Technical Details
The age and gender classifier is a neural network model in TensorFlow format. It is is based on the fast MobileNet neural network architecture. It runs in real time on CPU of a regular PC while at the same time achieves state-of-art accuracy. One facial image classification takes 35 milliseconds on Intel i5 CPU. For faster inference a NVIDIA GPU is recommended to be used. There are many ways to integrate the age and gender classifier into your software. For example, the model can be opened in OpenCV by DNN module. It is also possible to use TensorFlow library and to run the classifier using C++ or Python. Another option is to use TensorFlow Serving, which is a high-performance serving system for machine learning models, designed for production environments. It exposes RESTful API (in port 8501) and gRPC interface (in port 8500). The model server can be packaged in Docker container and to be hosted on the cloud or On-Premises servers.
Specifications:
224x224 Model Benchmark
| Company | Gender prediction accuracy (%) | Age estimation mean absolute error (in years) |
|---|---|---|
| Planetoid AI | 98.3% | 5.5 |
| Microsoft | 96.9% | 8.5 |
| Skybiometry | 92.9% | 7.2 |
| Sighthound | 91.1% | 8.1 |
| Eyedea | 90.7% | 8.0 |
| VisageCloud | 91.1% | 9.1 |
Business Applications
Intelligent Video Analytics
Public safety and security organizations can include advanced search and car analytics functionalities into their software to find or redact relevant information in video records.
Targeted Advertising
Marketing and retail specialists can use our age and gender estimation to target their ads, content, products, or shelf placement towards a specific audience.
Digital Asset Management
Organizing, storing, and retrieving multimedia content like photos and videos. Building searchable car image databases for video and image archives.
