US 11,699,277 B2
Classification with segmentation neural network for image-based content capture
Sreelatha Reddy Samala, Los Altos, CA (US)
Assigned to OPEN TEXT SA ULC, Halifax (CA)
Filed by Open Text SA ULC, Halifax (CA)
Filed on Apr. 5, 2021, as Appl. No. 17/222,940.
Application 17/222,940 is a continuation of application No. 16/381,962, filed on Apr. 11, 2019, granted, now 10,977,524.
Prior Publication US 2021/0224577 A1, Jul. 22, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/00 (2017.01); G06V 10/26 (2022.01); G06T 5/20 (2006.01); G06T 7/11 (2017.01); G06F 18/2413 (2023.01); G06F 18/21 (2023.01); G06V 30/19 (2022.01); G06V 10/82 (2022.01); G06V 30/413 (2022.01)
CPC G06V 10/26 (2022.01) [G06F 18/2178 (2023.01); G06F 18/2413 (2023.01); G06T 5/20 (2013.01); G06T 7/11 (2017.01); G06V 10/82 (2022.01); G06V 30/1916 (2022.01); G06V 30/19173 (2022.01); G06V 30/413 (2022.01); G06T 2207/20036 (2013.01); G06T 2207/20081 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An image processing method, comprising:
receiving, by a computer, an input image;
detecting, by the computer utilizing a segmentation neural network, pixels in the input image having a particular feature type;
generating, by the computer based on the pixels in the input image having the particular feature type, a heatmap of the input image;
generating, by the computer from the heatmap, a morphed heatmap with contextual information on the pixels in the input image having the particular feature type;
detecting, by the computer, an object or region in the input image by masking the input image using the morphed heatmap; and
classifying, by the computer based at least on the object or region, the input image.