Vision Testing Augmented With Imperceivable Band Signaling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual testing of display systems is time-consuming and labor-intensive, and current automated systems, such as optical character recognition, often fail to accurately differentiate between text and symbology, leading to false positives and inefficiencies.

Innovation Solution

A test system that uses a camera to record both visually perceivable and imperceivable images from a display, with a controller employing artificial intelligence and computer vision models to analyze the imperceivable data and guide the analysis of perceivable data, determining compliance and reporting a compliance score based on deviations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual testing is used to observe and grade display systems, then testing accuracy can be maintained, but testing time and labor costs increase significantly

Engineering Contradiction:
Improvetesting accuracyVSAvoidtesting time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual visual inspection with an automated optical testing system that uses cameras to capture display output and AI algorithms to analyze the captured images. This substitution of mechanical/physical inspection with automated optical-digital processing maintains measurement precision while dramatically reducing testing time and labor requirements.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary AI-based image analysis system between the display output and the testing evaluation. This intermediary processes the visual output through computer vision algorithms, enabling automated decision-making while preserving the accuracy that would otherwise require human expertise.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If optical character recognition is used to automate display testing, then testing speed increases, but false positives increase due to inability to differentiate text from symbology

Engineering Contradiction:
Improvetesting speedVSAvoidfalse positive rate
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent changes the analysis parameters from simple character recognition patterns to multi-parameter visual feature analysis including text characteristics, symbology patterns, spatial relationships, and contextual information. This parameter expansion enables the system to distinguish between text and symbology, maintaining high testing speed while eliminating false positives.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent segments the display content analysis into multiple distinct processing streams: one for text detection, another for symbology recognition, and additional streams for contextual analysis. This segmentation allows each stream to specialize in specific features, improving both speed and accuracy while reducing false positives through cross-validation.

Inventive Principle:
Principle #1Segmentation

3Device complexity

If visible band imaging only is used for display testing, then system simplicity is maintained, but detection capability is limited to visible content

Engineering Contradiction:
Improvesystem simplicityVSAvoiddetection capability
Core Design Contradiction:
Device complexityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent extends the detection dimension from visible light spectrum to include infrared and ultraviolet bands. By adding these spectral dimensions, the system can detect imperceivable images and out-of-band signaling without significantly increasing overall system complexity, as the same camera hardware can capture multiple spectral ranges.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent makes the imaging system universal by enabling it to capture both visible and imperceivable content using the same hardware platform. This multi-functionality allows a single camera system to perform both traditional visible content testing and advanced imperceivable image detection, eliminating the need for separate specialized systems.

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

Data Source

PatentEP4250244A1Vision based testing augmented with out of visible band signaling
Publication Date: 2023.09.27 ROCKWELL COLLINS INC
  • EP4250244A1 patent drawingFigure 1
  • EP4250244A1 patent drawingFigure 2
  • EP4250244A1 patent drawingFigure 2

AI summary

A system and method for determining a compliance of a display (90) to a reference is disclosed. The system includes a camera (104) configured to record images from a display (90), wherein the display (90) is configured to simultaneously display a visually perceivable image and a visually imperceivable image based on an input signal. The test system further includes a controller (116) with processors (140) and a memory (136). The memory (136) has instructions stored upon that instruct the processors (140) to receive the display signal, generate imperceivable image data and perceivable image data based on the display signal, use the imperceivable image data to guide an analysis of the perceivable image data, and determine a compliance score of the display based on a deviation between the perceivable image data and perceivable input of the input signal. The imperceivable image may be a UV image, an infrared image, or an image based on an imperceivable frame rate.