blocks|key|4675133|text|如果您知道要在护照中查找文本，为什么不先尝试查找护照上的模型点。使用ASM/AAM+(Active+shape+model，主动外观模型)技术将护照模板与之匹配。一旦你有了护照位置信息，你就可以剪切出你感兴趣的地区。不过，这需要一些时间来实现。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|4675134|entityMap^0|0^^$0|@$1|2|3|4|5|6|7|D|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|E|8|@]|9|@]|A|$]]]|C|$]]

If you know that you will look for text in a passport, why not try to find passport model points on it first. Match template of a passport to it by using ASM/AAM (Active shape model, Active Appearance Model) techniques. Once you have passport position information you can cut out the regions that you are interested in. This will take some time to implement though.

blocks|key|841620|text|将this+approach视为一个很好的起点：|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|841621|841622|Black+top-hat和characters.|unordered-list-item|841623|Morphological+closing高亮显示长行blobs.|841624|Otsu+thresholding操作将附近的字符和字符行合并成单个大的horisontal+derivative。|841625|可选的erosion操作删除小的contour+detection，并过滤掉明显太小、太圆或位于错误位置的轮廓将最终为|841626|获得少量可能的位置。计算您找到的位置的光学字符识别并查看是否可以对其进行光学字符识别(+successfully.|841627|+)|841628|这可能不是解决问题的最有效的方法，但它出人意料地健壮。|841629|entityMap|0|LINK|mutability|MUTABLE|url|http://www.pyimagesearch.com/2015/11/30/detecting-machine-readable-zones-in-passport-images/|1|https://en.wikipedia.org/wiki/Top-hat_transform|2|https://en.wikipedia.org/wiki/Closing_(morphology)|3|https://en.wikipedia.org/wiki/Otsu%2527s_method|4|https://en.wikipedia.org/wiki/Edge_detection|5|https://en.wikipedia.org/wiki/Erosion_(morphology)|6|https://ru.wikipedia.org/wiki/Marching_squares^0|1|D|0|0|0|0|D|1|0|0|L|2|0|0|H|3|10|L|4|0|3|7|5|G|H|6|0|0|0|0^^$0|@$1|2|3|4|5|6|7|1D|8|@]|9|@$A|1E|B|1F|1|1G]]|C|$]]|$1|D|3|-4|5|6|7|1H|8|@]|9|@]|C|$]]|$1|E|3|F|5|G|7|1I|8|@]|9|@$A|1J|B|1K|1|1L]]|C|$]]|$1|H|3|I|5|G|7|1M|8|@]|9|@$A|1N|B|1O|1|1P]]|C|$]]|$1|J|3|K|5|G|7|1Q|8|@]|9|@$A|1R|B|1S|1|1T]|$A|1U|B|1V|1|1W]]|C|$]]|$1|L|3|M|5|G|7|1X|8|@]|9|@$A|1Y|B|1Z|1|20]|$A|21|B|22|1|23]]|C|$]]|$1|N|3|O|5|G|7|24|8|@]|9|@]|C|$]]|$1|P|3|Q|5|6|7|25|8|@]|9|@]|C|$]]|$1|R|3|S|5|6|7|26|8|@]|9|@]|C|$]]|$1|T|3|-4|5|6|7|27|8|@]|9|@]|C|$]]]|U|$V|$5|W|X|Y|C|$Z|10]]|11|$5|W|X|Y|C|$Z|12]]|13|$5|W|X|Y|C|$Z|14]]|15|$5|W|X|Y|C|$Z|16]]|17|$5|W|X|Y|C|$Z|18]]|19|$5|W|X|Y|C|$Z|1A]]|1B|$5|W|X|Y|C|$Z|1C]]]]

Consider <a href="http://www.pyimagesearch.com/2015/11/30/detecting-machine-readable-zones-in-passport-images/" rel="nofollow">this approach</a> as a great starting point:

<ul>
<li><a href="https://en.wikipedia.org/wiki/Top-hat_transform" rel="nofollow">Black top-hat</a> followed by a <a href="https://en.wikipedia.org/wiki/Edge_detection" rel="nofollow">horisontal derivative</a> highlights long rows of characters.</li>
<li><a href="https://en.wikipedia.org/wiki/Closing_(morphology)" rel="nofollow">Morphological closing</a> operation(s) merge the nearby characters and character rows together into a single large blob.</li>
<li>Optional <a href="https://en.wikipedia.org/wiki/Erosion_(morphology)" rel="nofollow">erosion</a> operation(s) remove the small blobs.</li>
<li><a href="https://en.wikipedia.org/wiki/Otsu%27s_method" rel="nofollow">Otsu thresholding</a> followed by <a href="https://ru.wikipedia.org/wiki/Marching_squares" rel="nofollow">contour detection</a> and filtering away the contours which are apparently too small, too round, or located in the wrong place will get you a small number of possible locations for the MRZ</li>
<li>Finally, compute <a href="https://en.wikipedia.org/wiki/Minimum_bounding_box_algorithms" rel="nofollow">bounding boxes</a> for the locations you found and see whether you can OCR them successfully.</li>
</ul>

It may not be the most efficient way to solve the problem, but it is surprisingly robust.

