融合深度字典学习和特征重建的遮挡人脸检测研究

AN OCCLUSION FACE DETECTION METHOD COMBINING DEPTH DICTIONARY LEARNING AND FEATURE RECONSTRUCTION

针对复杂场景中遮挡人脸检测精度低的问题,提出一种融合深度字典学习和特征重建的遮挡人脸检测方法。利用一个浅层CNN(Convolutional Neural Networks)生成人脸候选区域并用预训练好的VGG16网络对其进行特征描述。采用稀疏编码建立一个由典型性的人脸和非人脸构成的深度检索字典。采用局部保留投影的方法,利用检索字典将人脸候选区域的特征描述符重建为一个基于相似性的特征向量。将重建后的特征向量送入到深层神经网络以同时进行人脸/非人脸分类和人脸边界框位置回归。在MAFA遮挡人脸数据集上的实验结果表明,该方法的检测精度比当前主流人脸检测方法提高了约12.3百分点。

Aimed at the low accuracy of occluded face detection in complex scenes,an occlusion face detection method combining depth dictionary learning and feature reconstruction is proposed.A shallow CNN was used to generate face candidate regions,and the pre-trained VGG16 network was used to characterize them.A sparse coding method was used to establish a deep retrieval dictionary composed of typical faces and non-faces.Using the locality preserving projections method,the feature descriptor of the face candidate region was reconstructed into a similarity-based feature vector by using the retrieval dictionary.The reconstructed feature vector was sent to the deep neural network to perform face/non-face classification and face bounding box location regression simultaneously.The experimental results on the MAFA occlusion face dataset show that the detection accuracy of this method is about 12.3 percentage points higher than the current mainstream face detection method.