To address overfitting of recognition results in complex Convolutional Neural Network(CNN) on small and medium face databases,this paper proposes a face recognition algorithm based on improved CNN and ensemble learning.Combining the characteristics of planar networks and residual networks,the improved CNN replaces the fully connected layer with the average pooling layer to make the network structure simple and highly portable.Based on this improved CNN,the voting-based ensemble learning strategy is used to implement convex combination for results of all individual learners and obtain the final result,so more accurate face recognition could be realized.Experimental results show that the recognition accuracy of the proposed algorithm reaches 98.89%,99.67% and 100% respectively on Color FERET,AR and ORL face databases with a high convergence speed.

In order to overcome the effects of posture, illumination, expression and other factors on face recognition, this paper proposes an algorithm which is based on local binary pattern (LBP) and convolutional neural network (CNN). LBP is a texture description method which describes the local texture features of an image. It has good robustness of illumination and posture. CNN can effectively extract the spatial features of images and reduce the dimensions of features. This paper combines the advantages of LBP and CNN to improve the accuracy of face recognition. The CNN in this algorithm has four convolution layers, two max-pooling layers, one activation layer, one fully connected layer, and one output layer. In order to optimize the network structure, batch normalization layer is added after the convolution layer. We get the local binary pattern coded images and put the images as the input of the CNN and train the network. Hence, we can use the well-trained CNN for classification and identification. The Experiments on the CMU-PIE face database show that our algorithm can effectively improve the rate of face recognition.

Using a conventional radio frequency( RF) magnetron sputtering system, we have succeeded in fabricating ZnO films with high (1120) preferred orientation on Si substrate by introducing a SiO2 buffer layer and adjusting the sputtering gas pressure. The crystallographic characteristics and the preferred orientation of ZnO films were characterized by X-ray diffraction ( XRD) and atomic force microscopic ( AFM) analysis. The temperature coefficient of delay ( TCD) of the ZnO/SiO2/Si SAW device decreases significantly when a SiO2 buffer layer is introduced. When the thickness of SiO2 buffer layer is 200 nm, ZnO film shows ( 0002 ) and ( 1120 ) preferred orientations simultaneously, and the TCD of ZnO/SiO2/Si SAW device is nearly 2 × 10 -6℃ -1 , indicating that the device main-tains good temperature stability. When the sputtering gas pressure decreases, the ( 1120 ) preferred orientation is enhanced, and the corresponding electromechanical coupling coefficient ( K2 ) of the SAW devices enlarges. The tri-layer structure of ZnO/SiO2/Si with large K2 and high temperature stability is promising for fabricating high performance Love mode SAW biosensors.