Hi!
I remember we could check whether the result of recognition was suspicious or not for each character.
And I am wondering if we could do the same thing using RTR SDK.
Thank you,
Hi!
I remember we could check whether the result of recognition was suspicious or not for each character.
And I am wondering if we could do the same thing using RTR SDK.
Thank you,
0 out of 0 found this helpful
Comments
2 comments
The basic technologies are different in ABBYY Real-Time Recognition SDK (RTR SDK) and in other our products. RTR SDK is a software development kit which provides a technology to recognize text directly in smartphone camera preview stream without snapping a photo.
The RTR SDK processes recognize the text of several frames in parallel on the available CPUs. Then the recognition results are merged in order to eliminate random recognition errors and get higher accuracy. RTR SDK does not returns the information about recognition confidence or suspiciousness for separate recognized characters, but you can obtain the result stability status for all extracted text. The result stability status is an estimate of how stable the result is, and whether it is likely to be improved by adding new frames. Please find more information about the RTRResultStabilityStatus enumeration and its constants in the Help file (RtrSdkDevelopersGuide.pdf).
This feature (the suspicious characters markup) is available in RTR with the extended license for single shot images recognition through CoreAPI.
Hi Oksana,
Understood, thank you for your quick response!
Best regards,
Please sign in to leave a comment.