ocr used to extract text from image by mobile camera? [closed]

Closed. This question is opinion-based. It is not currently accepting answers.

---

Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.

Closed 6 years ago.

Improve this question

What is the best OCR algorithm 开发者_如何学Cused to extract text from an image taken with a mobile camera?

---

That depends on your application requirements.

Usually OCR engine can only return characters, font, word, line or region information. You need add many other modules and tune them to get the best results.

First, image preprocessing is necessary for camera OCR application. Background, noise removal, binarization, resize ... should be added to clean image as possible as you can.

Secondly, you need locate the text region. The algorithm not only depends on image features but also on your OCR objective. For example, if you need to OCR plate number, you can use the plate number's length, width or height for more accurate location.

After OCR, you can add some post processing to correct some OCR errors. Common OCR engines such as Abyy, ExperVision, Omnipage, GOCR, Tesseract are all trained according to common documents, magazine or office paper. If your documents are special, you can establish your high-level data extraction or analysis logic over OCR layer.

---

You can try the OCR API at http://www.wisetrend.com/wisetrend_ocr_cloud.shtml - it's a REST API that should be very simple to use from any mobile platform, and it's based on the ABBYY OCR engine which is great for low-quality images such as those from mobile phone cameras. Disclaimer: WiseTrend is my company's customer.