如何衡量图像检测算法的成功率和百分比准确度？ [英] How to measure the success and percent accuracy of an image detection algorithm?

问题描述

有谁知道如何正确量化图像检测算法的成功？你如何结合2个错误来源？因为一个源是算法无法检测到的对象数，另一个是算法错误识别为对象的误报数。

Does anyone know how to properly quantify the success of an image detection algorithm? How do you combine the 2 sources of error? since one source is the number of objects that the algorithm failed to detect and the other is the number of false positives that the algorithm misidentified as the object.

所以，例如，如果图像中有574个对象，但算法仅检测到540个对象，同时产生113个误报，如何获得百分比准确度？

So if for example there were 574 objects in the image but the algorithm only detected 540 of them while producing 113 false positives, how do I get the percent accuracy?

推荐答案

您可以先计算精度和 F ₁ 得分（有时只是F得分） >回忆算法的性能。

You can calculate what is know as the F₁ Score (sometimes just F Score) by first calculating the precision and recall performance of your algorithm.

精度是真阳性的数量除以预测阳性的数量，其中预测阳性=（真阳性+误报）。

The precision is the number of true positives divided by the number of predicted positives, where predicted positives = (true positives + false positives).

召回是真阳性的数量除以实际阳性的数量，其中实际阳性=（真实）积极+假阴性）。

The recall is the number of true positives divided by the number of actual positives, where actual positives = (true positives + false negatives).

换句话说，精确度表示在我们检测到匹配的所有对象中，分数确实匹配？并且召回意味着在所有实际匹配的对象中，我们正确检测到哪些对象匹配？。

In other words, precision means, "Of all objects where we detected a match, what fraction actually does match?" And recall means "Of all objects that actually match, what fraction did we correctly detect as matching?".

计算精度， P ，召回， R ， F ₁ 得分 2 *（PR /（P + R） ））并为您提供一个指标 - 介于0和1之间 - 用于比较不同算法的性能。

Having calculated precision, P, and recall, R, the F₁ Score is 2 * (PR / (P + R)) and gives you a single metric - between 0 and 1 - with which to compare the performance of different algorithms.

F ₁ 得分是在机器学习中使用的统计指标，以及其他应用程序。您可以在此维基百科条目中阅读更多相关信息。

The F₁ Score is a statistical measure used, among other applications, in machine learning. You can read more about it in this Wikipedia entry.

这篇关于如何衡量图像检测算法的成功率和百分比准确度？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！