Video super-resolution can generate corresponding to high-resolution video frames from a plurality of low-resolution video frames which have rich details and temporally consistency. Most current methods use two-level structure to reconstruct video frames by combining optical flow network and super-resolution network, but this process does not deeply mine the effective information contained in video frames. Therefore, we propose a video super-resolution method that combines non-local features and multi-scale features to extract more in-depth effective information contained in video frames. Our method obtains long-distance effective information by calculating the similarity between any two pixels in the video frame through the non-local module, extracts the local information covered by different scale convolution cores through the multi-scale feature fusion module, and fully fuses feature information using different connection modes of convolution cores. Experiments on different data sets show that the proposed method is superior to the existing methods in quality and quantity.

Single-image super-resolution technology has made great progress with the development of the convolutional neural network, but most of the current super-resolution methods do not attempt high-magnification image super-resolution reconstruction; only reconstruction with ×2, ×3, ×4 magnification is carried out for low-magnification down-sampled images without serious degradation. Based on this, this paper proposed a single-image high-magnification super-resolution method, which extends the scale factor of image super-resolution to high magnification. By introducing the idea of multi-task learning, the process of the high-magnification image super-resolution process is decomposed into different super-resolution tasks. Different tasks are trained with different data, and network models for different tasks can be obtained. Through the cascade reconstruction of different task network models, a low-resolution image accumulates reconstruction advantages layer by layer, and we obtain the final high-magnification super-resolution reconstruction results. The proposed method shows better performance in quantitative and qualitative comparison on the benchmark dataset than other super-resolution methods.

Video super-resolution reconstruction is the process of reconstructing low-resolution video frames into high-resolution video frames. Most of the current methods use motion estimation and motion compensation to extract temporal series information, but the inaccuracy of motion estimation will lead to the degradation of the quality of video super-resolution results. Additionally, when using convolution network to extract feature information, the number of feature information is limited by the number of feature channels, resulting in poor reconstruction results. In this paper, we propose a recurrent structure of regional focus network for video super-resolution, which can avoid the influence of inaccurate motion compensation on super-resolution results. Meanwhile, regional focus blocks in the network can focus on different areas of video frames, extract different features from shallow to deep layers, and skip-connect to the last layer of the network through feature aggregation to improve the richness of features participating in the reconstruction. The experimental results show that our method has higher computational efficiency and better video super-resolution results than other temporal modeling methods.

Tongue diagnosis is a kind of Traditional Chinese Medicine (TCM) diagnosis, which is one of the key elements of “Inspection Diagnosis of TCM”. According to TCM, the tongue is closely related to the internal organs, and when the body suffers from various diseases, it will affect the endocrine function, blood composition, nerve conduction, and digestive function. Therefore, the tongue diagnosis can effectively identify whether a patient is suffering from a disease or not, and provide a medical basis for TCM diagnosis. In this paper, we propose a fusion model based on the YOLOX model and attention mechanism, which can effectively identify three pathological features of the tongue image of kidney disease: Teeth-printed tongue, Wrinkled tongue, and Greasy-fur tongue. The experimental results showed that the overall recognition of the 3 features by this fusion model was significantly improved. The overall mAP value was 91.95%, including 0.85 for the Teeth-printed tongue, 0.96 for the Wrinkled tongue, and 0.95 for the Greasy-fur tongue. Therefore, the fusion model based on the YOLOX model and attention mechanism proposed in this paper can assist physicians in quickly identifying whether a patient has kidney disease by the three types of kidney disease tongue features, which have a certain significance for the prevention and treatment of kidney disease.