Various types of knowledge and features have been explored for level set based segmentation. On the ground, the prior knowledge and carefully-designed features perform well to identify the foreground-background contrast, which improves the performance of the segmentation method for complicated and distorted data. However, this is not the case for underwater environments, since the features available on the ground are not suitable for challenging underwater environments. Thus, underwater image segmentation currently lags behind ground-based segmentation. In this paper, novel cues and a suitable model formulation for object segmentation from underwater images are proposed. We consider the special haze effect over underwater images and extract an informative feature (transmission feature) from haze condensation. The saliency feature is also used for underwater object segmentation. Consequently, in our method, the object-background difference can be presented by these features on two levels, i.e. the edge-level transmission and region-level saliency features. These two types of features are integrated in a unified level set formulation to propose a solution that handles the challenging issues in underwater object segmentation. Experimental comparisons of our method with other methods comprehensively demonstrate the satisfactory performance of our method.

In recent years, thanks to the inherent powerful feature representation and learning abilities of the convolutional neural network (CNN), deep CNN-steered single image super-resolution approaches have achieved remarkable performance improvements. However, these methods are often accompanied by large consumption of computing and memory resources, which is difficult to be adopted in real-world application scenes. To handle this issue, we design an efficient Feature De-redundancy and Self-calibration Super-resolution network (FDSCSR). In particular, a Feature De-redundancy and Self-calibration Block (FDSCB) is proposed to reduce the repetitive feature information extracted by the model and further enhance the efficiency of the model. Then, based on FDSCB, a Local Feature Fusion Module is presented to elaborately utilize and fuse the feature information extracted by each FDSCB. Abundant experiments on benchmarks have demonstrated that our FDSCSR achieves superior performance with relatively less computational consumption and storage resource than other state-of-the-art approaches. The code is available at https://github.com/IVIPLab/FDSCSR .

Analysis-synthesis dictionary pair learning, which can provide a comprehensive view of data representation, has been applied in various computer vision tasks. Although good performance has been reported in image denoising, discriminative dictionary pair learning for image classification remains unsolved. In this paper, we propose a novel model of graph-regularized discriminative analysis-synthesis dictionary pair learning (GDASDL), in which a graph-regularized term and a discriminative term are incorporated into dictionary pair learning. By taking advantage of graph constraints, the proposed GDASDL can preserve the local geometry structure of the data. Global information is introduced by associating label information with dictionary atoms. An iteration algorithm is presented in this paper to efficiently solve the proposed GDASDL. We extensively conduct experiments on three public image datasets and one face dataset in comparison with the existing dictionary learning approaches, and the experimental results show that the proposed model achieves superior performance using a simple linear classifier.