AR Recognition of Printed 2D Objects Using Security Features

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing augmented reality systems struggle to effectively recognize and enhance two-dimensional real-world objects without relying on specialized markers or barcodes, particularly in scenarios where security features vary by viewing angle, leading to inconsistent recognition and limited interaction possibilities.

Innovation Solution

A system that uses visible security features and pattern recognition techniques, combined with machine learning, to identify two-dimensional objects and superimpose interactive virtual content, while accounting for varying security features and viewing angles, without requiring specialized markers or barcodes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional electronic advertisements are used, then advertising delivery is simple, but user attention and engagement are low

Engineering Contradiction:

Improveuser attentionVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces an augmented reality system as an intermediary between traditional advertisements and users. The AR system captures images of products in the real world and superimposes virtual advertisement content, creating an intermediate layer that enhances user engagement while delivering advertising messages. This resolves the contradiction by maintaining simple advertisement delivery through the AR intermediary while significantly improving user attention through immersive visual overlays.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If augmented reality superimposes advertisements over product images, then user attention increases, but recognition accuracy decreases due to varying security features and viewing angles

Engineering Contradiction:

Improveuser attentionVSAvoidobject recognition accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent implements dynamic image recognition that adapts to varying viewing angles and lighting conditions. The system uses machine learning models that are trained to recognize products from multiple perspectives and under different lighting conditions. This dynamic adaptation allows the system to maintain high recognition accuracy even when security features appear differently due to viewing angle changes, thereby resolving the contradiction between maintaining user attention through AR and ensuring accurate product recognition.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes recognition parameters dynamically based on detected viewing angles and lighting conditions. When a product is detected at an unusual angle or under poor lighting, the system adjusts recognition thresholds and parameters to compensate. This parameter adaptation enables the system to maintain accurate product identification despite variations in how security features appear, resolving the contradiction between AR engagement and recognition precision.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If AR systems use specialized markers or barcodes for recognition, then recognition accuracy improves, but ease of operation deteriorates due to requirement for specific markers

Engineering Contradiction:

Improverecognition accuracyVSAvoiduser convenience

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent extracts the recognition function from specialized markers and barcodes, enabling direct recognition of product images themselves. The system uses machine learning to identify products based on their visual appearance without requiring additional marker elements. This extraction resolves the contradiction by maintaining accurate recognition through advanced image processing while eliminating the need for specialized markers, thereby improving user convenience.

Inventive Principle:

Principle #2Taking out (Extraction)

4Reliability

If machine learning is used for pattern recognition, then recognition robustness improves, but processing time increases

Engineering Contradiction:

Improverecognition robustnessVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent implements preliminary action by pre-training machine learning models with extensive product images and security feature variations before deployment. The models are pre-processed and optimized so that during actual operation, they can quickly match captured images against known products without requiring extensive real-time computation. This preliminary preparation resolves the contradiction by establishing robust recognition capabilities in advance, enabling fast processing during actual use.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12555137B2Augmented reality content selection and display based on printed two-dimensional objects

Publication Date: 2026.02.17 TECHINVEST CO LTD

AI summary

Systems, methods and techniques for automatically recognizing two-dimensional real world objects with an augmented reality display device, and augmenting or enhancing the display of such real world objects by superimposing virtual images such as a still or video advertisement, a story or other virtual image presentation. In non-limiting embodiments, the real world object includes visible features including visible security features and a recognition process takes the visible security features into account when recognizing the object and/or displaying superimposed virtual images.