US 11,659,104 B2
Generation of an electronic document capable of receiving user input
Maanusri Balasubramanian, Chennai (IN); and Arjun Ashok Kumar, Coimbatore (IN)
Filed by Citrix Systems, Inc., Fort Lauderdale, FL (US)
Filed on Dec. 28, 2020, as Appl. No. 17/134,841.
Prior Publication US 2022/0210280 A1, Jun. 30, 2022
Int. Cl. H04N 1/00 (2006.01); G06V 20/20 (2022.01); G06V 10/22 (2022.01); G06V 30/412 (2022.01); G06K 9/62 (2022.01); H04N 7/18 (2006.01)
CPC H04N 1/00251 (2013.01) [G06K 9/6256 (2013.01); G06V 10/235 (2022.01); G06V 20/20 (2022.01); G06V 30/412 (2022.01); H04N 7/188 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
receiving an image of a document from an image capture device, the image being in a format of an image file;
detecting at least one location of a user input field within the image based on patterns detected in a set of other images, the set of other images being annotated to identify locations of user input fields within individual images of the set;
determining coordinates for the at least one location; and
generating an electronic document based on the received image, the generation of the electronic document including addition of a software user input component at the location within the image with use of the determined coordinates, wherein the software user input component is configured to receive input from a user in electronic form;
wherein the set of other images comprises a set of annotated training images, wherein at least one annotated training image includes a training document image and annotations indicating locations of user input fields within the training document image, and further comprising:
using the set of annotated training images to train a field detection model to detect locations of user input fields within images based on patterns detected in the set of annotated training images.