A chaotic gyro system to investigate the method for higher order sliding mode control design. The system is assumed to have uncertain parameters with known upper and lower bounds. We also design an optimal sliding surface for the sliding mode control. The control law is designed to guarantee the existence of the sliding mode around the nonlinear surface Simulations are carried out to demonstrate the utility of the control method.

Aesthetic image quality assessment (or aesthetic assessment) is the use of computers to automatically evaluate the "beauty" of images by simulating human perceptions and cognition of beauty [1]. Aesthetic image quality assessment is a new direction of intersection between computational aesthetics and computer vision, psychology, virtual reality, etc. Its core is to use computers to simulate human preferences for image content and composition, including the aesthetic stimuli formed under the influence of aesthetic factors such as images, so as to simulate human perception and cognition of beauty, automatically evaluate the "beauty" of images "The main purpose of this paper is to introduce the most recent work on the "aesthetics" of images. The main purpose of this paper is to present the recent developments in the evaluation of the aesthetic quality of images over the years.

As for actual content in the field of computer vision, image inpainting has increasingly become a research hotspot in recent years. Image inpainting is the task of restoring the lost image content according to the known image content. It has a broad application value in image editing, film and television stunt production, virtual reality, and digital cultural heritage protection. To make more researchers explore the theory and development of image restoration based on deep learning, this paper summarizes the research status in this field. Firstly, starting from the traditional image inpainting methods, this paper analyzes their existing problems, focuses on the overview of image inpainting methods based on deep learning, including image inpainting methods based on convolution neural network, generation countermeasure network, and cyclic neural network, introduces the principle and structure of various methods, and summarizes the application scope, advantages and disadvantages of various methods based on deep learning. Finally, the future research direction and focus have been prospected.

The latest deep learning-based approaches have shown  promising results for the challenging task of inpainting missing regions of an image. However, the existing methods often generate contents with blurry textures and distorted structures due to the discontinuity of the local pixels. From a semantic-level perspective, the local pixel dis continuity is mainly because these methods ignore the semantic relevance and feature continuity of hole regions. To handle this problem, we investigate the human behavior in repairing pictures and propose a fifined deep generative model-based approach with a novel coherent semantic attention (CSA) layer, which can not only preserve contextual structure but also make more effective predictions of missing parts by modeling the semantic relevance between the holes features. The task is divided into rough, refifinement as two steps and model each step with a neural network under the U-Net architecture, where the CSA layer is embedded into the encoder of refifinement step. To stabilize the network training process and promote the CSA layer to learn more effective parameters, we propose a consistency loss to enforce the both the CSA layer and the corresponding layer of the CSA in decoder to be close to the VGG feature layer of a ground truth image simultaneously. The experiments on CelebA, Places2, and Paris StreetView datasets have validated the effectiveness of our proposed methods in image inpainting tasks and can obtain images with a higher quality as compared with the existing state-of-the-art approaches.