Liu Jie, Xu Wenqiang, Li Xiumin, Zheng Xiao
College of Automation, Chongqing University, Chongqing, China.
School of Computer Science and Technology, Anhui University of Technology, Ma'anshan, China.
Front Neurosci. 2021 Oct 5;15:718541. doi: 10.3389/fnins.2021.718541. eCollection 2021.
Traditional facial recognition methods depend on a large number of training samples due to the massive turning of synaptic weights for low-level feature extractions. In prior work, a brain-inspired model of visual recognition memory suggested that grid cells encode translation saccadic eye movement vectors between salient stimulus features. With a small training set for each recognition type, the relative positions among the selected features for each image were represented using grid and feature label cells in Hebbian learning. However, this model is suitable only for the recognition of familiar faces, objects, and scenes. The model's performance for a given face with unfamiliar facial expressions was unsatisfactory. In this study, an improved computational model via grid cells for facial recognition was proposed. Here, the initial hypothesis about stimulus identity was obtained using the histograms of oriented gradients (HOG) algorithm. The HOG descriptors effectively captured the sample edge or gradient structure features. Thus, most test samples were successfully recognized within three saccades. Moreover, the probability of a false hypothesis and the average fixations for successful recognition were reduced. Compared with other neural network models, such as convolutional neural networks and deep belief networks, the proposed method shows the best performance with only one training sample for each face. Moreover, it is robust against image occlusion and size variance or scaling. Our results may give insight for efficient recognition with small training samples based on neural networks.
传统的面部识别方法由于在低级特征提取中突触权重的大量调整，依赖于大量的训练样本。在先前的工作中，一种受大脑启发的视觉识别记忆模型表明，网格细胞对显著刺激特征之间的平移扫视眼动向量进行编码。对于每种识别类型使用少量训练集，在Hebbian学习中使用网格和特征标签细胞来表示每个图像所选特征之间的相对位置。然而，该模型仅适用于识别熟悉的面孔、物体和场景。对于具有不熟悉面部表情的给定面孔，该模型的性能并不理想。在本研究中，提出了一种通过网格细胞改进的面部识别计算模型。在此，使用定向梯度直方图（HOG）算法获得关于刺激身份的初始假设。HOG描述符有效地捕获了样本边缘或梯度结构特征。因此，大多数测试样本在三次扫视内被成功识别。此外，错误假设的概率以及成功识别的平均注视次数都有所减少。与其他神经网络模型（如卷积神经网络和深度信念网络）相比，所提出的方法在每张面孔仅一个训练样本的情况下表现出最佳性能。此外，它对图像遮挡和尺寸变化或缩放具有鲁棒性。我们的结果可能为基于神经网络的小训练样本高效识别提供见解。
