Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

MS-GATOR: multi-scale graph attention with topological reasoning for segmentation and classification of prostate cancer based on Gleason scores using histopathology images.

Scientific reports·2026
Same author

Interval versus primary cytoreductive surgery in BRCA-mutated advanced-stage ovarian/peritoneal/tubal carcinoma.

International journal of gynecological cancer : official journal of the International Gynecological Cancer Society·2026
Same author

Racial and Ethnic Disparities in Persistent Chemotherapy-Induced Alopecia Among Women With Breast Cancer.

JAMA network open·2026
Same author

Optimizing feature selection with random reversal and adaptive Gaussian based Dung beetle optimizer for intrusion detection system in IoT.

Scientific reports·2025
Same author

Neutrophil to lymphocyte ratio varies in magnitude and biomarker utility based on patient demographics.

The Journal of clinical investigation·2025
Same author

Impact of an Electronic Patient-Reported Outcome-Informed Clinical Decision Support Tool on Clinical Discussions With Head and Neck Cancer Survivors: Findings From the HN-STAR Randomized Controlled Trial (WF-1805CD).

JCO oncology practice·2025

相关实验视频

Updated: Sep 16, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.6K

智能自适应学习和优化的功能聚类,以增强图像检索.

P Umaeswari1, Sujata Patil2, Parameshachari Bidare Divakarachari3

  • 1Department of Computer Science and Business Systems R.M.K. Engineering College, Kavaraipettai, India.

Scientific reports
|July 7, 2025
PubMed
概括

本研究介绍了SEGJO-EDCNN,这是一种基于内容的图像检索 (CBIR) 的新方法. 它增强了特征集群和匹配精度,在基准数据集上实现了卓越的性能.

关键词:
基于内容的图像检索卷积神经网络是一种卷积神经网络.精英学习反对派学习.基于的分歧函数是基于的.金子优化优化 黄金子优化扩展因子的扩展因子

更多相关视频

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.2K

相关实验视频

Last Updated: Sep 16, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.6K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K
Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.2K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 信息检索 信息检索

背景情况:

  • 基于内容的图像检索 (CBIR) 面临着巨大的多媒体数据挑战.
  • 准确的特征差异对于有效的CBIR至关重要.
  • 现有的方法在过早的融合和冗余激活方面扎.

研究的目的:

  • 提出一种新的方法,SEGJO-EDCNN,用于增强CBIR.
  • 改进特征聚类和图像检索中的匹配精度.
  • 为了解决现有的CBIR技术的局限性.

主要方法:

  • 开发了SEGJO (基于Scaling Factor和精英反对派学习的黄金子优化) 用于特征集群.
  • 综合扩展因子 (SF) 和精英反对派学习 (EOL) 增强搜索并防止过早的融合.
  • 使用本地二进制模式,Zernike时刻和颜色时刻来提取特征.
  • 在一个称为EDCNN的卷积神经网络 (CNN) 中整合了一个基于的分歧 (ED) 函数,以改善匹配.

主要成果:

  • 在Corel 5K和牛津花的数据集上,SEGJO-EDCNN表现出卓越的性能.
  • 在Corel 5K数据集上实现了97.595%的平均平均精度 (MAP),表现优于ELNDP和DNN-SAR.
  • 在牛津花朵数据集上获得了99.239%的MAP,超过了SVM-CBIR.

结论:

  • 拟议的SEGJO-EDCNN方法显著提高了CBIR的业绩.
  • 整合SF,EOL和EDCNN有效地提高了特征集群和检索准确度.
  • 对于大规模图像检索日益增长的挑战,SEGJO-EDCNN提供了一个强大的解决方案.