IMAGE CLASSIFICATION UTILIZING SEMANTIC RELATIONSHIPS IN A CLASSIFICATION HIERARCHY

Patent №

US 10,102,454

Granted

2018-10-16

Filed 2017

Owner

INTERNATIONAL BUSINESS MACHINES CORPORATION

AI components

5

ml · nlp · vision · kr · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

15813401

A method includes utilizing two or more classifiers to calculate, for an input image, probability scores for a plurality of classes based on visual information extracted from the input image and semantic relationships in a classification hierarchy, wherein each of the two or more classifiers is associated with a given one of two or more levels in the classification hierarchy with each level in the classification hierarchy comprising a subset of the plurality of classes, and classifying the input image based on the calculated probability scores.

Machine learningNatural languageVisionKnowledge representationAI hardwareG06N 3/08G06V 10/82G06F 18/241G06F 18/2415G06F 18/2431G06F 18/24323G06F 18/245G06N 3/045+11 more

AI classification

Vision1.00
Machine learning1.00
AI hardware1.00
Natural language1.00
Knowledge representation1.00
Planning0.00
Speech0.00
Evolutionary computation0.00

Ownership

INTERNATIONAL BUSINESS MACHINES CORPORATION

assignment · 441320580

Assignors

MERLER, MICHELE, SMITH, JOHN R., UCEDA-SOSA, ROSARIO A., WU, HUI

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC