在 Android 上使用 Google Docs OCR 进行其他操作
我正在考虑使用我的 Android 手机从文档中捕获一些文本，并且正在寻找 Android 上理想的 OCR 应用程序。我今天偶然读到 Google 引入了 OCR 来扫描可以在 Google Docs 中编辑的文档。我想知道除了将文档转换为 Google 文档之外，我是否还可以使用 OCR 做其他事情 - 例如，拍摄证书照片并捕获候选人的姓名和出生日期，或者拍摄车牌照片并进行识别。能够以可存储的文本形式获取信息。
如果有人知道如何使用 Google 的 OCR 在 Android 上实现此目的，那就太好了。我确实读过有关 Tesseract/Tesjeract 的内容，但似乎很难使用它来实现我想要的东西 - 也许我没有完全理解如何通过 Java 使用它。以下是使用 OCR 扫描文档的新应用程序的链接 - Google Android 上的文档
I am thinking of capturing some text from documents using my android phone and was looking for an ideal OCR app on android. I just happened to read today that Google introduced OCR for scanning documents that can be edited in Google Docs. I was wondering if I could use the OCR for things other than converting the documents to Google Docs - say, like taking a picture of a certificate and capturing the names and dates of birth of the candidates or taking a photo of a license plate and be able to get the info as text that can be stored.
If anyone has an idea of how to achieve this on Android using Google's OCR, that would be great to know. I did read about Tesseract/Tesjeract but it seems very difficult to implement what I want using it - maybe I didnt fully understand how to use it through Java. Here's the link to the new app that uses OCR to scan documents - Google Docs on Android
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论
评论（2）
我们前段时间尝试过Google Docs API，但它的准确性非常差。看起来它是基于某些过时版本的超正方体。我想如果您尝试使用超正方体，您会获得更高的准确性。但是，您需要对相机拍摄的图像进行特殊预处理，因为它们会带来额外的挑战。 Google Docs API 没有这个功能。
在 Android 上运行 Tesseract 请看这里：
在 android 上使用 tesseract
在手机上进行 OCR 的 tesseract 的商业替代方案：
http://www.abbyy.com/mobileocr/
但是，如果您不仅仅考虑捕获文本，还提取数据，那么您可能需要额外的技术来解析文本输出。这意味着编写更多的代码。或者可以选择从 ABBYY 获取现有商业数据捕获 API 的许可。这已经在这里讨论过：
使用 Iphone 识别特定位置的文本相机
免责声明：我为 ABBYY 工作
We have tried Google Docs API a wile ago, but it is very weak in terms of accuracy. Looks like it is based on some outdated version of tesseract. I suppose you would get more accuracy if you try tesseract. However, you will need to manage special preprocessing of images taken by camera since they introduce additional challenges. Google Docs API does not have that.
On running Tesseract on Android look here:
Using tesseract on android
Commertial alternative to tesseract for OCR on mobile phone:
http://www.abbyy.com/mobileocr/
However, if you are looking not into just capturing text, but also exptracting data, then you may need additional technology to parse text output. That means writing even more code. Or there is alternative to license existing commertial Data Capture API from ABBYY. That was already discussed here:
Recognise text in certain position using the Iphone camera
Disclaimer: I work for ABBYY
您可以使用 Google 文档（现在称为 Google 云端硬盘）通过将图像上传到 Google 云端硬盘来对图像进行 OCR。稍后您可以将此 Google 文档作为 text/rtf/doc/html 文件拉回。现在，您可以在应用程序中随意使用这些数据。这可以使用 Google Drive API 直接实现，无需用户干预。以下是一些 Google App API 参考：
要使用 OCR 上传：请参阅
无法将图片文件上传到 Google通过 java api 与 ?convert=true
进行文档
要从 Google 云端硬盘下载文件：
https://developers.google.com/google-apps/documents-list /#downloading_documents_and_files
https://docs.google.com/feeds/download/documents/Export?docID=__INSERT-ID__&exportFormat=txt&format=txt请注意，使用 OCR 应该有配额服务。
You can use Google Docs (now called Google Drive) to OCR an image by uploading the image to Google Drive. Later you can pull this Google Document back as a text/rtf/doc/html file. This data now - you may use however you like in your app. This can be achieved directly without user intervention using Google Drive APIs. Here are some Google App API references:
To upload with OCR: see
Fail to upload a image file into Google Doc via java api with ?convert=true
To download a file from Google Drive:
https://developers.google.com/google-apps/documents-list/#downloading_documents_and_files
https://docs.google.com/feeds/download/documents/Export?docID=__INSERT-ID__&exportFormat=txt&format=txtBeware there should be a quota in place to use the OCR service.