Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Proposed system for real-time security surveillance.

More »

Fig 1 Expand

Fig 2.

Using a simple image as the input.

More »

Fig 2 Expand

Fig 3.

Extracted face from human image.

More »

Fig 3 Expand

Fig 4.

Process of face detection.

More »

Fig 4 Expand

Fig 5.

Architecture of RetinaFace.

More »

Fig 5 Expand

Fig 6.

RetinaFace multi-task loss function.

More »

Fig 6 Expand

Fig 7.

Triple loss function.

More »

Fig 7 Expand

Fig 8.

Triple loss and selection.

More »

Fig 8 Expand

Fig 9.

Sample image dataset for training.

More »

Fig 9 Expand

Fig 10.

Single face detection with various poses.

More »

Fig 10 Expand

Table 1.

Performance comparison between face detection techniques.

More »

Table 1 Expand

Fig 11.

Single face detection on different occlusion rate.

More »

Fig 11 Expand

Table 2.

Performance comparison between different occlusion rates.

More »

Table 2 Expand

Fig 12.

Accuracy of facial recognition techniques on different λ value.

More »

Fig 12 Expand

Fig 13.

Single face recognition result with various poses.

More »

Fig 13 Expand

Fig 14.

Single face recognition on different occlusion rate.

More »

Fig 14 Expand

Fig 15.

Recognize multiple human faces.

More »

Fig 15 Expand

Table 3.

Performance comparison between face recognition techniques.

More »

Table 3 Expand

Table 4.

Performance comparison between baseline models of deep learning and the proposed method.

More »

Table 4 Expand