ACCURATELY EXTRACTING INFORMATION USING MULTIPLE IMAGES

Patent №

US 8,890,978

Granted

2014-11-18

Filed 2012

Owner

INTUIT INC.

Lab

AI components

2

vision · planning

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

13431559

During an information-extraction technique, a user of the electronic device may be instructed by an application executed by an electronic device (such as a software application) to point an imaging sensor, which is integrated into the electronic device, toward a location on a document. For example, the user may be instructed to point a cellular-telephone camera toward a field on an invoice. After providing the instruction, the electronic device captures multiple images of the document by communicating a signal to the imaging device to acquire the images. Each of these images has an associated exposure setting with a different point of interest proximate to the location). Then, the electronic device stores the images and the points of interest. Furthermore, the electronic device analyzes the images to extract the information proximate to the location on the document.

VisionPlanningH04N 5/76G06V 10/141G06V 30/40

AI classification

Vision1.00
Planning1.00
AI hardware0.21
Knowledge representation0.14
Natural language0.03
Evolutionary computation0.00
Speech0.00
Machine learning0.00

Ownership

INTUIT INC.

assignment · 281210243

Assignors

MADHANI, SUNIL H., KAKKAR, SAMIR REVTI, SREEPATHY, ANU

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

© 2026 NYSGPT2525 LLC