blocks|key|1637793|text|我发现了PaddleOCR+2和Tesseract+4之间的一个比较，但只针对英语文本。简要概述：|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1637794|PaddleOCR比GPU上的Tesseract稍慢一些，但是有了GPU的支持，它在标准GPU上比Tesseract高出46%25。|ordered-list-item|1637795|在没有后置处理的情况下，PaddleOCR主要是在单词和标点符号之间缺少空格的情况下出错.然而，这些错误可以很容易地纠正。经过后处理，精度与Tesseract相当(低1%25)。|1637796|经过预培训的英语模型只有Tesseracts英语列车数据文件大小的10%25+(2MB对23+2MB)。|1637797|对于目前看来是PaddleOCR的主要优先事项的中文文本来说，情况可能有所不同。|1637798|entityMap|0|LINK|mutability|MUTABLE|url|https://converter.app/blog/paddleocr-engine-example-and-benchmark^0|4|N|0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|U|8|@]|9|@$A|V|B|W|1|X]]|C|$]]|$1|D|3|E|5|F|7|Y|8|@]|9|@]|C|$]]|$1|G|3|H|5|F|7|Z|8|@]|9|@]|C|$]]|$1|I|3|J|5|F|7|10|8|@]|9|@]|C|$]]|$1|K|3|L|5|6|7|11|8|@]|9|@]|C|$]]|$1|M|3|-4|5|6|7|12|8|@]|9|@]|C|$]]]|N|$O|$5|P|Q|R|C|$S|T]]]]

I found a comparison between <a href="https://converter.app/blog/paddleocr-engine-example-and-benchmark" rel="nofollow noreferrer">PaddleOCR 2 and Tesseract 4</a>, but only for English texts. Briefly summarized:
<ol>
<li>PaddleOCR is slightly slower than Tesseract on CPUs, but with GPU support it beats Tesseract by 46% on a standard-GPU.</li>
<li>Without post-processing, PaddleOCR mainly makes mistakes with missing white spaces between words and punctuation symbols. However, these errors can be easily corrected. After postprocessing the accuracy is comparable to Tesseract (1% less).</li>
<li>The pre-trained model for English has only 10% of the file size of Tesseracts English train data (2MB vs 23MB).</li>
</ol>
For Chinese texts, which seem to be the main priortiy of PaddleOCR at the moment, the situation could be different.

blocks|key|583923|text|我用它们测试了英语和日语，但有趣的是，PaddleOCR似乎比Tesseract更能识别它们。PaddleOCR的文本检测似乎也更好。然而，根据他们的帖子，PaddleOCR不能很好地处理空间，并且有来自非中国(或日本)用户的抱怨。PaddleOCR非常渴望将最新的识别/检测算法作为研究论文发表，我已经决定使用PaddleOCR。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|583924|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|$]]

I tested English and Japanese with them but interestingly PaddleOCR seems to recognize both of them better than Tesseract.
PaddleOCR's text detection also seems better.
However according to their posts, PaddleOCR cannot handle spaces very well and there are complaints from non Chinese (or Japanese) users.
PaddleOCR is very eager in incorporating the latest recognition/detection algorithms published as research papers, for which I have decided to use PaddleOCR.

blocks|key|585331|text|我在一些研究中使用这两种方法已经将近一年了。我可以说，每个人都有自己完美的用途。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|585332|PaddleOCR的优点：|offset|length|style|BOLD|585333|如果文本在非90度旋转中旋转，PaddleOCR仍然可以正确地检测到某些文本，但是即使使用OSD，PaddleOCR也无法做到这一点。|ordered-list-item|585334|您可以使用检测结果来修复旋转，但是Tesseract很可能检索无意义的结果。|585335|如果不能对图像进行二值化，PaddleOCR比RGB/BGR中的图像更好。|585336|Tesseract的优点：|585337|即使在操作参数之后，PaddleOCR在检测空间方面也有严重的问题，但是在下一次升级时，他们正在致力于修复这个问题。Tesseract没有明显的空间问题。|585338|Tesseract在处理扫描文档()方面更好。|585339|图像分割模式对于救援和提高图像分割效果有很大帮助。|585340|对于具有长文本的二值化图像，Tesseract的效果通常优于PaddleOCR。|585341|Tesseract在检测符号方面要好得多。|585342|Tesseract是上速度更快的。|585343|简而言之，使用Tesseract将非常适合于扫描文档和PaddleOCR用于通用计算机视觉项目。|585344|entityMap^0|0|0|D|0|5|6|0|5|2|0|N|7|0|0|D|0|M|2|0|C|5|0|2|4|0|4|1|8|3|0|C|2|0|A|6|0|M|4|12|9|0^^$0|@$1|2|3|4|5|6|7|16|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|17|8|@$D|18|E|19|F|G]]|9|@]|A|$]]|$1|H|3|I|5|J|7|1A|8|@$D|1B|E|1C|F|G]]|9|@]|A|$]]|$1|K|3|L|5|J|7|1D|8|@$D|1E|E|1F|F|G]]|9|@]|A|$]]|$1|M|3|N|5|J|7|1G|8|@$D|1H|E|1I|F|G]]|9|@]|A|$]]|$1|O|3|P|5|6|7|1J|8|@$D|1K|E|1L|F|G]]|9|@]|A|$]]|$1|Q|3|R|5|J|7|1M|8|@$D|1N|E|1O|F|G]]|9|@]|A|$]]|$1|S|3|T|5|J|7|1P|8|@$D|1Q|E|1R|F|G]]|9|@]|A|$]]|$1|U|3|V|5|J|7|1S|8|@$D|1T|E|1U|F|G]]|9|@]|A|$]]|$1|W|3|X|5|J|7|1V|8|@$D|1W|E|1X|F|G]|$D|1Y|E|1Z|F|G]]|9|@]|A|$]]|$1|Y|3|Z|5|J|7|20|8|@$D|21|E|22|F|G]]|9|@]|A|$]]|$1|10|3|11|5|J|7|23|8|@$D|24|E|25|F|G]]|9|@]|A|$]]|$1|12|3|13|5|6|7|26|8|@$D|27|E|28|F|G]|$D|29|E|2A|F|G]]|9|@]|A|$]]|$1|14|3|-4|5|6|7|2B|8|@]|9|@]|A|$]]]|15|$]]

