Review: Single attribute and multi attribute facial gender and age estimation

Gupta, Sandeep; Nain, Neeta

doi:10.1007/s11042-022-12678-6

Cited by 16 publications

(8 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human faces have various related attributes, such as gender, race, and expression, which provide different useful information for age estimation [20]. Zhang et al.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐task multi‐scale attention learning‐based facial age estimation

Shi

Zhao

Zhang

et al. 2023

IET Signal Processing

View full text Add to dashboard Cite

Face‐based age estimation strongly depends on deep residual networks (ResNets), used as the backbone in the relevant research. However, ResNet‐based methods ignore the importance of some large‐scale facial information and other facial age attributes. Inspired by the attention mechanism, a multi‐task learning framework for face‐based age estimation called multi‐task multi‐scale attention is proposed. First, the authors embed the alternative strategy structure of dilated convolution into ResNet34 to construct a multi‐scale attention module (MSA) to improve the network's receptive field, which extracts local age‐sensitive information while obtaining multi‐scale features. The MSA can have a larger receptive field to extract both large‐scale and local detailed feature information. Second, multi‐task learning network structures are built to predict gender and race, which can share rigid network parameters to improve age estimation and improve the accuracy of age estimation by other age‐related parameters. Finally, the Kullback‐Leibler divergence loss is adopted between a Dirac delta label and a Gaussian prediction to guide the training. The numerical tests on the MORPH Album II and Adience datasets prove the superiority of the proposed method over other state‐of‐the‐art ones.

show abstract

“…Human faces have various related attributes, such as gender, race, and expression, which provide different useful information for age estimation [20]. Zhang et al.…”

Section: Related Workmentioning

confidence: 99%

“…This method effectively exploits label ambiguity in both feature learning and classifier learning and helps prevent network overfitting for small datasets. Subsequently, Gao et al [16] [20]. Zhang et al [21] used multilevel residual convolutional neural networks for age estimation and gender classification.…”

Section: Related Workmentioning

confidence: 99%

Multi‐task multi‐scale attention learning‐based facial age estimation

Shi

Zhao

Zhang

et al. 2023

IET Signal Processing

View full text Add to dashboard Cite

show abstract

“…The features used in image dependant gender recognition are Raw pixels, Haar-based features, Independent Component Analysis (IDA), Principal Component Analysis (PCA), Local Binary Pattern (LBP), Gabor, Discrete Cosine Transform (DCT), Scale Invariant Feature Transform (SIFT), Histogram Oriented Gradients (HOG), Weber's Law Descriptor (WLD), etc., The classifiers such as Decision tree, Support Vector Machine (SVM), ensembles of Radial Basis Functions (RBFs), Adaboost, Linear Discriminant Analysis (LDA), Artificial Neural Network (ANN), Gaussian Mixture Model (GMM) and Random Forest are frequently used in this gender recognition system [4].…”

Section: Introductionmentioning

confidence: 99%

Voice-Based Gender Recognition Model Using FRT and Light GBM

2023

Teh. vjesn.

View full text Add to dashboard Cite

Voice-based gender recognition is vital in many computer-aided voice analysis applications like Human-Computer Interaction, fraudulent call identification, etc. A powerful feature is needed for training the machine learning model to discriminate a gender as male or female from a voice signal. This work proposes the use of a gradient boosting model in conjunction with a novel Cumulative Point Index (CPI) feature computed by Forward Rajan Transform (FRT) for gender recognition from voice signals. Firstly, voice signals are preprocessed to remove the nonsignificant silence period and are further framed and windowed to make them stationary. Then CPI is computed using the first coefficients of FRT and concatenated to form a feature set, and it is used to train the Light Gradient Boosting Machine (LightGBM) to recognize the gender. This approach provides better accuracy and faster training compared with the state of the art techniques. Experimental results show the primacy of the FRTCPI over other standard features used in the literature. It is also shown that the proposed features, in combination with LightGBM, provide better accuracy of 95.26% with a less computational time of 2.25 s over the challenging large datasets like Speech Accent Archive,

show abstract

“…The automatic prediction of age and gender from facial images has been a topic of considerable interest among computer vision researchers, due to its significance in human interactions [1][2][3]. This burgeoning interest is primarily driven by increasing commercial demands for gender and age classification, utilising digital images and videos, thereby spurring active research in the field.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Prediction of Age and Gender from Facial Images

Veesam,

Ravichandran,

Gatram

2023

ISI

View full text Add to dashboard Cite

The automated prediction of age and gender using facial images is gaining traction in various real-world applications, including social media platforms, surveillance systems, and medical fields. This study primarily focuses on automatic gender classification, a critical research domain with substantial potential in systems pertaining to computer vision, biometric authentication, credit card verification, visual surveillance, demographic data gathering, and security. Despite the apparent ease with which humans discern gender by facial observation, replicating this process in computers is challenging due to diverse variables such as illumination, facial expressions, head pose, age, image scale, camera quality, and facial part occlusion. Thus, an effective computer-based system necessitates meaningful data or discriminative features for accurate identification. Over the years, automated facial recognition, along with gender and age estimation using Artificial Intelligence (AI), has been the subject of extensive research. This paper presents a comprehensive summary of the technical aspects of the Deep Convolutional Neural Network (DCNN) architecture, emphasizing key concepts and potential algorithms for predictive applications. The primary aim of this research is to devise and analyze an expression-invariant gender classification algorithm. This algorithm is founded on the fusion of image intensity variation, shape, and texture features, extracted from various scales of facial images using a block processing technique. Looking ahead, our proposed system could potentially be extended for medical analyses, offering personalized medication and nutritional recommendations based on individual gender and age factors. Such an expansion could herald a new era in personalized healthcare, underscoring the importance of our research.

show abstract

Review: Single attribute and multi attribute facial gender and age estimation

Cited by 16 publications

References 94 publications

Multi‐task multi‐scale attention learning‐based facial age estimation

Multi‐task multi‐scale attention learning‐based facial age estimation

Voice-Based Gender Recognition Model Using FRT and Light GBM

Deep Learning-Based Prediction of Age and Gender from Facial Images

Contact Info

Product

Resources

About