Search results

1 – 10 of 30
To view the access options for this content please click here
Article

Shuangshuang Liu and Xiaoling Li

Conventional image super-resolution reconstruction by the conventional deep learning architectures suffers from the problems of hard training and gradient disappearing. In…

Abstract

Purpose

Conventional image super-resolution reconstruction by the conventional deep learning architectures suffers from the problems of hard training and gradient disappearing. In order to solve such problems, the purpose of this paper is to propose a novel image super-resolution algorithm based on improved generative adversarial networks (GANs) with Wasserstein distance and gradient penalty.

Design/methodology/approach

The proposed algorithm first introduces the conventional GANs architecture, the Wasserstein distance and the gradient penalty for the task of image super-resolution reconstruction (SRWGANs-GP). In addition, a novel perceptual loss function is designed for the SRWGANs-GP to meet the task of image super-resolution reconstruction. The content loss is extracted from the deep model’s feature maps, and such features are introduced to calculate mean square error (MSE) for the loss calculation of generators.

Findings

To validate the effectiveness and feasibility of the proposed algorithm, a lot of compared experiments are applied on three common data sets, i.e. Set5, Set14 and BSD100. Experimental results have shown that the proposed SRWGANs-GP architecture has a stable error gradient and iteratively convergence. Compared with the baseline deep models, the proposed GANs models have a significant improvement on performance and efficiency for image super-resolution reconstruction. The MSE calculated by the deep model’s feature maps gives more advantages for constructing contour and texture.

Originality/value

Compared with the state-of-the-art algorithms, the proposed algorithm obtains a better performance on image super-resolution and better reconstruction results on contour and texture.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 12 no. 3
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Article

Lei Zeng, Xiaofeng Li and Jin Xu

The purpose of this paper is to introduce an improved method for joint training of low‐ and high‐resolution dictionaries in the single image super resolution. With…

Abstract

Purpose

The purpose of this paper is to introduce an improved method for joint training of low‐ and high‐resolution dictionaries in the single image super resolution. With simulations, the proposed method is thereafter evaluated.

Design/methodology/approach

Sparse representations of low‐resolution image patches are used to reconstruct the high‐resolution image patches with high resolution dictionary. By using different factors, the scheme weights the two dictionaries in the high‐ and low‐resolution spaces in the training process. It is reasonable to achieve better reconstructed images with more emphasis on the high‐resolution spaces.

Findings

An improved joint training algorithm based on K‐SVD is developed with flexible weight factors on dictionaries in the high‐ and low‐resolution spaces. From the experiment results, the proposed scheme outperforms the classic bicubic interpolation and neighbor‐embedding learning based method.

Originality/value

By using flexible weight factors in joint training of the dictionaries for super resolution, better reconstruction results can be achieved.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering, vol. 32 no. 2
Type: Research Article
ISSN: 0332-1649

Keywords

To view the access options for this content please click here
Article

Haiqing He, Ting Chen, Minqiang Chen, Dajun Li and Penggen Cheng

This paper aims to present a novel approach of image super-resolution based on deep–shallow cascaded convolutional neural networks for reconstructing a clear and…

Abstract

Purpose

This paper aims to present a novel approach of image super-resolution based on deep–shallow cascaded convolutional neural networks for reconstructing a clear and high-resolution (HR) remote sensing image from a low-resolution (LR) input.

Design/methodology/approach

The proposed approach directly learns the residuals and mapping between simulated LR and their corresponding HR remote sensing images based on deep and shallow end-to-end convolutional networks instead of assuming any specific restored models. Extra max-pooling and up-sampling are used to achieve a multiscale space by concatenating low- and high-level feature maps, and an HR image is generated by combining LR input and the residual image. This model ensures a strong response to spatially local input patterns by using a large filter and cascaded small filters. The authors adopt a strategy based on epochs to update the learning rate for boosting convergence speed.

Findings

The proposed deep network is trained to reconstruct high-quality images for low-quality inputs through a simulated dataset, which is generated with Set5, Set14, Berkeley Segmentation Data set and remote sensing images. Experimental results demonstrate that this model considerably enhances remote sensing images in terms of spatial detail and spectral fidelity and outperforms state-of-the-art SR methods in terms of peak signal-to-noise ratio, structural similarity and visual assessment.

