Team,
I have some Video KYC recordings from which I need to extract data. The document appears at various points while the video is playing, and I need to capture its details.
Can Automation Anywhere extract data from a video in such a scenario?
Note: The document may be visible at any time during the video.
Kindly comment your inputs here
Hi
Please find the below,
Vision models or computer vision models are a type of artificial intelligence (AI) that are specifically designed to process, understand, and interpret data such as document layout, recognizing tables, form fields, images, graphics, and barcodes.
https://docs.automationanywhere.com/bundle/enterprise-v2019/page/data-extraction-vision-models.html
Use OpenCV within a Python script to extract frames. You can call this script from an Automation Anywhere bot.
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.