论文标题
可靠面部识别的中值像素差卷积网络
Median Pixel Difference Convolutional Network for Robust Face Recognition
论文作者
论文摘要
面部识别是计算机视觉中最活跃的任务之一，在现实世界中已被广泛使用。凭借在卷积神经网络（CNN）方面取得的巨大进步，许多面部识别算法在各种面部数据集上取得了很高的精度。但是，基于CNN的现有面部识别算法容易受到噪声的影响。噪声损坏的图像模式可能导致错误的激活，在嘈杂的情况下大大降低了面部识别精度。为了使CNN对不同级别的噪声配备内置的鲁棒性，我们提出了一个中位像素差卷积网络（MEDINET），通过用拟议的新型中间像素差卷积层（Mediconv）层代替一些传统的卷积层。拟议的Medinet将传统的多尺度中位过滤的想法与深CNN结合在一起。在四个面部数据集（LFW，CA-LFW，CP-LFW和YTF）上测试了MedInet，并在模糊内核，噪声强度，尺度和JPEG质量因素上进行了多功能设置。广泛的实验表明，我们的Medinet可以在功能图中有效去除嘈杂的像素并抑制噪声的负面影响，从而在这些实际噪声下与在清洁条件下的标准CNN相比，在这些实际噪声下实现了有限的精度损失。
Face recognition is one of the most active tasks in computer vision and has been widely used in the real world. With great advances made in convolutional neural networks (CNN), lots of face recognition algorithms have achieved high accuracy on various face datasets. However, existing face recognition algorithms based on CNNs are vulnerable to noise. Noise corrupted image patterns could lead to false activations, significantly decreasing face recognition accuracy in noisy situations. To equip CNNs with built-in robustness to noise of different levels, we proposed a Median Pixel Difference Convolutional Network (MeDiNet) by replacing some traditional convolutional layers with the proposed novel Median Pixel Difference Convolutional Layer (MeDiConv) layer. The proposed MeDiNet integrates the idea of traditional multiscale median filtering with deep CNNs. The MeDiNet is tested on the four face datasets (LFW, CA-LFW, CP-LFW, and YTF) with versatile settings on blur kernels, noise intensities, scales, and JPEG quality factors. Extensive experiments show that our MeDiNet can effectively remove noisy pixels in the feature map and suppress the negative impact of noise, leading to achieving limited accuracy loss under these practical noises compared with the standard CNN under clean conditions.
