US 12,260,536 B2
Automatic image based object damage assessment
Christopher Campbell, South Shields (GB); Karl Hewitson, Tyne and Wear (GB); Karl Brown, Tyne and Wear (GB); Jon Wilson, Consett (GB); and Sam Warren, Salt Lake City, UT (US)
Assigned to Emergent Network Intelligence Ltd., Newcastle Tyne and Wear (GB)
Filed by Emergent Network Intelligence Ltd., Newcastle Tyne and Wear (GB)
Filed on Nov. 17, 2023, as Appl. No. 18/512,643.
Application 18/512,643 is a continuation of application No. 16/335,674, granted, now 11,823,365, previously published as PCT/GB2017/052729, filed on Sep. 15, 2017.
Claims priority of application No. 1616078 (EP), filed on Sep. 21, 2016.
Prior Publication US 2024/0087102 A1, Mar. 14, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/00 (2017.01); G06N 3/045 (2023.01); G06Q 10/10 (2023.01); G06Q 40/08 (2012.01)
CPC G06T 7/0002 (2013.01) [G06N 3/045 (2023.01); G06Q 10/10 (2013.01); G06Q 40/08 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30252 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A computer-based method for automatically evaluating validity and extent of at least one damaged object from image data, comprising the steps of:
(a) receiving image data comprising one or more images of at least one damaged object;
(b) processing said one or more images using an image alteration detection algorithm to detect fraudulent manipulation of said one or more images by classifying at least one attribute of said one or more images;
(c) removing any image comprising fraudulent manipulation from said one or more images;
(d) processing said one or more images using at least one machine learning algorithm to identify at least one of: a damaged object in any one of said one or more images a damaged area of said damaged object, and an extent of damage of said at least one damaged area; and
(e) generating a predictive analysis to repair and/or replace said at least one damaged object.