US 12,333,840 B2
Security-based image classification using artificial intelligence techniques
Franklin Jebadoss Mohandoss, Austin, TX (US); Bijan Kumar Mohanty, Austin, TX (US); and Ramesh Rajendra Rao, Bangalore (IN)
Assigned to Dell Products, L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Sep. 19, 2022, as Appl. No. 17/947,385.
Prior Publication US 2024/0096122 A1, Mar. 21, 2024
Int. Cl. G06V 10/82 (2022.01); G06F 40/284 (2020.01); G06V 30/148 (2022.01); G06V 30/19 (2022.01); G06V 30/413 (2022.01); G06V 30/416 (2022.01)
CPC G06V 30/19173 (2022.01) [G06V 10/82 (2022.01); G06V 30/148 (2022.01); G06V 30/19147 (2022.01); G06F 40/284 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining one or more images;
extracting text from at least a portion of the one or more images by processing the one or more images using at least a first set of one or more artificial intelligence techniques;
classifying at least one of the one or more images, into one or more of multiple security-based classification categories, by processing at least a portion of the extracted text using at least a second set of one or more artificial intelligence techniques, wherein classifying at least one of the one or more images comprises determining content of at least a portion of the extracted text using one or more natural language processing techniques, and classifying, using at least one artificial intelligence-based multi-class classification algorithm, the content into at least one of the multiple security-based classification categories at least in part by identifying at least one hyperplane that differentiates two or more of the multiple security-based classification categories in at least one n-dimensional space; and
performing one or more automated actions based at least in part on the classifying of the at least one of the one or more images, wherein performing one or more automated actions comprises augmenting the at least one image with classification-related metadata;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.