- Patent Title: Shape-biased image classification using deep convolutional networks
-
Application No.: US17197678Application Date: 2021-03-10
-
Publication No.: US11893086B2Publication Date: 2024-02-06
- Inventor: Dan Levi , Noa Garnett , Roy Uziel
- Applicant: GM GLOBAL TECHNOLOGY OPERATIONS LLC
- Applicant Address: US MI Detroit
- Assignee: GM GLOBAL TECHNOLOGY OPERATIONS LLC
- Current Assignee: GM GLOBAL TECHNOLOGY OPERATIONS LLC
- Current Assignee Address: US MI Detroit
- Agency: CANTOR COLBURN LLP
- Main IPC: G06F18/00
- IPC: G06F18/00 ; G06F18/241 ; G06N3/08 ; G06V20/56 ; G06F18/214

Abstract:
A system for analyzing images includes a processing device includes a receiving module configured to receive an image, and an analysis module configured to apply the received image to a machine learning network and classify one or more features in the received image, the machine learning network configured to propagate image data through a plurality of convolutional layers, each convolutional layer of the plurality of convolutional layers including a plurality of filter channels, the machine learning network including a bottleneck layer configured to recognize an image feature based on a shape of an image component, The system also includes an output module configured to output characterization data that includes a classification of the one or more features.
Public/Granted literature
- US20220292316A1 SHAPE-BIASED IMAGE CLASSIFICATION USING DEEP CONVOLUTIONAL NETWORKS Public/Granted day:2022-09-15
Information query