Search

  • Select Article Type
  • Abstract Supplements
  • Blood Group Review
  • Call to Arms
  • Hypothesis
  • In Memoriam
  • Interview
  • Introduction
  • Letter to the Editor
  • Short Report
  • abstract
  • Abstracts
  • Article
  • book-review
  • case-report
  • case-study
  • Clinical Practice
  • Commentary
  • Conference Presentation
  • conference-report
  • congress-report
  • Correction
  • critical-appraisal
  • Editorial
  • Editorial Comment
  • Erratum
  • Events
  • Letter
  • Letter to Editor
  • mini-review
  • minireview
  • News
  • non-scientific
  • Obituary
  • original-paper
  • original-report
  • Original Research
  • Pictorial Review
  • Position Paper
  • Practice Report
  • Preface
  • Preliminary report
  • Product Review
  • rapid-communication
  • Report
  • research-article
  • Research Communicate
  • research-paper
  • Research Report
  • Review
  • review -article
  • review-article
  • review-paper
  • Review Paper
  • Sampling Methods
  • Scientific Commentary
  • short-communication
  • short-report
  • Student Essay
  • Varia
  • Welome
  • Select Journal
  • In Jour Smart Sensing And Intelligent Systems
  • International Journal Advanced Network Monitoring Controls

 

Article | 11-January-2021

Conditional GAN-based Remote Sensing Target Image Generation Method

: Figure 1. Conditional generative countermeasure network structure (1) minGmaxDV(G,D)=Ex∼pdatat(x)[log⁡D(x∣y)]+Ez∼pz[log⁡(1−D(G(x∣y)))] A. Model design of conditional generative countermeasure network Due to the high cost of acquiring remotely sensed sea target image samples, the traditional DGAN model is not ideal when applied to sea target image generation. To reduce the dependence on the number of samples, this paper proposes a conditional generative confrontation network model for ocean

Haoyang Liu, Zhiyi Hu, Jun Yu, Shouyi Gao

International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 4, 66–74

research-article | 30-November-2020

Generating Sea Surface Object Image Using Image-to-Image Translation

I. INTRODUCTION Image generation is one of the popular research domain of computer vision. It is a technology for generating images based on known content (e.g. text, image). It is considered as image-to-image translation when the content is images. 3 In general, a new image can be quickly generated from several images by human beings. However, for machine learning, it can train a large number of images using Generative Adversarial Network (GAN) so as to generate new images. GAN contains a

Wenbin Yin, Jun Yu, Zhiyi Hu

International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 2, 48–55

research-article | 30-November-2020

A review on high dynamic range (HDR) image quality assessment

image processing techniques can make these false contours more visible than ever before; for example, contrast enhancement, sharpness enhancement, color modification, and so on. Some of these techniques are actually used in the HDR image generation process. A summary of various contour detection methods is given in Table 3. Table 3. Summary of contour detection methods. Paper Method Advantage Drawback Huang et al. (2018a, b) False contour candidate in HEVC Detecting very

Irwan Prasetya Gunawan, Ocarina Cloramidina, Salmaa Badriatu Syafa’ah, Rizcy Hafivah Febriani, Guson Prasamuarso Kuntarto, Berkah Iman Santoso

International Journal on Smart Sensing and Intelligent Systems, Volume 14 , ISSUE 1, 1–17

Article | 13-July-2020

Image Inpainting Research Based on Deep Learning

Zhao Li, Zhao Ruixia

International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 2, 23–30

Article | 30-November-2020

Motion Blur Image Restoration by Multi-Scale Residual Neural Network

is to correctly judge whether the data is real data. Because of this way of confrontation training, Gan network can generate new data based on the original data set. Gan network has powerful image generation ability. The generator uses multi-scale residual module to fully extract image features. In each scale, it uses convolution advantages of different sizes to output to the next scale, and transfers parameters through jump connection, which makes it easy to share data. The discriminator

Xu Hexin, Zhao Li, Jiao Yan

International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 1, 57–67

No Record Found..
Page Actions