Face Detection - 1.1 English

Vitis AI Library User Guide (UG1354)

Document ID
UG1354
Release Date
2020-03-23
Version
1.1 English

This library uses DenseBox neuron network to detect human face. Input is a picture with some faces you would like to detect. Output is a vector of the result structure containing each box’s information.

The following image show the result of face detection.

Figure 1. Face Detection Example

The following table shows the face detection model supported by the AI Library.

Table 1. The face detection model list
No Model Name Framework
1 densebox_320_320 Caffe
2 densebox_640_360