blocks|key|287155|text|对于这类问题，Shape+Context似乎是一个自然而然的选择。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|287156|entityMap|0|LINK|mutability|MUTABLE|url|http://en.wikipedia.org/wiki/Shape_context^0|7|D|0|0^^$0|@$1|2|3|4|5|6|7|L|8|@]|9|@$A|M|B|N|1|O]]|C|$]]|$1|D|3|-4|5|6|7|P|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]]]

It seems like <a href="http://en.wikipedia.org/wiki/Shape_context" rel="nofollow">Shape Context</a> would be a natural choice for this type of problem.

blocks|key|855247|text|几年前，我尝试使用here.描述的OpenCV进行模板匹配|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|855248|它工作得很好，我认为这就是你想要的；但是我记得它相当慢，所以如果你正在编写实时应用程序，它可能不是一个很好的选择。如果是这种情况，您可能需要处理形状的几何体，并尝试使用用于lines和circles的Hough+transforms来查找它们，这两个工具都是在OpenCV中实现的。|855249|祝你玩得开心！|855250|entityMap|0|LINK|mutability|MUTABLE|url|http://opencv.itseez.com/doc/tutorials/imgproc/histograms/template_matching/template_matching.html?highlight=template%2520matching|1|http://opencv.itseez.com/modules/imgproc/doc/feature_detection.html?highlight=hough#CvSeq%252a%2520cvHoughLines2%2528CvArr%252a%2520image,%2520void%252a%2520line_storage,%2520int%2520method,%2520double%2520rho,%2520double%2520theta,%2520int%2520threshold,%2520double%2520param1,%2520double%2520param2%2529|2|http://opencv.itseez.com/modules/imgproc/doc/feature_detection.html?highlight=hough#CvSeq%252a%2520cvHoughCircles%2528CvArr%252a%2520image,%2520void%252a%2520circle_storage,%2520int%2520method,%2520double%2520dp,%2520double%2520min_dist,%2520double%2520param1,%2520double%2520param2,%2520int%2520min_radius,%2520int%2520max_radius%2529|3|http://en.wikipedia.org/wiki/Hough_transform^0|9|5|0|0|2E|5|1|2K|7|2|2S|G|3|0|0^^$0|@$1|2|3|4|5|6|7|V|8|@]|9|@$A|W|B|X|1|Y]]|C|$]]|$1|D|3|E|5|6|7|Z|8|@]|9|@$A|10|B|11|1|12]|$A|13|B|14|1|15]|$A|16|B|17|1|18]]|C|$]]|$1|F|3|G|5|6|7|19|8|@]|9|@]|C|$]]|$1|H|3|-4|5|6|7|1A|8|@]|9|@]|C|$]]]|I|$J|$5|K|L|M|C|$N|O]]|P|$5|K|L|M|C|$N|Q]]|R|$5|K|L|M|C|$N|S]]|T|$5|K|L|M|C|$N|U]]]]

some years ago I tried template matching with OpenCV, which is described <a href="http://opencv.itseez.com/doc/tutorials/imgproc/histograms/template_matching/template_matching.html?highlight=template%20matching" rel="nofollow">here.</a>

It worked pretty well, and I think this is what you are looking for; however I remember that it was pretty slow, so maybe it won't be a good fit if you are programming a real time application. If this is the case, you may have to play around with the geometry of your shapes, and try to find them with <a href="http://en.wikipedia.org/wiki/Hough_transform" rel="nofollow">Hough transforms</a> for <a href="http://opencv.itseez.com/modules/imgproc/doc/feature_detection.html?highlight=hough#CvSeq%2a%20cvHoughLines2%28CvArr%2a%20image,%20void%2a%20line_storage,%20int%20method,%20double%20rho,%20double%20theta,%20int%20threshold,%20double%20param1,%20double%20param2%29" rel="nofollow">lines</a> and <a href="http://opencv.itseez.com/modules/imgproc/doc/feature_detection.html?highlight=hough#CvSeq%2a%20cvHoughCircles%28CvArr%2a%20image,%20void%2a%20circle_storage,%20int%20method,%20double%20dp,%20double%20min_dist,%20double%20param1,%20double%20param2,%20int%20min_radius,%20int%20max_radius%29" rel="nofollow">circles</a>, which are both implemented in OpenCV.

Have fun !

I'm working on my first computer vision project where I take a picture of a chart and detect the symbols on it. There are 5 distinct shapes that need to be detected. 

This is the result of my edge detection algorithm: <a href="http://i.imgur.com/mh9Ol.jpg">http://i.imgur.com/mh9Ol.jpg</a>. The 5 symbols are a single dot, 4 dots grouped together, a rectangle, and 2 oddly shaped symbols.

At this point I'm not sure which algorithms I should look at that will allow me to pick out these shapes and discern them from each other. Any ideas would be very helpful. Thanks!

Shape recognition after edge detection

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

教程

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云智能顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云AI代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

功能1上新10个字符

功能2描述100个字符功能2描述100个字符功能2描述100个字符功能2描述100个字符功能2描述100个字符功能2描述100个字符功能2描述100个字符功能2描述100个字符功能2描述100个字符。

功能2上新100个字符功能2上新100个字符功能2上新100个字符功能2上新100个字符功能2上新100个字符功能2上新100个字符功能2上新100个字符功能2上新100个字符功能2上新100个字符。

功能5描述100个字符功能5描述100个字符功能5描述100个字符功能5描述100个字符功能5描述100个字符功能5描述100个字符

功能5上新100个字符功能5上新100个字符功能5上新100个字符功能5上新100个字符功能5上新100个字符功能5上新100个字符功能5上新100个字符功能5上新100个字符功能5上新100个字符功能5上新100个字符

功能4上新

文章&问答评论现已支持表情

全新交互，全新视觉，新增快捷键、悬浮工具栏、高亮块等功能并同时优化现有功能，全面提升创作效率和体验

社区富文本编辑器全新改版！诚邀体验～ 

精选全网热门MCP server，让你的AI更好用 🚀

💥开发者 MCP广场重磅上线！

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

聚焦“写作效率、视觉美观与运行性能”三方面进行全面升级，为您提供更高效、稳定的创作环境

社区富文本&Markdown编辑器全新改版上线，欢迎大家体验!

诚挚邀请您参与本次调研，分享您的真实使用感受与建议。您的反馈至关重要，感谢您的支持与参与！

社区新版编辑器体验调研

我正在做我的第一个计算机视觉项目，我拍摄了一张图表的照片，并检测上面的符号。有5个不同的形状需要检测。这是我的边缘检测算法的结果。这5个符号是一个单独的点，4个点组合在一起，一个矩形，和两个奇怪的形状的符号。在这一点上，我不确定我应该查看哪些算法，以便我能够挑选出这些形状，并将它们彼此区分开来。任何想法都会很有帮助。谢谢!

问边缘检测后的形状识别
EN

回答 2

Stack Overflow用户

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问边缘检测后的形状识别EN

回答 2

Stack Overflow用户

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问边缘检测后的形状识别
EN