Skip to content

About gender classification works

In \cite{ciobotaru2023comparing}, the authors trained simple CNNs to estimate gender and age in images of the UTK-Face dataset. They compared backpropagation with genetic algorithms and obtained competitive results with both of them. Also for age and gender classification, Yaman et al. \cite{yaman2022multimodal} presented a multimodal CNN framework using VGG-16 and ResNet-50 models based on ear and profile face, indicating that these features contain useful biometric traits. In \cite{haseena2022prediction}, a nutrition system was powered by an age and gender recognition module based on CNNs and support vector machines to tailor its food suggestions.

Datasets

UTKFace dataset is a large-scale face dataset with long age span (range from 0 to 116 years old). The dataset consists of over 20,000 face images with annotations of age, gender, and ethnicity. The images cover large variation in pose, facial expression, illumination, occlusion, resolution, etc.

References

  1. Comparing Deep Learning and Genetic Algorithms Techniques for Age and Gender Classification
  2. Multimodal soft biometrics: combining ear and face biometrics for age and gender classification
  3. Prediction of the Age and Gender Based on Human Face Images Based on Deep Learning Algorithm