G2

Amar K.

Data Engineer II

Enterprise (> 1000 emp.)

6/30/2021

"Great library for accurate OCR"

4/5

What do you like best about Tesseract?

Tesseract is a great library for OCR, though there are different online and paid OCR libraries that do exist, that comes with a hefty cost, which is not affordable by the mid-scale organizations. The alternate is to look for a library that can work locally and is cost-efficient. Tesseracts serves both the purpose. it's cost efficient and most accurate. Review collected by and hosted on G2.com.

What do you dislike about Tesseract?

The processing time of tesseract is slow when processing high-resolution large images. This can be reduced by doing some kinds of pre-processing on the image, and also sometimes the tesseract does not give us accurate results. Tesseract should also support the native language. such as Hindi. etc. It is mostly optimized for English characters. Tesseract should enhance the support for multiple languages. Review collected by and hosted on G2.com.

What problems is Tesseract solving and how is that benefiting you?

We are trying to read a financial statement and try to extract the financial data from it. We have a custom algorithm written which extracts only the required field at certain image coordinates. Mostly the location of the text we want to extract would be fixed. We run the OCR and extract the data and store them in the Dataware housing solution, where we perform certain analytics on top of it. Review collected by and hosted on G2.com.