Jove
Visualize
联系我们

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

IoT-Based System for Real-Time Monitoring and AI-Driven Energy Consumption Prediction in Fresh Fruit and Vegetable Transportation.

Sensors (Basel, Switzerland)·2025
Same author

TLC-bioautography-guided valorization of vetiver (Chrysopogon spp.) leaf extracts into an anti-acne gel.

Bioresources and bioprocessing·2025
Same author

Phytochemical Characterization, Bioactivities, and Nanoparticle-Based Topical Gel Formulation Development from Four <i>Mitragyna speciosa</i> Varieties.

Gels (Basel, Switzerland)·2025
Same author

Formulation and Stability of Quercetin-Loaded Pickering Emulsions Using Chitosan/Gum Arabic Nanoparticles for Topical Skincare Applications.

Polymers·2025
Same author

Enhanced Multi-Model Machine Learning-Based Dementia Detection Using a Data Enrichment Framework: Leveraging the Blessing of Dimensionality.

Bioengineering (Basel, Switzerland)·2025
Same author

Development and Evaluation of Anti-Pollution Film-Forming Facial Spray Containing Coffee Cherry Pulp Extract.

Pharmaceutics·2025
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

相关实验视频

Updated: Jul 9, 2025

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.3K

使用图像处理和深度学习方法对人类皮肤类型进行分类.

Sirawit Saiwaeo1, Sujitra Arwatchananukul1,2, Lapatrada Mungmai3,4

  • 1School of Information Technology, Mae Fah Luang University, Chiang Rai, Thailand.

Heliyon
|November 29, 2023
PubMed
概括
此摘要是机器生成的。

这项研究开发了一种使用卷积神经网络 (CNN) 的AI模型,以准确地从图像中分类皮肤类型. EfficientNet-V2模型实现了高精度,帮助消费者选择合适的化品.

关键词:
在美国,CNN是CNN.对比性有限的适应性直方体平衡 (CLAHE)数据准备 数据准备图像增强 图像增强 图像增强图像增强 图像增强 图像增强皮肤图像 皮肤图像

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K

相关实验视频

Last Updated: Jul 9, 2025

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.3K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K

科学领域:

  • 皮肤病学 皮肤病学
  • 人工智能的人工智能
  • 计算机视觉 计算机视觉

背景情况:

  • 准确的皮肤类型识别对于化品产品的选择至关重要.
  • 皮肤类型的变化 (油性,干燥,正常) 可以使自我评估复杂化.
  • 人工智能 (AI) 和机器学习 (ML) 为客观分类提供了潜在的解决方案.

研究的目的:

  • 开发和评估用于自动化皮肤类型分类的深度学习模型.
  • 为了比较各种卷积神经网络 (CNN) 架构的性能.
  • 优化CNN模型,以提高皮肤类型识别的准确性.

主要方法:

  • 一个数据集的正常,油性和干燥的皮肤图像被策划.
  • 图像预处理包括对比限度自适应组图平衡 (CLAHE) 和数据增强.
  • 一些CNN架构 (MobileNet-V2,EfficientNet-V2,InceptionV2,ResNet-V1) 进行了训练和优化.这些架构包括:
  • 使用超参数调整和10倍交叉验证进行了可靠的评估.

主要成果:

  • EfficientNet-V2架构表现出卓越的性能,达到91.55%的准确性.
  • 超参数调整进一步提高了模型的准确性,达到94.57%.
  • 最终的模型在未见的数据上实现了89.70%的准确性,这表明了强大的概括性.

结论:

  • 使用CNN进行人工智能驱动的皮肤类型分类是一种可行的,准确的方法.
  • 开发的模型可以帮助消费者做出关于化品产品的明智决策.
  • 进一步的研究可以探索更大的数据集和多样化的群体,以提高模型的稳定性.