We need to extract the registration data from a registration form. now we have trained the FlexiCapture how to extract the data from the registration form, by uploading around 30 registration forms. but in our case the documents that will be processed by the FlexiCapure , might contain random pages and one registration form.
So if we trained the FlexCapture to extract data from the registration forms, and then we upload a pdf file which contain let say 10 pages and the registration form is on N pages (where N can be any number from 1 to 10),, then will FlexiCapture be able to know the registration form and differentiate it from random documents? and extract the data accordingly?
Thanks in advance for any help.
Sort of. Keep in mind there are 2 type of training. Extraction training and Classification training. So if you just build an extraction training project, it would build rules to capture the data based on the sample you provided. So if you load other document type in, it will still run those same logic. So any document you load in the system will run those logic, which means it could accidently capture something because a page might be similar to those trained document. Now if you also add classification, it will only run those training on the class you trained it on.
Please sign in to leave a comment.