Person-specific age estimation under ranking framework

Age estimation is a complex issue of multiclassification or regression. To address a common problem of uneven distribution of age database, this paper shows a hierarchic age estimation system, comprising age group and specific age estimation. In our system, two novel classifiers, Sequence K-Nearest Neighbor (SKNN) and Ranking-KNN, are introduced to predict age group and age value respectively. Notably, Ranking-KNN utilizes the ordinal information between samples in estimation process rather than regards samples as separate individuals. Tested on FG-NET database, our system achieves 5.37 evaluated by MAE (Mean Absolute Error) for age estimation. And the comparison between our solution and others is also shown.

show abstract

“…These algorithms are KNN [11], Ranking-SVM [12], Rank [13]. Table 4 shows that our system outperforms other similar age estimation systems.…”

Section: B Age Estimationmentioning

confidence: 98%

A Hierarchical System for Age Estimation Based on Appearance Feature and Ranking-KNN

Liang

Wang

Zhang

et al. 2013

2013 Fourth International Conference on Intelligent Systems Design and Engineering Applications

View full text Add to dashboard Cite

show abstract

“…Author provided the feasible solution to improve the feature extraction process and to perform the object recognition. Yong Ma [4] has presented a person specific approach to estimate the age of the person based on the feature ranking. Author defined a ranking framework to identify the facial features and to perform the recognition under the aging process.…”

Section: Existing Workmentioning

confidence: 99%

An Occluded Face Recognition Approach using Feature Specific KPCA Approach

Sharma¹,

Kumar²

2014

Proceedings of the 2014 International Conference on Information and Communication Technology for Competitive Strategies

View full text Add to dashboard Cite

Facial Recognition is having many challenges along with the application. One of such challenge is facial expression recognition. In this work, feature analysis based hybrid architecture is defined to perform facial expression recognition. The work is divided in two main stags. First to recognize the face itself and later on the recognition of facial expression is performed. In this paper, the feature analysis is performed based on Gabor filter analysis. Once the featured dataset is generated, the recognition is performed using probabilistic neural network and the KPCA approach. The Weighted Eigen distance threshold based analysis is performed to recognize the face as well as the expression. The obtained result shows the accurate detection of face and the expression.

show abstract

“…Some typical aging face images in this dataset are shown in Figure 2. As in [20], the Gabor features are extracted to represent each facial image, and the corresponding dimensionality of feature vector is 1868. Besides comparing with related feature selection algorithms, we also compare with the method in [10], which utilizes contextual features for age range estimation.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…For example, the face of a 5-year-old person is much more related to the face of a 10-year-old one than the face of a 30-year-old one. Motivated by ordinal characteristic of aging faces, some methods take age estimation as a ranking problem [4,29,20].…”

Section: Introductionmentioning

confidence: 99%

Learning ordinal discriminative features for age estimation

Liu

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

In this paper, we present a new method for facial age estimation based on ordinal discriminative feature learning. Considering the temporally ordinal and continuous characteristic of aging process, the proposed method not only aims at preserving the local manifold structure of facial images, but also it wants to keep the ordinal information among aging faces. Moreover, we try to remove redundant information from both the locality information and ordinal information as much as possible by minimizing nonlinear correlation and rank correlation. Finally, we formulate these two issues into a unified optimization problem of feature selection and present an efficient solution. The experiments are conducted on the public available Images of Groups dataset and the FG-NET dataset, and the experimental results demonstrate the power of the proposed method against the state-of-the-art methods.

show abstract

Person-specific age estimation under ranking framework

Cited by 13 publications

References 21 publications

A Hierarchical System for Age Estimation Based on Appearance Feature and Ranking-KNN

A Hierarchical System for Age Estimation Based on Appearance Feature and Ranking-KNN

An Occluded Face Recognition Approach using Feature Specific KPCA Approach

Learning ordinal discriminative features for age estimation

Contact Info

Product

Resources

About