@文章{信息:doi/10.2196/15602,作者="Van Asbroeck, Stephanie and Matthys, Christophe",标题="在膳食评估中使用不同的食品图像识别平台:比较研究",期刊="JMIR Form Res",年="2020",月="12",日="7",卷="4",数="12",页="e15602",关键词="图像识别;饮食的评估;自动食品识别;背景:在饮食评估领域,越来越多的人批评基于记忆的技术,如食物频率问卷调查或24小时回忆。一种替代方法是记录所吃食物的图片,然后进行自动图像识别分析,提供图片中食物的类型和数量的信息。然而,目前尚不清楚商业图像识别平台的表现如何,以及它们是否真的可以用于饮食评估。目的:这是一个商业图像识别平台的性能比较研究。方法:在一系列标准设置下拍摄各种食物和饮料。所有图片(n=185)上传到选定的识别平台(n=7),并保存估计值。在多种成分盘子的情况下,准确性与估计的总数一起确定。 Results: Top 1 accuracies ranged from 63{\%} for the application programming interface (API) of the Calorie Mama app to 9{\%} for the Google Vision API. None of the platforms were capable of estimating the amount of food. These results demonstrate that certain platforms perform poorly while others perform decently. Conclusions: Important obstacles to the accurate estimation of food quantity need to be overcome before these commercial platforms can be used as a real alternative for traditional dietary assessment methods. ", issn="2561-326X", doi="10.2196/15602", url="https://formative.www.mybigtv.com/2020/12/e15602", url="https://doi.org/10.2196/15602", url="http://www.ncbi.nlm.nih.gov/pubmed/33284118" }
Baidu
map