A Family of Generalized Cardinal Polishing Splines.

Spline functions have received widespread attention in the fields of image sampling and reconstruction. To enhance the performance of splines in reconstruction and reduce the computational burden of solving large linear equations, we propose a family of generalized cardinal polishing splines (GCP-splines) and provide a system of linear equations to obtain the expressions of GCP-splines. First, we propose a cardinal polishing spline basis function with high-precision. Then, we propose a class of GCP-splines and give a general theory of GCP-splines. To calculate the expressions of GCP-splines, we adopt a system of linear equations to obtain the time shifts operator and the convolutional coefficients based on the search spacing and number of terms. Finally, we propose continuous and discrete interpolation models based on GCP-splines, and demonstrate several valuable properties, such as order of approximation and the Riesz basis. To evaluate the performance of GCP-splines, we conduct several experiments on test images from different modalities. The experimental results demonstrate that the GCP-splines for image interpolation and image denoising have better performance and outperform other methods.

Cross Domain Lifelong Learning Based on Task Similarity.

Humans gradually learn a sequence of cross-domain tasks and seldom experience catastrophic forgetting. In contrast, deep neural networks achieve good performance only in specific tasks within a single domain. To equip the network with lifelong learning capabilities, we propose a Cross-Domain Lifelong Learning (CDLL) framework that fully explores task similarities. Specifically, we employ a Dual Siamese Network (DSN) to learn the essential similarity features of tasks across different domains. To further understand similarity information across domains, we introduce a Domain-Invariant Feature Enhancement Module (DFEM) to better extract domain-invariant features. Moreover, we propose a Spatial Attention Network (SAN) that assigns different weights to various tasks based on the learned similarity features. Ultimately, to maximize the use of model parameters for learning new tasks, we propose a Structural Sparsity Loss (SSL) that can make the SAN as sparse as possible while ensuring accuracy. Experimental results show that our method effectively reduces catastrophic forgetting compared with state-of-the-art methods when continuously learning multiple tasks across different domains. It is worth noting that the proposed method scarcely forgets old knowledge while consistently enhancing the performance of learned tasks, more closely aligning with human learning.

Typical curve with G1 constraints for curve completion.

This paper presents a novel algorithm for planar G1 interpolation using typical curves with monotonic curvature. The G1 interpolation problem is converted into a system of nonlinear equations and sufficient conditions are provided to check whether there is a solution. The proposed algorithm was applied to a curve completion task. The main advantages of the proposed method are its simple construction, compatibility with NURBS, and monotonic curvature.

Reversible Data Hiding Based on Dual Pairwise Prediction-Error Expansion.

Reversible data hiding generally exploits the redundancy of the cover medium and prediction-error expansion (PEE) has become the most effective mechanism. However, although the pairwise PEE technique has been proposed to jointly modify the prediction-errors to achieve less degradation, there is still room for improvement. In this paper, a dual pairwise PEE strategy is proposed to fully exploit the potential of pairwise PEE. The key observation behind dual pairwise PEE lies in that most capacity is provided by individually expanding only one pairing error. For such separable error-pairs, we propose to recalculate and collect the rest pairing error to form an error sequence after shifting any one pairing error. Next, by considering every two neighboring errors of the sequence together, a new set of error-pairs for double pairwise PEE can be obtained. Compared with original pairwise PEE, dual pairwise PEE significantly better exploits the correlation of errors such that it leads to better capacity-distortion performance. Experimental results also demonstrate that the proposed scheme outperforms several state-of-the-art schemes.

Severity Assessment of COVID-19 Based on Feature Extraction and V-Descriptors.

Digital image feature recognition is significant to industrial information applications, such as bioengineering, medical diagnosis, and machinery industry. In order to supply an effective and reasonable technology of the severity assessment mission of coronavirus disease (COVID-19), in this article, we propose a new method that identifies rich features of lung infections from a chest computed tomography (CT) image, and then assesses the severity of COVID-19 based on the extracted features. First, in a chest CT image, the lung contours are corrected for the segmentation of bilateral lungs. Then, the lung contours and areas are obtained from the lung regions. Next, the coarseness, contrast, roughness, and entropy texture features are extracted to confirm the COVID-19 infected regions, and then the lesion contours are extracted from the infected regions. Finally, the texture features and V-descriptors are fused as an assessment descriptor for the COVID-19 severity estimation. In the experiments, we show the feature extraction and lung lesion segmentation results based on some typical COVID-19 infected CT images. In the lesion contour reconstruction experiments, the performance of V-descriptors is compared with some different methods, and various feature scores indicate that the proposed assessment descriptor reflects the infected ratio and the density feature of the lesions well, which can estimate the severity of COVID-19 infection more accurately.