# Age Range Estimation using MTCNN and VGG-Face Model

arXiv: https://arxiv.org/abs/2104.08585 · HTML: https://mlsanity.com/paper/2104.08585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 17 Apr 2021.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Data Augmentation using Random Image Cropping and Patching for Deep CNNs](https://mlsanity.com/paper/1811.09030/) (2018)
- [Emotion Detection and Analysis on Social Media](https://mlsanity.com/paper/1901.08458/) (2019)
- [Deep Convolutional Neural Network for Age Estimation based on VGG-Face Model](https://mlsanity.com/paper/1709.01664/) (2017)
- [Ordinal Distribution Regression for Gait-based Age Estimation](https://mlsanity.com/paper/1905.11005/) (2019)

## Abstract (arXiv)

The Convolutional Neural Network has amazed us with its usage on several applications. Age range estimation using CNN is emerging due to its application in myriad of areas which makes it a state-of-the-art area for research and improve the estimation accuracy. A deep CNN model is used for identification of people's age range in our proposed work. At first, we extracted only face images from image dataset using MTCNN to remove unnecessary features other than face from the image. Secondly, we used random crop technique for data augmentation to improve the model performance. We have used the concept of transfer learning in our research. A pretrained face recognition model i.e VGG-Face is used to build our model for identification of age range whose performance is evaluated on Adience Benchmark for confirming the efficacy of our work. The performance in test set outperformed existing state-of-the-art by substantial margins.