of the performance of the automated analysis with data from 68 days of continuous deployment of a robot in a care home, and also presents a set of findings obtained through the analysis, underpinning the viability of the approach.

show abstract

Section: Scientific Contextmentioning

confidence: 99%

Getting to Know Your Robot Customers: Automated Analysis of User Identity and Demographics for Robots in the Wild

Herrero¹,

Fentanes

Hanheide

2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Gender plays a vital role in the aging process because features and aging patterns are distinct in masculine and feminine [2]. Although the area of age estimation has grown a lot, it is still difficult to estimate an age of person because the process of aging is influenced by factors like change in shape and size of face, environment, eating habits, living pattern, etc.…”

Section: Introductionmentioning

confidence: 99%

“…Unknown brightness conditions, non-frontal facial poses, and availability of facial expressions are some of the factors. Especially, facial expressions like the smile might induce negatively accuracy of automated systems [2]: When a person smiles wrinkles are generated. These wrinkles can be ambiguous when only the actualization features are taken into consideration.…”

Section: Introductionmentioning

confidence: 99%

“…Somy Soman and Amel Austine[2] compare the Age Estimation Techniques which includes Facial Aging Patterns, Regression on Discriminative Aging Manifold, Manifold Learning and Locally Adjusted Robust Regression, Compositional and Dynamic Model, Grouping and Decision Fusion, Combining Facial Dynamics with Appearance, etc. They observed that the most usually used database is FG-NET and the most frequently used age estimation method is regression based because it considers the inter-relationship among the age values.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Survey on Age Estimation System

Gunjal¹,

Abin²

2018

IJCA

View full text Add to dashboard Cite

There has been a enlarge interest in the automatic determination of age from facial photograph due to a lot of inherent applications. However, in spite of advances in automatic age estimation, it remains a difficult problem because the face aging process does not depend only by intrinsic factors, e.g. genetic factors, but also on extrinsic factors, e.g. lifestyle, environment, and expression. The recognition properties of face images have been well investigated in real-world applications. Although the wide survey of person recognition from face images, there is only a small amount of research carried out on how to exactly estimate and use the analytical information contained in face images such as age, gender, and nationality. Some of the inherent applications of automatic estimation of age are: (i)Law enforcement: Automatic age estimation systems will facilitate to see the inherent suspects more accurately and expertly by sorting the gallery database of images using the estimated age of the input photographs. (ii)Security control: an Associate degree automatic age estimation system can be used to prohibit minors from buying alcohol or cigarette from vending machines or getting access to improper web pages. (iii)Human-computer interaction (HCI)-the system can modify the contents given to a user based on their age. Experimentation has been performed on Appa-Real-Release dataset and observed that Mean Absolute Error be minimized using RBF-Kernel.

show abstract

A Survey on Age Estimation Techniques

Cited by 2 publications

References 10 publications

Getting to Know Your Robot Customers: Automated Analysis of User Identity and Demographics for Robots in the Wild

Getting to Know Your Robot Customers: Automated Analysis of User Identity and Demographics for Robots in the Wild

Survey on Age Estimation System

Contact Info

Product

Resources

About