Checkout Image Database for Unreadable Object Identifier Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional systems face inefficiencies and high overhead costs when machine-readable identifiers for physical objects are unavailable or unreadable, leading to prolonged checkout times and potential fraudulent activities, especially in high-volume environments.

Innovation Solution

A computer-implemented method and system that generates and utilizes an image database by capturing images of objects during the checkout process, allowing for image recognition when machine-readable identifiers are unavailable, thereby ensuring efficient object identification and reducing fraud.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual database generation is used to identify objects when machine-readable identifiers are unavailable, then object identification can be achieved, but overhead costs and time consumption increase significantly

Engineering Contradiction:

Improveobject identification capabilityVSAvoidcheckout time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system captures images of objects during the normal checkout process when machine-readable identifiers are successfully scanned, and pre-processes these images to create a database before they are needed. This preliminary action ensures that when an identifier is unavailable, the object can be quickly identified through image matching without manual intervention or time-consuming processing.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Instead of manually creating detailed object descriptions or specifications for the database, the system creates visual copies (images) of the objects during checkout. These image copies serve as the database entries, enabling rapid visual comparison and identification later without requiring manual data entry or complex object characterization.

Inventive Principle:

Principle #26Copying

2Reliability

If manual database generation is performed outside the checkout process, then a comprehensive image database can be created, but the system complexity and overhead costs increase

Engineering Contradiction:

Improvedatabase completenessVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The existing checkout system performs multiple functions: it scans machine-readable identifiers for pricing and tracking, captures images of objects, and builds an image database all in one process. This multi-functionality eliminates the need for separate database generation systems, reducing overall system complexity while ensuring comprehensive database coverage from real checkout scenarios.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The checkout system automatically captures images and builds the database without requiring separate manual intervention or dedicated database creation resources. The system serves itself by utilizing the existing checkout workflow to generate the image database, eliminating the need for additional staff or systems dedicated solely to database creation.

Inventive Principle:

Principle #25Self-service

3Device complexity

If no image database is maintained, then the system remains simple, but object identification cannot be performed when machine-readable identifiers are unreadable or fraudulent

Engineering Contradiction:

Improvesystem simplicityVSAvoidfraud detection capability

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system replaces reliance on machine-readable identifiers (barcodes, RFID tags) with an image-based recognition system. Instead of using mechanical/optical scanning of coded patterns, the system uses visual image matching to identify objects, providing fraud detection capability without requiring complex cryptographic verification systems.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10108880B2Systems and methods of object identification and database creation

Publication Date: 2018.10.23 WALMART APOLLO LLC

AI summary

Exemplary embodiments are generally directed to systems and methods of object identification. Exemplary embodiments can scan, by an optical reader, a machine-readable identifier associated with an original object. Exemplary embodiments can capture an image of the original object at a first orientation using an image capture device. Exemplary embodiments can transmit the machine-readable identifier and the image of the original object to an image database to store an association between the image of the original object and the machine-readable identifier. Exemplary embodiments can receive a subsequent object having a subsequent machine-readable identifier that is unavailable or incapable of being scanned. Exemplary embodiments can capture an image of the subsequent object with the image capture device. Exemplary embodiments can execute an image recognition function that outputs object identification information for the image of the subsequent object based on the machine-readable identifier associated with the image of the original object.