Comparison of CNN Tolerances to Intra Class Variety in Food Recognition

机译：CNN对食品识别中类内品种的耐受性比较

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

Intra-class variation defines image variations occur between different images of one class. The similarity between samples within the same class is typically measured by the Intra-class Correlation coefficient. A high Intra-class Correlation Coefficient close to 1 indicates high similarity between samples from the same class where a low ICC close to zero means opposite. This paper deals with intra-class variety problem of Kegels Foodl0l dataset. 21 classes that have high ICC values were chosen. We have applied well known convolutional neural networks including ResNet, GoogleNet, MobileNet and VGG-Net with different train and test percentages in order to compare the recognition rates for the classes. Although the samples in Food101 dataset vary widely, GoogleNet (Inception V3) has the highest validation accuracy value with the lowest number of epochs.

机译：类内变化定义图像变化发生在一类的不同图像之间。同一类别内样本之间的相似性通常由类别内相关系数来衡量。接近1的高类内相关系数表示来自同一类的样本之间的相似度高，而接近零的低ICC表示相反。本文讨论了凯格斯食品101数据集的类内变种问题。选择了21个具有较高ICC值的类。我们已经应用了包括ResNet，GoogleNet，MobileNet和VGG-Net在内的众所周知的卷积神经网络，它们具有不同的训练和测试百分比，以便比较类别的识别率。尽管Food101数据集中的样本差异很大，但GoogleNet（Inception V3）的验证准确性值最高，历元数最少。

著录项

来源
《2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications》|2019年|1-5|共5页
会议地点 Sofia(BG)
作者
Murat Taskiran; Nihan Kahraman;
展开▼
作者单位

Dept. Electronics and Communication Engineering, Yildz Technical University, Istanbul, Turkey;

Dept. Electronics and Communication Engineering, Yildz Technical University, Istanbul, Turkey;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Training; Reactive power; Deep learning; Databases; Correlation; Convolutional neural networks; Obesity;

机译：培训;无功;深度学习;数据库;关联;卷积神经网络;肥胖;;

相似文献

外文文献
中文文献
专利

1. 模糊的类内矩阵模式主分量分析及在人脸识别中的应用 [J] . 朱玉莲南京航空航天大学学报（英文版） . 2008,第002期
2. CNN-SSPSO: A Hybrid and Optimized CNN Approach for Peripheral Blood Cell Image Recognition and Classification [J] . Kumar Rajiv, Joshi Shivani, Dwivedi Avinash International Journal of Pattern Recognition and Artificial Intelligence . 2021,第5期

机译：CNN-SSPSO：一种用于外围血细胞图像识别和分类的混合和优化的CNN方法
3. Recognition of human actions using CNN-GWO: a novel modeling of CNN for enhancement of classification performance [J] . Kumaran N., Vadivel A., Kumar S. Saravana Multimedia Tools and Applications . 2018,第18期

机译：使用CNN-GWO识别人类行为：用于增强分类性能的CNN新型模型
4. Striking sequence similarity in inter- and intra-specific comparisons of class I SLG alleles from Brassica oleracea and Brassica campestris: Implications for the evolution and recognition mechanism [J] . Makoto Kusaba, Takeshi Nishio, Yoko Satta Proceedings of the National Academy of Sciences of the United States of America . 1997,第14期

机译：甘蓝和油菜I类SLG等位基因种间和种内比较的惊人序列相似性：对进化和识别机制的启示
5. Comparison of CNN Tolerances to Intra Class Variety in Food Recognition [C] . Murat Taskiran, Nihan Kahraman IEEE International Symposium on INnovations in Intelligent SysTems and Applications . 2019

机译：CNN耐受对食品认可中类多样性的比较
6. UAV Imagery for Tree Species Classification in Hawai'i: A Comparison of MLC, RF, and CNN Supervised Classification [D] . Ford, Derek James. 2020

机译：夏威夷树种类的无人机图像：MLC，RF和CNN监督分类的比较
7. Striking sequence similarity in inter- and intra-specific comparisons of class I SLG alleles from Brassica oleracea and Brassica campestris: Implications for the evolution and recognition mechanism [O] . Makoto Kusaba, Takeshi Nishio, Yoko Satta, 1997

机译：甘蓝和油菜I类SLG等位基因的种间和种内比较中的惊人序列相似性：对进化和识别机制的启示
8. Food Recognition using Fusion of Classifiers based on CNNs [O] . Aguilar, Eduardo, Bolaños, Marc, Radeva, Petia 2017

机译：基于CNN的分类器融合的食物识别

Comparison of CNN Tolerances to Intra Class Variety in Food Recognition

摘要

著录项

相似文献

相关主题

期刊订阅