Stereo Camera User Verification for Hands-Free Transactions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems for conducting interactions at physical locations, such as purchases, often inaccurately select the wrong user account due to issues with facial recognition, leading to incorrect loyalty rewards and merchant system errors, requiring multiple corrections and causing burdensome processing.

Innovation Solution

Implementing a user verification device with a stereo camera to capture images and determine the user's location, recognizing motions indicative of a transaction, and using receipt data for accurate identification, allowing hands-free transactions and secure loyalty reward distribution.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If conventional facial recognition is used to identify users at physical locations, then user identification speed is improved, but identification accuracy deteriorates when multiple users are captured in the image

Engineering Contradiction:
Improveuser identification speedVSAvoididentification accuracy
Core Design Contradiction:
SpeedVSMeasurement precision

Solution Approach 1:

The patent segments the identification process into multiple independent verification stages: initial facial recognition to identify potential users, stereo camera-based location verification to determine which user is at the point of interaction, and motion analysis to confirm transactional intent. This segmentation allows each stage to focus on a specific aspect of identification, improving overall accuracy while maintaining speed.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces stereo camera location data and motion recognition data as intermediary verification layers between the initial facial recognition and final user identification. These intermediaries act as filters to eliminate false positives from multi-user scenarios, ensuring that only the actual transactor is identified without significantly slowing down the process.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If multiple verification steps are added to improve identification accuracy, then identification reliability is improved, but system complexity increases

Engineering Contradiction:
Improveidentification reliabilityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent makes the verification system multi-functional by using the stereo camera for both location determination and motion analysis, and by having the system perform multiple verification functions through integrated processing. This universality allows multiple verification steps to be implemented without proportionally increasing hardware complexity, as existing components serve multiple purposes in the verification chain.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Reliability

If accurate user identification is implemented to prevent wrong account access, then transaction security is improved, but processing time increases due to multiple verification steps

Engineering Contradiction:
Improvetransaction securityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by continuously capturing stereo camera data and analyzing user motions before the actual transaction occurs. The system pre-verify user location and intent, so that when identification is needed, the verification steps are already complete or can be quickly finalized, minimizing the time added to the actual transaction process.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11030640B2Providing hands-free data for interactions
Publication Date: 2021.06.08 GOOGLE LLC
  • US11030640B2 patent drawing
  • US11030640B2 patent drawing
  • US11030640B2 patent drawing

AI summary

A user verification system is configured to identify likely interactors approaching points of interaction to ensure accurate interactions and to provide loyalty rewards. In an example, a interaction system installs a user verification device with a stereo camera at an interacting device to capture images of the user and to obtain data from the device. The user verification device uses the stereo camera to determine the location of the user to determine if the user is a likely interactor. The user verification device recognizes motions of the user that are indicative of an interactor, such as reaching across the counter or looking at the operator. The user verification device identifies or verifies the interactor based on the record data or the display data. If the user is the likely interactor, then the system conducts a hands-free interaction with the user account or provides loyalty rewards to the user account.