Originality/value

The proposed method can reconstruct an HR remote sensing image from an LR input and significantly improve the quality of remote sensing images in terms of spatial detail and fidelity.

Details

Sensor Review, vol. 39 no. 5
Type: Research Article
ISSN: 0260-2288

Keywords

To view the access options for this content please click here
Article

Shafinaz Mohd Basir, Idnin Pasya, Tajmalludin Yaakob, Nur Emileen Abd Rashid and Takehiko Kobayashi

This paper aims to present an approach of utilizing multiple-input multiple-output (MIMO) radar concept to enhance pedestrian classification in automotive sensors. In a…

Abstract

Purpose

This paper aims to present an approach of utilizing multiple-input multiple-output (MIMO) radar concept to enhance pedestrian classification in automotive sensors. In a practical environment, radar signals reflected from pedestrians and slow-moving vehicles are similar in terms of reflecting angle and Doppler returns, inducing difficulty for target discrimination. An efficient discrimination between the two targets depends on the ability of the sensor to extract unique characteristics from each target, for example, by exploiting Doppler signatures. This study describes the utilization of MIMO radar for Doppler measurement and demonstrates its application to improve pedestrian classification through actual laboratory measurements.

Design/methodology/approach

Multiple non-modulated sinusoidal signals are transmitted orthogonally over a MIMO array using time division scheme, illuminating human and non-human targets. The reflected signal entering each of the receiving antenna are combined at the radar receiver prior to Doppler processing. Doppler histogram was formulated based on a series of measurements, and the Doppler spread of the targets was determined from the histograms. Results were compared between MIMO and conventional single antenna systems.

Findings

Measurement results indicated that the MIMO configuration provides able to capture more Doppler information compared to conventional single antenna systems, enabling a more precise discrimination between pedestrian and other slow-moving objects on the road.

Originality/value

The study demonstrated the effectiveness of using MIMO configuration in radar-based automotive sensor to enhance the accuracy of Doppler estimation, which is seldom highlighted in literature of MIMO radars. The result also indicated its usefulness in improving target discrimination capability of the radar, through actual measurement.

Details

Sensor Review, vol. 38 no. 2
Type: Research Article
ISSN: 0260-2288

Keywords

Content available
Article

Jean Paul Simon

This paper aims to clarify the notion of artificial intelligence (AI), reviewing the present scope of the phenomenon through its main applications. It aims at describing…

Abstract

Purpose

This paper aims to clarify the notion of artificial intelligence (AI), reviewing the present scope of the phenomenon through its main applications. It aims at describing the various applications while assessing the markets, highlighting some of the leading industrial sectors in the field. Therefore, it identifies pioneering companies and the geographical distribution of AI companies.

Design/methodology/approach

The paper builds upon an in-depth investigation of public initiatives focusing mostly on the EU. It is based on desk research, a comprehensive review of the main grey and scientific literature in this field.

Findings

The paper notes that there is no real consensus on any definition for this umbrella term, that the definition does fluctuate over time but highlights some of the main changes and advances that took place over the past 60 years. It stresses that, in spite of the hype, on both the business and consumer sides, the demand appears uncertain. The scope of the announced disruptions is not easy to assess, technological innovation associated with AI may be modest or take some time to be fully deployed. However, some companies and regions are leading already in the field.

Research limitations/implications

The paper, based on desk research, does not consider any expert opinions. Besides, the scientific literature on the phenomenon is still scarce (but not the technical one in the specific research sectors of AI). Most of the data come from consultancies or government publications which may introduce some bias, although the paper gathered various, often conflicting viewpoints.

Originality/value

The paper gives a thorough review of the available literature (consultancies, governments) stressing the limitations of the available research on economic and social aspects. It aims at providing a comprehensive overview of the major trends in the field. It gives a global overview of companies and regions.

