An unsupervised learning based method for content-based image retrieval using hopfield neural network

机译：基于Hopfield神经网络的基于无监督学习的基于内容的图像检索方法

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

Presently, corporations and individuals have large image databases due to the explosion of multimedia and storage devices available. Furthermore, the accessibility to high speed internet has escalated the level of multimedia exchanged by users across cyberspace every second. Accordingly, it has increased the demand for searching among large databases of images. Conventionally, text-based image retrieval is used. The major problems in text-based image retrieval are related to annotation that is often impossible due to human perception of images being subjective, and also due to the size of the information that needs indexing. To overcome such limitations, content-based image retrieval systems have been proposed. However, there is a key hindrance, namely, the need to match the human visual system to overcome the semantic gap between human perception and low-level features. In this paper, we propose a new unsupervised method based on Hopfield neural networks that seeks to model human visual memory to increase the efficacy of retrieval and reduce the semantic gap. A comparative study with other neural-network based methods, such as the feed forward backpropagation and Boltzmann deep learning, shows the effectiveness of our method.

机译：当前，由于多媒体和可用存储设备的爆炸性增长，公司和个人拥有大型图像数据库。此外，对高速互联网的可访问性已经提高了用户跨网络空间每秒交换的多媒体水平。因此，它增加了在大型图像数据库中搜索的需求。传统上，使用基于文本的图像检索。基于文本的图像检索中的主要问题与注释有关，由于人们对图像的主观感知以及需要索引的信息量，注释通常是不可能的。为了克服这些限制，已经提出了基于内容的图像检索系统。但是，存在一个关键障碍，即需要匹配人类视觉系统以克服人类感知和低级特征之间的语义鸿沟。在本文中，我们提出了一种新的基于Hopfield神经网络的无监督方法，该方法旨在为人类视觉记忆建模，以提高检索效率并减少语义鸿沟。与其他基于神经网络的方法（例如前馈反向传播和Boltzmann深度学习）的比较研究显示了我们方法的有效性。

著录项

来源
《2016 2nd International Conference of Signal Processing and Intelligent Systems》|2016年|1-5|共5页
会议地点 Tehran(IR)
作者
F. Sabahi; M. Omair Ahmad; M. N. S. Swamy;
展开▼
作者单位

Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada;

Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada;

Department of Electrical and Computer Engineering, Concordia University, Montreal, Canada;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Image retrieval; Semantics; Hopfield neural networks; Feature extraction; Training; Classification algorithms;

机译：图像检索;语义; Hopfield神经网络;特征提取;训练;分类算法;

相似文献

外文文献
中文文献
专利

1. Convolutional neural network based dictionary learning to create hash codes for content-based image retrieval [J] . ?aban ?ztürk Procedia Computer Science . 2021,第1期

机译：基于卷积神经网络的基于内容的图像检索创建散列代码
2. Similarity-preserving hash for content-based audio retrieval using unsupervised deep neural networks [J] . Petcharat Panyapanuwat, Suwatchai Kamonsantiroj, Luepol Pipanmaekaporn International Journal of Electrical and Computer Engineering . 2021,第1期

机译：基于内容的音频检索的相似性保存哈希使用无监督的深神经网络
3. Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion [J] . Yansheng Li, Yongjun Zhang, Chao Tao, Remote Sensing . 2016,第9期

机译：通过无监督特征学习和协作亲和度度量融合来基于内容的高分辨率遥感图像检索
4. An unsupervised learning based method for content-based image retrieval using hopfield neural network [C] . F. Sabahi, M. Omair Ahmad, M. N. S. Swamy International Conference of Signal Processing and Intelligent Systems . 2016

机译：基于内容的基于内容图像检索的无监督基于学习方法，使用Hopfield神经网络
5. Content-based image retrieval using deep belief networks. [D] . Kroge, Jason. 2010

机译：使用深度信念网络的基于内容的图像检索。
6. Content-Based Image Retrieval of Chest CT with Convolutional Neural Network for Diffuse Interstitial Lung Disease: Performance Assessment in Three Major Idiopathic Interstitial Pneumonias [O] . Hye Jeon Hwang, Joon Beom Seo, Sang Min Lee, 2021

机译：基于内容的胸部CT与卷积神经网络弥漫性间质肺病的图像检索：三个主要特发性肺炎的性能评估
7. Similarity-preserving hash for content-based audio retrieval using unsupervised deep neural networks [O] . Petcharat Panyapanuwat, Suwatchai Kamonsantiroj, Luepol Pipanmaekaporn 2021

机译：基于内容的音频检索使用无监督的深神经网络的相似性 - 保留哈希

An unsupervised learning based method for content-based image retrieval using hopfield neural network

摘要

著录项

相似文献

相关主题

期刊订阅