RGB-D Gate-guided edge distillation for indoor semantic segmentation

Multimedia Tools and Applications - Fusing the RGB and depth information can significantly improve the performance of semantic segmentation since the depth data represents the geometric...     

Multi-objective genetic algorithms: A way to improve the convergence rate

Multi-objective optimization is generally a time consuming step of the design process. In this paper, a Pareto based multi-objective genetic algorithm is proposed, which enables a faster convergence without degrading the estimated set of solutions. Indeed, the population diversity is correctly conserved during the optimization process; moreover, the solutions belonging to the frontier are equally distributed along the frontier. This improvement is due to an extension function based on a natural phenomenon, which is similar to a cyclical epidemic which happens every N generations (eN-MOGA). The use of this function enables a faster convergence of the algorithm by reducing the necessary number of generations.     

Just-noticeable difference estimation with pixels in images

Perceptual visibility threshold estimation, based upon characteristics of the human visual system (HVS), is widely used in digital image and video processing. We propose in this paper a scheme for estimating JND (just-noticeable difference) with explicit formulation for image pixels, by summing the effects of the visual thresholds in sub-bands. The factors being considered include spatial contrast sensitivity function (CSF), luminance adaptation, and adaptive inter- and intra-band contrast masking. The proposed scheme demonstrates favorable results in noise shaping and perceptual visual distortion gauge for different images, in comparison with the relevant existing JND estimators.     

A novel energy functional minimization model for speckle noise removal

In this paper, a novel energy functional minimization model is proposed for ultrasound images denoising. A controllable regularized term and the variational method are employed in the process of speckle noise. This model not only improves the plasticity of the model, but also improves the effect and efficiency of noise removal. The new model has different diffusion performance in different regions. At the same time, the diffusion performance is related to the parameters introduced by the proposed model. Numerical simulation results show that different parameters have different denoising effects, and the proposed model for speckle noise removal is superior to traditional models.     

DHIQA: Quality assessment of dehazed images based on attentive multi-scale feature fusion and rank learning

Haze is a ubiquitous atmospheric phenomenon that seriously influences the visibility of images. To this end, numerous image dehazing models have been proposed to improve the visual quality of hazy images. However, the quality assessment of dehazed images has fallen behind. Traditional IQA methods for dehazed images rely on complex handcrafted features that may not accurately evaluate the quality of dehazed images. In this paper, we present a novel no-reference image quality assessment network for dehazed images (called DHIQA). Firstly, we propose a multi-scale feature fusion network that considers typical dehazed distortion-related features, such as contrast, dark channel, edge, etc. Then, inspired by the contrast sensitivity function of the Human Visual System (HVS), we propose a contrast attentive module to enhance the effectiveness of the proposed IQA network. Moreover, in addition to the absolute quality score of dehazed images, their rankings are also important for quality assessment. Thus, we propose a new ranking loss, which takes both the absolute quality score and their rankings into consideration. Extensive experimental results on six publicly available dehazed IQA databases show that the proposed model achieves superior performance compared to current state-of-the-art metrics.     

Simulations of asynchronous evolution of discrete systems

Recently, a convergence theorem of asynchronous iterations of discrete dynamic systems partitioned into blocks has been proved [2]. This theorem is verified with several asynchronous block strategies. It also generalizes the chaotic iterations. Different simulations of asynchronous evolution of discrete systems performed with the research software Discrete System Evolution (DSE), lead to the first experimental results predicted by this theorem.     

Nonlocal ultrasound image despeckling via improved statistics and rank constraint

Pattern Analysis and Applications - Ultrasound images are often contaminated by speckle noise during the acquisition process, which influences the performance of subsequent applications. Hence, it...