blocks|key|185402|text|一种更好的方法是使用投影轮廓方法。投影轮廓法基于以下思想：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|185403|创建一个数组A，并为b/w输入文档中的每一行创建一个条目。现在将Ai设置为原始图像的第i行中的黑色像素数。|185404|(您还可以通过考虑原始图像中的列而不是行来创建垂直投影配置文件。)|185405|现在，数组A是文档的行/列投影直方图，可以通过检查A直方图中的谷来解决检测MRZ的问题。|185406|然而，这个问题并没有完全解决，因此有许多变体和改进。以下是一些附加文档：|185407|谷歌学者中的open+profiles：http://scholar.google.com/scholar?q=projection%2Bprofile%2Bmethod|offset|length|185408|Tesseract-ocr，一个伟大的开源OCR库：https://code.google.com/p/tesseract-ocr/|unordered-list-item|185409|185410|entityMap|0|LINK|mutability|MUTABLE|url|http://scholar.google.com/scholar?q=projection%2Bprofile%2Bmethod|1|https://code.google.com/p/tesseract-ocr/^0|0|0|0|0|0|K|1P|0|0|Q|14|1|0|0^^$0|@$1|2|3|4|5|6|7|11|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|12|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|13|8|@]|9|@]|A|$]]|$1|F|3|G|5|6|7|14|8|@]|9|@]|A|$]]|$1|H|3|I|5|6|7|15|8|@]|9|@]|A|$]]|$1|J|3|K|5|6|7|16|8|@]|9|@$L|17|M|18|1|19]]|A|$]]|$1|N|3|O|5|P|7|1A|8|@]|9|@$L|1B|M|1C|1|1D]]|A|$]]|$1|Q|3|-4|5|6|7|1E|8|@]|9|@]|A|$]]|$1|R|3|-4|5|6|7|1F|8|@]|9|@]|A|$]]]|S|$T|$5|U|V|W|A|$X|Y]]|Z|$5|U|V|W|A|$X|10]]]]

A better approach would be the use of projection profile methods. A projection profile method is based on the following idea:

Create an array A with an entry for every row in your b/w input document. Now set A[i] to the number of black pixels in the i-th row of your original image.

(You can also create a vertical projection profile by considering columns in the original image instead of rows.)

Now the array A is the projected row/column histogram of your document and the problem of detecting MRZs can be approached by examining the valleys in the A histogram.

This problem, however, is not completely solved, so there are many variations and improvements. Here's some additional documentation:

<ul>
<li>Projection profiles in Google Scholar: <a href="http://scholar.google.com/scholar?q=projection+profile+method" rel="nofollow">http://scholar.google.com/scholar?q=projection+profile+method</a></li>
<li>Tesseract-ocr, a great open source OCR library: <a href="https://code.google.com/p/tesseract-ocr/" rel="nofollow">https://code.google.com/p/tesseract-ocr/</a></li>
</ul>

blocks|key|4192141|text|Viola+&Jones的类Haar特征生成许多(许多)特征来尝试描述对象，并且在规模等方面更健壮。他们的方法是解决难题的独特方法。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|4192142|然而，在这里，您对问题有很多限制，这样的任何事情似乎有点夸张。而不是“提前优化”，我想说的是评估一下现成的标准OCR工具，看看它们会给你带来什么。我相信你会感到惊喜的。|4192143|PS：|4192144|您需要对图像进行预处理，以分离出白色背景上的字符。这可以很容易地完成，并且将对OCR算法有很大的帮助。|4192145|entityMap^0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|J|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|K|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|L|8|@]|9|@]|A|$]]|$1|F|3|G|5|6|7|M|8|@]|9|@]|A|$]]|$1|H|3|-4|5|6|7|N|8|@]|9|@]|A|$]]]|I|$]]

Viola &amp; Jones' Haar-like features generate many (many (many)) features to try to describe an object and are a bit more robust to scale and the like. Their approach was a unique approach to a difficult problem.

Here, however, you have plenty of constraint on the problem and anything like that seems a bit overkill. Rather than 'optimizing early', I'd say evaluate the standard OCR tools off the shelf and see where they get you. I believe you'll be pleasantly surprised.

PS: 
You'll want to preprocess the image to isolate the characters on a white background. This can be done quite easily and will help the OCR algorithms significantly.

blocks|key|185914|text|您可能需要考虑使用stroke+width+transform。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|185915|您可以遵循these+tips来实现它。|185916|entityMap|0|LINK|mutability|MUTABLE|url|http://www.math.tau.ac.il/%257Eturkel/imagepapers/text_detection.pdf|1|https://stackoverflow.com/q/11116199/1714410^0|9|M|0|0|5|A|1|0^^$0|@$1|2|3|4|5|6|7|P|8|@]|9|@$A|Q|B|R|1|S]]|C|$]]|$1|D|3|E|5|6|7|T|8|@]|9|@$A|U|B|V|1|W]]|C|$]]|$1|F|3|-4|5|6|7|X|8|@]|9|@]|C|$]]]|G|$H|$5|I|J|K|C|$L|M]]|N|$5|I|J|K|C|$L|O]]]]

You might want to consider using <a href="http://www.math.tau.ac.il/%7Eturkel/imagepapers/text_detection.pdf" rel="nofollow noreferrer">stroke width transform</a>. 
You can follow <a href="https://stackoverflow.com/q/11116199/1714410">these tips</a> to implement it.

What method is suitable to capture (detect) <a href="http://en.wikipedia.org/wiki/Machine_Readable_Travel_Document" rel="nofollow">MRZ</a> from a photo of a document? I'm thinking about cascade classifier (e.g. Viola-Jones), but it seems a bit weird to use it for this problem.

Algorithm for capturing machine readable zones

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

什么方法适合从文档的照片中捕获(检测) ？我正在考虑级联分类器(例如Viola-Jones)，但是使用它来解决这个问题似乎有点奇怪。

问捕获机器可读区域的算法
EN

回答 5

Stack Overflow用户

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

问捕获机器可读区域的算法EN

回答 5

Stack Overflow用户

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

问捕获机器可读区域的算法
EN