期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
Underwater Image Enhancement Based on Multi-scale Adversarial Network
1
作者 ZENG Jun-yang SI Zhan-jun 《印刷与数字媒体技术研究》 CAS 北大核心 2024年第5期70-77,共8页
In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of ea... In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm. 展开更多
关键词 Underwater image enhancement Generative adversarial network Multi-scale feature extraction Residual dense block
下载PDF
图神经网络 被引量:26
2
作者 白铂 刘玉婷 +5 位作者 马驰骋 王光辉 闫桂英 闫凯 张明 周志恒 《中国科学:数学》 CSCD 北大核心 2020年第3期367-384,共18页
近年来,随着海量数据的涌现,可以表示对象之间复杂关系的图结构数据越来越受到重视并给已有的算法带来了极大的挑战.图神经网络作为可以揭示深层拓扑信息的模型,已开始广泛应用于诸多领域,如通信、生命科学和经济金融等.本文对近几年来... 近年来,随着海量数据的涌现,可以表示对象之间复杂关系的图结构数据越来越受到重视并给已有的算法带来了极大的挑战.图神经网络作为可以揭示深层拓扑信息的模型,已开始广泛应用于诸多领域,如通信、生命科学和经济金融等.本文对近几年来提出的图神经网络模型和应用进行综述,主要分为以下几类:基于空间方法的图神经网络模型、基于谱方法的图神经网络模型和基于生成方法的图神经网络模型等,并提出可供未来进一步研究的问题. 展开更多
关键词 结构数据 神经网络 空间方法 谱方法 自编码器 图对抗生成网络 循环神经网络
原文传递
Gait recognition based on Wasserstein generating adversarial image inpainting network 被引量:4
3
作者 XIA Li-min WANG Hao GUO Wei-ting 《Journal of Central South University》 SCIE EI CAS CSCD 2019年第10期2759-2770,共12页
Aiming at the problem of small area human occlusion in gait recognition,a method based on generating adversarial image inpainting network was proposed which can generate a context consistent image for gait occlusion a... Aiming at the problem of small area human occlusion in gait recognition,a method based on generating adversarial image inpainting network was proposed which can generate a context consistent image for gait occlusion area.In order to reduce the effect of noise on feature extraction,the stacked automatic encoder with robustness was used.In order to improve the ability of gait classification,the sparse coding was used to express and classify the gait features.Experiments results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA-B and TUM-GAID for gait recognition. 展开更多
关键词 gait recognition image inpainting generating adversarial network stacking automatic encoder
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部