Will Wrinkle Estimate the Face Age?

Ng, Choon-Ching; Yap, Moi Hoon; Costen, Nicholas; Li, Baihua

doi:10.1109/smc.2015.423

Cited by 13 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mean Absolute Error (MAE) and Cumulative Score (CS). MAE is the average of absolute errors between estimated age and the ground truth [44], it is commonly used in previous age estimation research to measure the accuracy of an algorithm. The mathematical form of MAE is shown in equation 1.…”

Section: Performance Metrics For Age Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Computational Intelligence in Automatic Face Age Estimation: A Survey

Osman

Yap

2019

IEEE Trans. Emerg. Top. Comput. Intell.

Self Cite

View full text Add to dashboard Cite

With the rapid growth of computational intelligence techniques, automatic face age estimation has achieved good accuracy that benefited real-world applications such as access control and monitoring, soft biometrics and information retrieval. Over the past decade, many new algorithms were developed and previous surveys on face age estimation were either outdated or incomplete. Considering the importance of the expanding research in this topic, we aim to provide an up-to-date survey on the face age estimation techniques. First we summarise the stateof-the-art databases and the performance metrics for face age estimation. Then we review the age estimation techniques based on three categories of face features (local, global and hybrid) and discuss different types of age learning algorithms. Finally, we identify the challenges and provide new insights for future research directions of fully automated face age estimation.

show abstract

Section: Performance Metrics For Age Estimationmentioning

confidence: 99%

“…Recently, there are different works that focus on wrinkles in age estimation algorithms [61], [62], [63], [44], [48], [64]. El-Dib and Onsi [42] investigated the ability of wrinkled appearance in eyes, the face parts excluding the forehead and the whole face to estimate the age.…”

Section: A Features Extractionmentioning

confidence: 99%

Computational Intelligence in Automatic Face Age Estimation: A Survey

Osman

Yap

2019

IEEE Trans. Emerg. Top. Comput. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the local approach, this refers to representing local features such as wrinkles, spots and pores in an ageing pattern and then the corresponding age is estimated by regression. One might think that local features can only be used for age group classification, Ng et al [19] has proven that a specific age can be learned and estimated from the wrinkle-based features. They present wrinkle by the pixel intensity values at different wrinkle locations.…”

Section: Face Age Estimationmentioning

confidence: 99%

“…Knowledge of skin histology will deepen the understanding of cutaneous changes associated with ageing and will promote optimal cosmetic and functional patient outcomes. Due to these reasons, research into age estimation by using local features has gained increasing attention, e.g., bio-inspired features (BIF) [26], kernel-based local binary patterns (KLBP) [27] and wrinkles [19].…”

Section: Wrinkles Patternmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Ageing Patterns for face age estimation

Yap

Cheng

et al. 2018

Image and Vision Computing

Self Cite

View full text Add to dashboard Cite

Wrinkles can be embedded in several image-based applications as a descriptor for human skin. However, wrinkle-based age estimation research has not been widely addressed. In this paper, we introduce a Multi-scale Wrinkle Patterns (MWP) representation, investigate the effect of wrinkles on face age estimation and propose Hybrid Ageing Patterns (HAP) for face age estimation. To define the wrinkle regions more precisely, a template consisting of 10 regions constructed relatively to a set of automatically located facial landmarks is used. We extract the multi-scale wrinkles in each region and encode them into MWP. We use Support Vector Regression to estimate age from the combination of such patterns. The performance of the algorithms is assessed by using Mean Absolute Error (MAE) on three state-of-the-art datasets-FG-NET, FERET and MORPH. We observe that MWP produces a comparable MAE of 4.16 on FERET to the state of the art. Finally we propose HAP, which combines the features from MWP and the Facial Appearance Model (FAM), and demonstrate improved performance on FERET and MORPH with MAE of 3.02 (±2.92) and 3.68 (±2.98), respectively. Therefore, we conclude that MWP is an important complementary feature for face age estimation.

show abstract

Deep Learning Using Bayesian Optimization for Facial Age Estimation

Ahmed

Viriri

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Will Wrinkle Estimate the Face Age?

Cited by 13 publications

References 35 publications

Computational Intelligence in Automatic Face Age Estimation: A Survey

Computational Intelligence in Automatic Face Age Estimation: A Survey

Hybrid Ageing Patterns for face age estimation

Deep Learning Using Bayesian Optimization for Facial Age Estimation

Contact Info

Product

Resources

About