Loading patent…
AssigneeWalmart Apollo, LLC
InventorsRamanujam Ramaswamy Srinivasa, Pranav Aggarwal
Estimating the term…
This application related to automatic processes for identifying and extracting information from images of documents of varying layouts. For example, a computing device may receive an image of a document, where the image includes a plurality of color channels. The computing device applies a character recognition process to the image to generate optical character recognition data. Further, the computing device determines an area of the image that includes one or more characters based on the optical character recognition data. The computing device adjusts a value of each of a plurality of pixels corresponding to the area of the image determined for each character based on a value of each corresponding character to generate a modified image. The computing device then applies a trained machine learning process to the modified image to generate output data. The output data characterizes characters, such as words and number values, within the original image.
A system comprising:
A method comprising:
A non-transitory computer readable medium having instructions stored thereon, wherein the instructions, when executed by at least one processor, cause a device to perform operations comprising:
Dependencies are inferred from the claim text.