Details

Digital Policy, Regulation and Governance, vol. 21 no. 3
Type: Research Article
ISSN: 2398-5038

Keywords

To view the access options for this content please click here
Article

suryanarayana gunnam and Ravindra Dhuli

The purpose of this paper is to present an improved wavelet based approach in single image super resolution (SISR). The proposed method generates high resolution (HR…

Abstract

Purpose

The purpose of this paper is to present an improved wavelet based approach in single image super resolution (SISR). The proposed method generates high resolution (HR) images by preserving the image contrast and edges simultaneously.

Design/methodology/approach

Covariance based interpolation algorithm is employed to obtain an initial estimate of the unknown HR image. The proposed method preserves the image contrast, by applying singular value decomposition (SVD) based correction on the dual-tree complex wavelet transform (DT-CWT) coefficients. In addition, the dual operating mode diffusion based shock filter (DBSF) ensures noise mitigation and edge preservation.

Findings

Experimental results on various test images reveal superiority of the proposed method over the existing SISR techniques in terms of peak signal to noise ratio (PSNR), structural similarity index measure (SSIM) and visual quality.

Originality/value

With SVD based correction, the proposed method preserves the image contrast and also the DBSF operation helps to achieve sharper edges.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering , vol. 35 no. 3
Type: Research Article
ISSN: 0332-1649

To view the access options for this content please click here
Book part

Hongming Wang, Ryszard Czerminski and Andrew C. Jamieson

Neural networks, which provide the basis for deep learning, are a class of machine learning methods that are being applied to a diverse array of fields in business…

Abstract

Neural networks, which provide the basis for deep learning, are a class of machine learning methods that are being applied to a diverse array of fields in business, health, technology, and research. In this chapter, we survey some of the key features of deep neural networks and aspects of their design and architecture. We give an overview of some of the different kinds of networks and their applications and highlight how these architectures are used for business applications such as recommender systems. We also provide a summary of some of the considerations needed for using neural network models and future directions in the field.

Content available

Abstract

Details

Sensor Review, vol. 29 no. 3
Type: Research Article
ISSN: 0260-2288

To view the access options for this content please click here
Article

Jie Ren, Huimin Zhao, Jinchang Ren and Shi Cheng

Effective and robust motion estimation with sub-pixel accuracy is essential in many image processing and computer vision applications. Due to its computational efficiency…

Abstract

Purpose

Effective and robust motion estimation with sub-pixel accuracy is essential in many image processing and computer vision applications. Due to its computational efficiency and robustness in the presence of intensity changes as well as geometric distortions, phase correlation in the Fourier domain provides an attractive solution for global motion estimation and image registration. The paper aims to discuss these issues.

Design/methodology/approach

In this paper, relevant sub-pixel strategies are categorized into three classes, namely, single-side peak interpolation, dual-side peak interpolation and curve fitting. The well-known images “Barbara” and “Pentagon” were used to evaluate the performance of eight typical methods, in which Gaussian noise was attached in the synthetic data.

Findings

For eight such typical methods, the tests using synthetic data have suggested that considering dual-side peaks in interpolation or fitting helps to produce better results. In addition, dual-side interpolation outperforms curve fitting methods in dealing with noisy samples. Overall, Gaussian-based dual-side interpolation seems the best in the experiments.

Originality/value

Based on the comparisons of eight typical methods, the authors can have a better understanding of the phase correlation for motion estimation. The evaluation can provide useful guidance in this context.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 9 no. 4
Type: Research Article
ISSN: 1756-378X

Keywords

To view the access options for this content please click here
Book part

Madhulika Bhatia, Shubham Sharma, Madhurima Hooda and Narayan C. Debnath

Recent research advances in artificial intelligence, machine learning, and neural networks are becoming essential tools for building a wide range of intelligent…

Abstract

Recent research advances in artificial intelligence, machine learning, and neural networks are becoming essential tools for building a wide range of intelligent applications. Moreover, machine learning helps to automate analytical model building. Machine learning based frameworks and approaches allow making well-informed and intelligent choices for improving daily eating habits and extension of healthy lifestyle. This book chapter presents a new machine learning approach for meal classification and assessment of nutrients values based on weather conditions along with new and innovative ideas for further study and research on health care-related applications.

Details

Big Data Analytics and Intelligence: A Perspective for Health Care
Type: Book
ISBN: 978-1-83909-099-8

Keywords

1 – 10 of 30