Recommending appropriate tags for texts is an effective way to better organize and use the text content. At present, most tag recommendation methods mainly recommend tags by mining the text content. However, most of the data information does not exist independently, for example, the co-occurrence of words between texts in a corpus can form a complex network structure. Previous studies have shown that the network structure information between texts and the text content information can summarize the semantics of the same text from two different perspectives, and the information extracted from two aspects can complement and explain each other. Based on this, a tag recommendation method was proposed to simultaneously model the network structure information of text and the content information of text. Firstly, Graph Convolutional neural Network(GCN) was used to extract the structure information of the network between texts, then Recurrent Neural Network(RNN) was used to extract the text content information, and finally the attention mechanism was used to recommend tags by combining the network structure information between texts and the text content information. Compared with baseline methods, such as tag recommendation method based on GCN and tag recommendation method with Topical attention-based Long Short-Term Memory(TLSTM) neural network, the proposed tag recommendation method with attention mechanism combining network structure information and text content information has better performance. For example, on the Mathematics Stack Exchange dataset, the precision, recall and F1 of the proposed method are improved by 2.3%, 3.8%, and 7.0% respectively compared with the optimal baseline method.

Since the traditional Pulse Coupled Neural Network-based (PCNN) image fusion methods cannot extract the focus region clearly, a multi-focus image fusion technique using Phase Congruency (PC) and Spatial Frequency (SF) combined with PCNN model in Non-Subsampled Contourlet Transform (NSCT) domain was proposed. Firstly, the source images were decomposed into high frequency subband and low frequency subband by NSCT. Secondly, the values of SF and PC were calculated to motivate PCNN neurons to fire to find the focus regions, and then the high and low frequency subbands were fused respectively. Lastly, the fused image was reconstructed through inverse NSCT. Multi-focus image datasets Clock, Pepsi and Lab were utilized as the experimental image sets. In comparison, four classical fusion methods and three newly put forward fusion algorithms were compared with the proposed algorithm. Objective indicators including mutual information, edge intensity, entropy, standard deviation and average gradient were calculated, and the values of the proposed method were greater than or very close to the maximum value of the comparison algorithms; meanwhile, it was clearly found from the difference maps between the experimental result image and the source image that the difference graph of the proposed method contained significantly fewer traces of the clear region of the source image. The experimental results indicate that the proposed method can better extract the clear region of the fused image, and it can better retain details such as edges and textures of the source images, thus, a superior fusion effect is acquired.

Feature extraction is a key step of image retrieval and image registration, but the single feature can not express the information of medical images efficiently. To overcome this shortcoming, a new algorithm for medical image retrieval combining global features with local features was proposed based on the characteristics of medical images. First, after studying the medical image retrieving techniques with single feature, a new retrieval method was proposed by considering global feature and relevance feedback. Then to optimize the Scale-Invariant Feature Transform (SIFT) features, an improved SIFT features extraction and matching algorithm was proposed. Finally, in order to ensure the accuracy of the results and improve the retrieval result, local features were used for stepwise refinement. The experimental results on general Digital Radiography (DR) images prove the effectiveness of the proposed algorithm.

The alternating direction method is used widely to deal with the problem of total variation image restoration. A correction method was proposed to solve the problem of inaccuracy in search direction of the alternating direction method, which may influence the efficiency of the algorithm and the quality of the restored images adversely. Combining Taylor expansion of energy function and properties of differentiable function, this subspace-optimization-based method corrected the current direction effectively by utilizing the previous one, and improved the accuracy of search direction. The numerical experiments expound the efficiency of this algorithm and the quality of the restored images by running time and Peak-Signal-to-Noise Ratio (PSNR), respectively.

TI TMS320DM642 is a powerful multimedia DSP of TI.Methods transferring large quantities of data between DM642 and PC throught PCI data bus in multithread application were introduced,and a fast and stable way was presented in detail.