对象识别，检测与分类?有什么不同? [英] Object recognition vs detection vs classification? What's the difference?

问题描述

我不知道这是否是在正确的stackexchange论坛上问这个问题的地方，如果不是这种情况，请告诉我.

I don't know if this the right stackexchange forum where to ask this question, please let me know if this is not the case.

我正在开发一个应用程序，该应用程序给出了包含绘画的输入图像作为输入，它能够告诉您绘画的标题.类似的情况是:给定包含建筑物的输入图像，返回的结果就是建筑物的名称.

I'm developing an application which given an input image containing a painting as input, it is able to tell you the title of the painting. An analogous case is: given an input image containing a building, the returned result is the name of the building.

这是什么样的应用程序?首先，我会说图像分类"之类的话.我不是计算机视觉方面的专家，但我一直认为图像分类"类似于给定图像，告诉我该图像包含什么".

What kind of application is this? On first impact, I would say something like "image classification". I'm not an expert on computer vision, but I always thought that "image classification" is something like "given an image, tells me what is contained in this image".

另一方面，对象检测定义似乎与识别类的对象(例如，建筑物)更相关，而不是识别类本身的实例(例如，长城):

On the other hand, object detection definition seems more related to identify an object of a class (e.g. a building) and not an instance of the class itself (e.g. Great Wall):

对象检测是一种与计算机视觉有关的计算机技术 以及用于检测语义实例的图像处理 某类的物体(例如人，建筑物或汽车)在 数字图像和视频.

Object detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos.

关于对象识别:

对象识别是感知对象物理能力的能力 属性(例如形状，颜色和纹理)并应用语义 属性(例如，将对象识别为苹果).

Object recognition is the ability to perceive an object's physical properties (such as shape, colour and texture) and apply semantic attributes to it (such as identifying the object as an apple).

我真的不知道如何对所描述的应用程序进行分类(开个玩笑...).你觉得呢?

I don't really know how to classify (what a joke...) my described application. What do you think?

推荐答案

简单说明:您正要去森林，天黑了.突然之间，您会看到与背景不同的东西(纯黑).这称为检测.

To Explain Simply: You are going to the forest and it is utter dark. All of a sudden you see thing that is different from background (pure dark). This is called Detection.

1)出现了与您的背景不同的东西.因此您检测到了.

1) something is appearing which is different from your background.So you detected.

2)现在越来越近了，您发现它是动物.嗯..现在您已经分类/被认可了.也可能是人类.

2) Now coming closer, and you identified that it is an animal. Ah.. Now you have classified/Recognised. It could be a human too.

3)现在它越来越近了，现在您看到它是一只鹿.因此，现在您确定了它.

3) Now it is coming even closer, and now you see it a deer. So, now you identified it.

因此序列为 检测->识别/分类->已识别".

So the sequence is "Detected -> Recognized/classified -> Identified'.

身份识别是最后一个外壳，您可以使用带有您的面部(已识别)并归类为(人类)的身份证来记住这一点.

"Identification is the last shell, and this you could remember with your identity card that has your face ( identified), and classified as (Human).

这篇关于对象识别，检测与分类?有什么不同?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！