Face Recognition Using Sf_3CNN With Higher Feature Discrimination
share
With the advent of 2-dimensional Convolution Neural Networks (2D CNNs), the face recognition accuracy has reached above 99 still a challenge in real world conditions. A video, instead of an image, as an input can be more useful to solve the challenges of face recognition in real world conditions. This is because a video provides more features than an image. However, 2D CNNs cannot take advantage of the temporal features present in the video. We therefore, propose a framework called Sf_3CNN for face recognition in videos. The Sf_3CNN framework uses 3-dimensional Residual Network (3D Resnet) and A-Softmax loss for face recognition in videos. The use of 3D ResNet helps to capture both spatial and temporal features into one compact feature map. However, the 3D CNN features must be highly discriminative for efficient face recognition. The use of A-Softmax loss helps to extract highly discriminative features from the video for face recognition. Sf_3CNN framework gives an increased accuracy of 99.10 comparison to the previous 97
READ FULL TEXT