Multiple Sequential Regularized Extreme Learning Machines for Single Image Super Resolution

Cosmo, Daniel Luis; Salles, Evandro Ottoni Teatini

doi:10.1109/lsp.2019.2895543

Cited by 9 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of individual differences, the physical health evaluation scheme has a significant impact on the evaluation results, and there are significant differences in the effects of blood oxygen index, blood pressure, and heart rate [ 17 ]. Although the linear sequential extreme learning machine algorithm matrix can carry out progressive analysis on mass physical health data, the analysis results are discrete.…”

Section: The Prediction Model Of Physical Health Development Based On...mentioning

confidence: 99%

A Prediction Model of Health Development Based on Linear Sequential Extreme Learning Machine Algorithm Matrix

Cheng

Liu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The rapid development of social economy not only increases people’s living pressure but also reduces people’s health. Looking for a healthy development prediction model has become a domestic concern. Based on the analysis of the influencing factors of health development, this paper looks for a model to predict the development of public health, so as to improve the accuracy of health development prediction. In this paper, the linear sequential extreme learning machine algorithm can be used to evaluate the health status of a large number of data, analyze the differences of each evaluation index, and construct the analysis model of health status. Therefore, this paper introduces rough set theory into linear sequential extreme learning machine algorithm. Rough set can analyze the double analysis of evaluation scheme, predict the health development of different individuals, and improve the evaluation accuracy of mass health evaluation. The simulation results show that the improved line sequential extreme learning machine algorithm can accurately analyze the mass health and meet the needs of different individuals’ health evaluation.

show abstract

Section: The Prediction Model Of Physical Health Development Based On...mentioning

confidence: 99%

A Prediction Model of Health Development Based on Linear Sequential Extreme Learning Machine Algorithm Matrix

Cheng

Liu

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Owing to the rapid development of artificial intelligence technology, emerging applications, such as Alexa, Woogie, and Prisma, grow more prevalent than ever to change human lives. As a classical problem in computer vision, image super-resolution technology [1], [2], [3], [4], [5], [6], [7] also achieves tremendous progress and be widely used in many mobile devices, such as mobile phones, for photo enhancement [8]. With such a light-weight algorithm, mobile devices are capable of providing a high-quality photograph and free from purchase expensive sensors.…”

Section: Introductionmentioning

confidence: 99%

DDet: Dual-Path Dynamic Enhancement Network for Real-World Image Super-Resolution

Shi

Zhong

Yang

et al. 2020

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

Different from traditional image super-resolution task, real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and lowresolution(LR) image. Most of the traditional image SR obtains the LR sample by applying a fixed down-sampling operator. Real-SR obtains the LR and HR image pair by incorporating different quality optical sensors. Generally, Real-SR has more challenges as well as broader application scenarios. Previous image SR methods fail to exhibit similar performance on Real-SR as the image data is not aligned inherently. In this article, we propose a Dual-path Dynamic Enhancement Network(DDet) for Real-SR, which addresses the cross-camera image mapping by realizing a dual-way dynamic sub-pixel weighted aggregation and refinement. Unlike conventional methods which stack up massive convolutional blocks for feature representation, we introduce a content-aware framework to study non-inherently aligned image pair in image SR issue. First, we use a content-adaptive component to exhibit the Multi-scale Dynamic Attention(MDA). Second, we incorporate a long-term skip connection with a Coupled Detail Manipulation(CDM) to perform collaborative compensation and manipulation. The above dual-path model is joint into a unified model and works collaboratively. Extensive experiments on the challenging benchmarks demonstrate the superiority of our model.

show abstract

“…Recently, the advancement of convolutional neural networks (CNNs) has activated a lot of studies on both general image and face SR. The state-of-the-art methods [6][7][8][9][10][11] commonly adopt a well-customized CNN structure to learn a complex non-linear mapping between many pairs of LR and HR images. The structure of the CNN tends to be deeper and wider, with increasing data to feed.…”

Section: Introductionmentioning

confidence: 99%

Facial image super-resolution guided by adaptive geometric features

Fan

Chen

et al. 2020

J Wireless Com Network

View full text Add to dashboard Cite

This paper addresses the traditional issue of restoring a high-resolution (HR) facial image from a low-resolution (LR) counterpart. Current state-of-the-art super-resolution (SR) methods commonly adopt the convolutional neural networks to learn a non-linear complex mapping between paired LR and HR images. They discriminate local patterns expressed by the neighboring pixels along the planar directions but ignore the intrinsic 3D proximity including the depth map. As a special case of general images, the face has limited geometric variations, which we believe that the relevant depth map can be learned and used to guide the face SR task. Motivated by it, we design a network including two branches: one for auxiliary depth map estimation and the other for the main SR task. Adaptive geometric features are further learned from the depth map and used to modulate the mid-level features of the SR branch. The whole network is implemented in an end-to-end trainable manner under the extra supervision of depth map. The supervisory depth map is either a paired one from RGB-D scans or a reconstructed one by a 3D prior model of faces. The experiments demonstrate the effectiveness of the proposed method and achieve improved performance over the state of the arts.

show abstract

Multiple Sequential Regularized Extreme Learning Machines for Single Image Super Resolution

Cited by 9 publications

References 25 publications

A Prediction Model of Health Development Based on Linear Sequential Extreme Learning Machine Algorithm Matrix

A Prediction Model of Health Development Based on Linear Sequential Extreme Learning Machine Algorithm Matrix

DDet: Dual-Path Dynamic Enhancement Network for Real-World Image Super-Resolution

Facial image super-resolution guided by adaptive geometric features

Contact Info

Product

Resources

About