Invention Grant
- Patent Title: System and method for classifying image data
-
Application No.: US17130254Application Date: 2020-12-22
-
Publication No.: US11615166B2Publication Date: 2023-03-28
- Inventor: Arash Rahnama-Moghaddam , Andre Tai Nguyen
- Applicant: Booz Allen Hamilton Inc.
- Applicant Address: US VA McLean
- Assignee: Booz Allen Hamilton Inc.
- Current Assignee: Booz Allen Hamilton Inc.
- Current Assignee Address: US VA McLean
- Agency: Buchanan Ingersoll & Rooney PC
- Main IPC: G06F18/241
- IPC: G06F18/241 ; G06N3/08 ; G06N20/20 ; G06N20/10 ; G06V10/764 ; G06V10/82 ; G06N3/045

Abstract:
An exemplary device for classifying an image includes a receiving unit that receives image data. The device also includes a hardware processor including a neural network architecture to extract a plurality of features from the image data, filter each feature extracted from the image data, concatenate the plurality of filtered features to form an image vector, evaluate the plurality of concatenated features in first and second layers of a plurality of fully connected layers of the neural network architecture based on an amount of deviation in the features determined at each fully connected layer, and generate a data signal based on an output of the plurality of fully connected layers. A transmitting unit sends the data signal to a peripheral or remote device.
Public/Granted literature
- US20210133513A1 SYSTEM AND METHOD FOR CLASSIFYING IMAGE DATA Public/Granted day:2021-05-06
Information query