Stacked hourglass (HG) networks have been successfully applied to face alignment. However, due to the complex geometry of the facial appearance, the HG model still lacks the robustness of aligning faces in large poses. In this paper, a two-step method is proposed for robust face alignment. First, by using a convolutional neural network (CNN) to directly output the transformation parameters, the conventional procedure of normalizing the face region by performing Procrustes analysis based on the detected landmarks and the mean shape is simplified. In this way, faces with different poses can be converted to a canonical state, which is more advantageous for subsequent face alignment. Second, motivated by recent deformable convolutional networks, we propose a modulated deformable residual block and replace the plain counterparts in the HG model, resulting in deformable hourglass networks (DHNs). The DHN yields large performance improvements over original HG model while having the almost same amount of parameters and bringing minor additional computation costs. Depending on the synergistic effect of two innovations, the proposed method achieves better performance in comparison to the state-of-the-art methods on challenging benchmark datasets.
The finger vein feature extraction algorithm based on global or local features is sensitive to rotation, translation and scaling. Convolutional neural networks have higher robustness, but fewer finger vein samples are prone to over-fitting. Therefore, this paper designs a network architecture FingerveinNet for finger vein recognition. Firstly, based the Inception-resnet module, the design of the finger vein network architecture is used to extract the multi-scale finger vein features while slowing down the gradient disappearance problem without increasing the parameters. Secondly, the center-loss is used as the loss function to optimize the network model and improve. The discriminability of feature vectors for better detail discrimination. Experiments on three international finger vein databases FV-TJ, FV-USM and PolyU show that the proposed method is robust to rotation and translation, and the effectiveness of the proposed method is verified.
Difference summation is utilized to calculate the differential excitation of Weber Local Descriptor (WLD), however, this method is sensitive to noise and may offset positive and negative difference; at the same time, the orientation operator of WLD solely calculates the ratio of the gray difference between the vertical and horizontal orientations, that cannot portray the orientation features of the finger vein effectively. According to the features of finger vein images, this paper based on the differential excitation and orientation operator of Weber descriptors, several improvements are as below: 1)firstly, find the edge area in the image, and optimize the gradient magnitude according to the position of the pixel to increase the discrimination, 2)and then differential excitation is represented by the ratio of the optimized gradient magnitude to the current pixel; 3)double Gabor orientations are leveraged to replace the original gradient orientation to reduce the influence of translation and rotation on recognition; 4)finally, in order to better measure the similarity among features, a cross-matching algorithm is used to improve the recognition rate. In this work, the proposed local descriptor and the cross-matching algorithm are combined for finger vein image recognition, the recognition rates reached 100% and 99. 458% on the two finger vein databases at home and abroad, respectively.