To ensure the security and privacy of images, this paper proposes an Improved 1D Sine–Logistic (I1DSL) chaotic system and its application in multiple Regions of Interest (ROI) image encryption. As the security foundation, the I1DSL chaotic system is employed to generate highly secure chaotic key streams. Performance analysis demonstrates that it exhibits superior dynamic behavior and a broader parameter space. During encryption, YOLOv10 is used to extract ROIs and generate keys accurately. For each ROI, a selective scrambling is applied to achieve a uniform and unpredictable pixel distribution. In image diffusion, a Multi-directional Dynamic Josephus (MDJ) matrix is introduced to realize synchronous scrambling and diffusion of multiple ROIs. Finally, a global random scrambling process is applied to ROIs of different sizes to further enhance the overall randomness and security of the encryption. Experimental results demonstrate that the proposed multi-ROI image encryption algorithm exhibits excellent performance in both security and efficiency, further validating the security of the I1DSL system.

The effective integration of multi-level contextual information is crucial for deep learning-based salient object detection. However, most existing approaches either adopt the parallel structure or the progressive structure to predict salient objects, which still face challenges in consistently and accurately detecting salient objects of varying scales. In this paper, we propose a novel cross dual branch guidance network to effectively extract the rich semantic features and gradually enhance the saliency map scale-by-scale. Concretely, the parallel branch is guided by the progressive branch to obtain coarse location information of salient objects. In turn, the progressive branch is able to obtain uniform semantics and rich details to enhance saliency map with the guidance of the parallel branch. To obtain the dynamic receptive field, a dynamic sampling module (DSM) is introduced, which can dynamically adjust the sampling positions such that the spatial details of salient objects in complex scenes can be well recognized. In addition, we design a global context module (GCM) to explore the correlation between different parts of salient object or different salient objects, which is favorable for improving the completeness of saliency map. Experiments on five released benchmark datasets demonstrate the effectiveness and superiority of our proposed approach against other state-of-the-art methods.

Recent advances in text-to-image synthesis have captivated audiences worldwide, drawing considerable attention. Although significant progress in generating photo-realistic images through large pre-trained autoregressive and diffusion models, these models face three critical constraints: (1) The requirement for extensive training data and numerous model parameters; (2) Inefficient, multi-step image generation process; and (3) Difficulties in controlling the output visual features, requiring complexly designed prompts to ensure text-image alignment. Addressing these challenges, we introduce the CLIP-GAN model, which innovatively integrates the pretrained CLIP model into both the generator and discriminator of the GAN. Our architecture includes a CLIP-based generator that employs visual concepts derived from CLIP through text prompts in a feature adapter module. We also propose a CLIP-based discriminator, utilizing CLIP's advanced scene understanding capabilities for more precise image quality evaluation. Additionally, our generator applies visual concepts from CLIP via the Text-based Generator Block (TG-Block) and the Polarized Feature Fusion Module (PFFM) enabling better fusion of text and image semantic information. This integration within the generator and discriminator enhances training efficiency, enabling our model to achieve evaluation results not inferior to large pre-trained autoregressive and diffusion models, but with a 94% reduction in learnable parameters. CLIP-GAN aims to achieve the best efficiency-accuracy trade-off in image generation given the limited resource budget. Extensive evaluations validate the superior performance of the model, demonstrating faster image generation speed and the potential for greater stylistic diversity within the GAN model, while still preserving its smooth latent space.

Superpixels are widely used in computer vision applications. Most of the existing superpixel methods use established criteria to indiscriminately process all pixels, resulting in superpixel boundary adherence and regularity being unnecessarily inter-inhibitive. This study builds upon a previous work by proposing a new segmentation strategy that classifies image content into meaningful areas containing object boundaries and meaningless parts that include color-homogeneous and texture-rich regions. Based on this classification, we design two distinct criteria to process the pixels in different environments to achieve highly accurate superpixels in content-meaningful areas and keep the regularity of the superpixels in content-meaningless regions. Additionally, we add a group of weights when adopting the color feature, successfully reducing the undersegmentation error. The superior accuracy and the moderate compactness achieved by the proposed method in comparative experiments with several state-of-the-art methods indicate that the content-adaptive criteria efficiently reduce the compromise between boundary adherence and compactness.

Superpixels are widely used in computer vision applications, as they conserve the running costs of subsequent processing while preserving the original performance. In most of the existing algorithms, the boundary adherence and the compactness of superpixels are necessarily inter-inhibitive because the color/gradient information is balanced against the position constraints, and the set criteria define all pixels indiscriminately. In this paper, we present a two-phase superpixel segmentation method based on the watershed transformation. After designing a new approach for calculating the flooding priority, we propose a new strategy with two distinct criteria for global and local refinement of the boundary pixels. These criteria reduce the compromise between the boundary adherence and compactness. Unlike the indiscriminate standards, our method applies different treatments to pixels in different environments, preserving the color homogeneity in content-rich areas while improving the regularity of the superpixels in content-plain regions. The superior accuracy and computing time of our proposed method are verified in comparison experiments with several state-of-the-art methods.

In this study, we describe a system-level multiple refactoring algorithm, which can identify the move method, move field, and extract class refactoring opportunities automatically according to the principle of “high cohesion and low coupling.” The algorithm works by merging and splitting related classes to obtain the optimal functionality distribution from the system-level. Furthermore, we present a weighted clustering algorithm for regrouping the entities in a system based on merged method-level networks. Using a series of preprocessing steps and preconditions, the “bad smells” introduced by cohesion and coupling problems can be removed from both the non-inheritance and inheritance hierarchies without changing the code behaviors. We rank the refactoring suggestions based on the anticipated benefits that they bring to the system. Based on comparisons with related research and assessing the refactoring results using quality metrics and empirical evaluation, we show that the proposed approach performs well in different systems and is beneficial from the perspective of the original developers. Finally, an open source tool is implemented to support the proposed approach.