Abstract To solve the problem that the deep learning‐based image matting algorithm cannot balance accuracy and model size, a lightweight image matting algorithm based on deep learning is proposed. Considering the limitation of memory and computing resources, and aiming at lightweight. We construct a network and gradually improved it. Firstly, apply deep detachable convolution to deep image matting networks to form faster and stronger encoder and decoder networks. The simultaneous use of depth‐separable convolution can also reduce the number of corresponding model parameters and computation. And then attention mechanism is integrated into the model and SE Block was used to assign different weights to feature channels to improve the accuracy of the model. Finally, knowledge distillation scheme is designed in part of the encoder‐decoder structure, the corresponding loss function is proposed, and the method of knowledge distillation is used to improve the feature learning ability of the lightweight neural network. Compared with the original deep image matting model, the number of parameters in the new model is greatly reduced without too much loss of accuracy.

Abstract The development of deep learning provides a new way for solving the colorization problem on the grayscale image. Excellent coding‐based methods appear in the automatic image colorization task, avoiding the unsaturated colour effect problem of previous methods based on the L2 loss function. Traditional neural networks come with high computational costs and a large number of parameters. Considering the limitation of memory and computing resources and aiming at lightweight, a novel grey image automatic colorization network is proposed. The basic idea of coding‐based methods is used, regarding the colorization task as a pixel‐level classification problem, meanwhile redesign and improve the colour encoding and decoding process. This network architecture leverages a lightweight convolution to reduce the computation and combines an efficient attention model to form a residual block as the kernel of the backbone network. Furthermore, an efficient image self‐attention mechanism placed at the end of the network is applied to enhance the ultimate colouring results. The method proposed in this paper can maintain the natural colouring effect and significantly reduce the computational amount and network model parameters.

Brain–computer interface is a new form of interaction between humans and machines. This interaction helps the human brain control or operate external devices directly using electroencephalograph (EEG) signals. In this study, we first adopt a canonical correlation analysis method to find the stimulation frequency by calculating the correlation coefficient between the EEG data and multiple sets of harmonics with different frequencies. Then, we select the maximum correlation coefficient as the stimulus frequency and consequently identify steady-state visual evoked potentials. Afterward, we introduce power spectral density to adjust the stimulus frequency and a voting mechanism to reduce the false activation rate. Finally, we build a virtual household electrical appliance brain–computer control interface, which achieves over 72.84% accuracy for three classification problems.

An improved single image fast deblurring algorithm based on hyper‐Laplacian constraint is proposed. The algorithm is improved in three aspects: image blur kernel estimation sub‐region selection, blur kernel precise estimation, and fast non‐blind deconvolution. First, image amplitude and gradient are used as the basis of blur kernel estimation. On the basis of analysing the edge amplitude and gradient of the image, the image sub‐region for blur kernel estimation is selected. Then the sparsity of the blur kernel is restricted by hyper‐Laplacian, and the fast solving mode of alternately solving different variables is designed. The blur kernel information is accurately estimated. In the fast non‐blind deconvolution restoration phase of the image, the regularised constraint term of the hyper‐Laplacian model is improved and the image gradient distribution is constrained. The blind growth trend of the regional gradient near the strong edge can be suppressed well, and the deblurred image with clear edge structure is generated. Experimental results show that the proposed algorithm can achieve better image deblurring effect and high efficiency.

A novel algorithm for mesh surface fairing based on empirical mode decomposition (EMD) is presented. To expand the EMD method to high-dimensional, spherical surface signal processing based on EMD is implemented. For mesh surface, parameterize the mesh to spherical surface, and build the mapping between original mesh and spherical mesh firstly. Then resample the spherical mesh and decompose the resample spherical signals by EMD method. Finally, remove the high-frequency component of spherical signals and inverse mapping the processed spherical signal back to the original mesh. So the smoothed mesh surface is obtained. Experiments show that the EMD based analysis method for mesh surface fairing can obtain good results, and geometric features of original mesh has been maintained.