> For the complete documentation index, see [llms.txt](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://baozoulin.gitbook.io/neural-networks-and-deep-learning/di-si-men-ke-juan-ji-shen-jing-wang-luo-convolutional-neural-networks/convolutional-neural-networks/object-detection/36-jiao-bing-bi-ff08-intersection-over-union.md).

# 3.6 交并比（Intersection over union）

并交比函数可以用来评价对象检测算法

[![](https://github.com/fengdu78/deeplearning_ai_books/raw/master/images/38eea69baa46091d516a0b7a33e5379e.png)](https://github.com/fengdu78/deeplearning_ai_books/blob/master/images/38eea69baa46091d516a0b7a33e5379e.png)

交并比（**loU**）函数是计算两个边界框交集和并集之比。两个边界框的并集是两个边界框绿色阴影区域，而交集是这个橙色阴影区域，交并比就是交集的大小（橙色阴影面积）除以绿色阴影的并集面积

一般约定，在计算机检测任务中，如果loU≥0.5，就说检测正确，如果预测器和实际边界框完美重叠，**loU**就是1，因为交集就等于并集