The human visual system (HVS), affected by viewing distance when perceiving the stereo image information, is of great significance to study of stereoscopic image quality assessment. Many methods of stereoscopic image quality assessment do not have comprehensive consideration for human visual perception characteristics. In accordance with this, we propose a Rich Structural Index (RSI) for Stereoscopic Image objective Quality Assessment (SIQA) method based on multi-scale perception characteristics. To begin with, we put the stereo pair into the image pyramid based on Contrast Sensitivity Function (CSF) to obtain sensitive images of different resolution. Then, we obtain local Luminance and Structural Index (LSI) in a locally adaptive manner on gradient maps which consider the luminance masking and contrast masking. At the same time we use Singular Value Decomposition (SVD) to obtain the Sharpness and Intrinsic Structural Index (SISI) to effectively capture the changes introduced in the image (due to distortion). Meanwhile, considering the disparity edge structures, we use gradient cross-mapping algorithm to obtain Depth Texture Structural Index (DTSI). After that, we apply the standard deviation method for the above results to obtain contrast index of reference and distortion components. Finally, for the loss caused by the randomness of the parameters, we use Support Vector Machine Regression based on Genetic Algorithm (GA-SVR) training to obtain the final quality score. We conducted a comprehensive evaluation with state-of-the-art methods on four open databases. The experimental results show that the proposed method has stable performance and strong competitive advantage.

Light field images can record multiple information about the light rays in a scene and provide multiple views from a single image, offering a new data source for 3D reconstruction. However, ensuring the quality of light field images themselves is challenging, and distorted image inputs may lead to poor reconstruction results. Accurate light field image quality assessment can pre-judge the quality of light field images used as input for 3D reconstruction, providing a reference for the reconstruction results before the reconstruction work, significantly improving the efficiency of 3D reconstruction based on light field images. In this paper, we propose an Adaptive Vision Transformer-based light-field image-quality assessment model (AViT-LFIQA). The model adopts a multi-view sub-aperture image sequence input method, greatly reducing the number of input images while retaining as much information as possible from the original light field image, alleviating the training pressure on the neural network. Furthermore, we design an adaptive learnable attention layer based on ViT, which addresses the lack of inductive bias in ViT by using adaptive diagonal masking and a learnable temperature coefficient strategy, making the model more suitable for training on small datasets of light field images. Experimental results demonstrate that the proposed model is effective for various types of distortions and shows superior performance in light-field image-quality assessment.

Human emotion label prediction is crucial to Artificial Intelligent in the Internet of Things (IoT). Facial expression recognition is the main technique to predict human emotion labels. Existing facial expression recognition methods do not consider the compound emotion and the fuzziness of emotion labels. Fuzzy learning is a mathematical tool for dealing with fuzziness and uncertainty information. The advantage of using fuzzy learning for human emotion recognition is that multiple fuzzy sentiment labels can be processed simultaneously. This paper proposes a fuzzy learning-based expression recognition method for human emotion label prediction. First, a fuzzy label distribution system is constructed using fuzzy sets for representing facial expressions. Then, two fuzzy label distribution prediction methods based on fuzzy rough sets are proposed to solve the compound emotion prediction. The probability that a sample is likely and definitely belongs to an emotion is obtained by calculating the upper and lower approximations. Experiments show the proposed algorithm not only performs well on human emotion label prediction but can also be used for other label distribution prediction tasks. The proposed method is more accurate and more general than other methods. The improvement of the method on the effect of emotion recognition extends the application scope of artificial intelligence in IoT.

Global photographic aesthetic image generation aims to ensure that images generated by generative adversarial networks (GANs) contain semantic information and have global aesthetic feelings. Existing image aesthetic generation algorithms are still in the exploratory stage, and images screened or generated by a computer have not yet achieved relatively ideal aesthetic quality. In this study, we use an existing generative model, StyleGAN, to build the height of image content and put forward a new method based on the GAN disentangled representation of a global aesthetic image generation algorithm by mining GANs’ latent space, potential global aesthetic feeling, and aesthetic editing of the original image to realize the aesthetic feeling and content of high-quality global aesthetic image generation. In contrast with the traditional aesthetic image generation methods, our method does not need to retrain GANs. Using the existing StyleGAN generation model, by learning a prediction model to score the generated image and the score as a label to learn a support vector machine decision surface, we use the learned decision to edit the original image to obtain an image with a global aesthetic feeling. This method solves the problems of poor content construction effect and poor global beauty of the aesthetic images generated by the existing methods. Experimental results show that the proposed method greatly increases the aesthetic score of the generated images and makes the generated images more in line with people’s aesthetic.

Global photographic aesthetic image generation aims to ensure that images generated by generative adversarial networks (GANs) contain semantic information and have global aesthetic feelings. Existing image aesthetic generation algorithms are still in the exploratory stage, and images screened or generated by computer have not yet achieved relatively ideal aesthetic quality. In this study, we use existing generative model, StyleGAN, to build the height of image content and put forward a new method based on the GAN disentangled representation of global aesthetic image generation algorithm by mining GANs latent space potential global aesthetic feeling and aesthetic editing of the original image to realize the aesthetic feeling and content of high-quality global aesthetic image generation. In contrast with the traditional aesthetic image generation methods, our method does not need to retrain GANs. Using the existing StyleGAN generation model, by learning a prediction model to score the generated image and the score as a label to learn a support vector machine decision surface, we use the learned decision to edit the original image to get an image with a global aesthetic feeling. This method solves the problems of poor content construction effect and poor global beauty of the aesthetic images generated by the existing methods. Experimental results show that the proposed method greatly increases theprobability of generating ”good-looking” images and aesthetic score of generated images.