I have been using both in some research for almost a year. I can say that each has its own perfect use.
PaddleOCR PROs:
<ol>
<li>If the text is rotated in non-90-degree rotations, PaddleOCR can still detect some text correctly, but Tesseract cannot do this even if OSD is used.</li>
<li>You can use the detection results to fix the rotation, but Tesseract is likely to retrieve non-sense results.</li>
<li>PaddleOCR works better than Tesseract when images in RGB/BGR if you can't binarize your image.</li>
</ol>
Tesseract PROs:
<ol>
<li>PaddleOCR has serious problems with detecting spaces even after manipulating the parameters, but they are working on fixing this in the next upgrade. Tesseract doesn't have significant spaces problems.</li>
<li>Tesseract is better in terms of processing scanned documents.</li>
<li>Image segmentation modes are to the rescue and help a lot with improving the results.</li>
<li>Tesseract results on binarized images with long text are usually better than PaddleOCR.</li>
<li>Tesseract is far better at detecting symbols.</li>
<li>Tesseract is faster on CPU.</li>
</ol>
In short, using Tesseract would be perfect for scanned documents and PaddleOCR for general computer vision projects.

blocks|key|1637906|text|我使用Tesseract已经有一段时间了，但它的准确性很差，例如，数字4被识别为A，1作为]，8+as+&等等，|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1637907|现在我转向paddleOCR，它在使用良好的检测/分类和识别模型时具有很高的识别水平。|1637908|传递给Tesseract的相同图像与paddleOCR一起使用，它们被paddleOCR+100%25正确地识别。|1637909|使用方框使信息处理变得非常简单，我们也可以在Tesseract中使用框，但是是按单词为基础的，而不是像在paddleOCR中那样按短语基础，所以PaddleOCR在这一点上是非常简单的。|1637910|我对paddleOCR的结果非常满意，但在空间管理方面仍然存在一些小问题，有时一条线会因为一个额外的空间而分成两行。但我认为这可以在后处理阶段解决。|1637911|entityMap^0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|L|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|M|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|N|8|@]|9|@]|A|$]]|$1|F|3|G|5|6|7|O|8|@]|9|@]|A|$]]|$1|H|3|I|5|6|7|P|8|@]|9|@]|A|$]]|$1|J|3|-4|5|6|7|Q|8|@]|9|@]|A|$]]]|K|$]]

I have used Tesseract for a moment, but it suffers from accuracy, for example the number 4 is recognized as A, 1 as ], 8 as &amp; and so on,
Now i switch to paddleOCR, it has a great recognizing level when using the good detection/classification and recognition models.
the same images passed to Tesseract are used with paddleOCR, they are recognized correctly 100% by paddleOCR.
using boxes make very simple the information processing, we can use boxes also with Tesseract, but the are by word basis, not by phrase basis as in paddleOCR, so PaddleOCR is very simple in this point
I'm very happy about paddleOCR results, but still some little issues with spaces management, sometimes a line is splited in two lines because of an additional space. but i think this could be fixed in the post processing stage.

blocks|key|104834|text|最近，PaddleOCR更新了v3版本，英语空间问题得到了显著改善。我试了一下英语模型，效果很好。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|104835|在文档场景中，PaddleOCR可以实现95%25%2B的精确性。但在某些有节奏的角色上，特瑟乐可能会感到困惑。|104836|尤其是，PaddleOCR在一些非拉丁语言​​中的表现超出了我的想象。例如阿拉伯语，效果要比EasyOCR和Tesseract好得多。|104837|强烈推荐PaddleOCR！|104838|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|$]]

Recently PaddleOCR updated the v3 version, and the English space problem has been significantly improved. I tried the English model, it works very well.
In document scenarios, PaddleOCR can achieve 95%+ accuracy. But Tesseract may be confused on some rhythmic characters.
In particular, PaddleOCR's performance in some non-Latin languages ​​is beyond my imagination. For example Arabic, the effect is far better than EasyOCR and Tesseract
Highly recommend PaddleOCR！！！

I recently came across PaddleOCR and am wondering, how this OCR system compares to Tesseract. Is there any data or benchmarks available?

How does PaddleOCR performance compare to Tesseract?

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

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 

腾讯云代码助手

CODING DevOps

Cloud Studio

SDK中心

API中心

命令行工具

最近我遇到了PaddleOCR，我想知道这个OCR系统与Tesseract相比是怎样的。是否有可用的数据或基准？

问与Tesseract相比，PaddleOCR的性能如何？
EN

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

问与Tesseract相比，PaddleOCR的性能如何？EN