基于多层特征融合可调监督函数卷积神经网络的人脸性别识别

为了进一步提高性别识别的准确率，提出了一种基于多层特征融合与可调监督函数机制的结合的卷积神经网络（L-MFCNN）模型，并将之用于人脸性别识别。与传统卷积神经网络（CNN）不同，L-MFCNN将多个浅层中间卷积层特征输出与最后卷积层特征输出相结合，融合多层卷积层的特征，不仅利用了深层卷积的整体语义信息，还考虑了浅层卷积的细节局部纹理信息，使得性别识别更加准确。此外L-MFCNN还引入具有可调目标监督函数机制的Large-Margin Softmax Loss作为输出层，利用其调节不同的间隔（margin）的机制来有效引导深层卷积网络学习，使得同种性别间的类内间距更小，不同性别间的类间距更大，获得更好的性别识别效果。在多个人脸数据集上的性别识别实验结果表明，L-MFCNN的识别准确率要高于其他传统的卷积网络模型。L-MFCNN模型也为将来的人脸性别识别研究提供了新的思路与方向。

Face gender recognition based on multi-layer feature fusion convolution neural network with adjustable supervisory function

In order to further improve the accuracy of gender recognition, this paper proposed the convolution neural network model based on multi-layer feature fusion with adjustable supervisory function , L-MFCNN, then it used for face gender recognition. Unlike the traditional convolution neural network, L-MFCNN combined the output of multiple shallow convolution layers with the final convolution layer output. Fusion the characteristics of multi-layer convolutions, not only use the high-level semantic information, but also consider the bottom of the details of the texture information, making the face gender recognition more accurate. While using the Large-Margin Softmax Loss could adjust the margin function, it could explicitly encourages the same gender intra-class compactness and the different gender inter-class separability to get better face gender recognition. The face gender recognition experiment data on multiple face data sets show that the accuracy of L-MFCNN is higher than that of traditional convolution network. Besides, L-MFCNN also provides the new ideas and directions for the future gender recognition of face.