GENERATING AND UTILIZING NORMALIZED SCORES FOR CLASSIFYING DIGITAL OBJECTS

• US 20180012109A1
• Filed: 09/21/2017
• Published: 01/11/2018
• Est. Priority Date: 12/31/2015
• Status: Active Grant

• Current Assignee: Dropbox, Inc.
• Original Assignee: Dropbox, Inc.
• Inventors: Kriegman, David J., Belhumeur, Peter N., Berg, Thomas, Welinder, Nils Peter
• Granted Patent: US 10,255,527 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 18/2415 based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data

Abstract

The present disclosure is directed toward systems and methods that enable more accurate digital object classification. In particular, disclosed systems and methods address inaccuracies in digital object classification introduced by variations in classification scores. Specifically, in one or more embodiments, disclosed systems and methods generate probability functions utilizing digital test objects and transform classifications scores into normalized classification scores utilizing probability functions. Disclosed systems and methods utilize normalized classification scores to more accurately classify and identify digital objects in a variety of applications.

Claims

1. A method comprising:

generating, by at least one processor and utilizing a model trained to identify a known object based on a set of digital training images portraying the known object, a classification score with regard to an unknown object portrayed in a probe digital image, the classification score indicating a likelihood that the unknown object portrayed in the probe digital image corresponds to the known object portrayed in the set of digital training images;

using a probability function specific to the number of tagged digital training images in the set of digital training images to transform the classification score into a normalized classification score; and

determining, using the normalized classification score, whether the unknown object portrayed in the probe digital image corresponds to the known object portrayed in the set of digital training images.