Embedded Optical Code Decoding on Curved Reflective Surfaces

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Optically readable codes embedded in the surfaces of objects, particularly on plant and animal products, are difficult to read due to distortions, reflections, and surface irregularities, making them challenging for consumers to decode using smartphones.

Innovation Solution

A method and system utilizing a trained machine learning model to perform transformations on images of optically readable codes, reducing distortions and reflections by learning from reference images to generate clearer, more readable codes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If optically readable codes are embedded in the surface of plant or animal products using a laser, then the codes are more difficult to remove and replace (increased reliability), but the contrast with the surrounding tissue is lower making them more difficult to read (worsened readability)

Engineering Contradiction:
Improvecode permanenceVSAvoidcode readability
Core Design Contradiction:
ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent applies preliminary image processing transformations to the captured image before decoding. The system pre-processes the image by correcting distortions, reducing reflections, and enhancing contrast specific to the object type (fruit, vegetable, meat, etc.). This preliminary action compensates for the low contrast inherent in embedded codes, making them readable without sacrificing their permanent embedded nature.

Inventive Principle:
Principle #10Preliminary action

2Ease of manufacture

If optically readable codes are applied to curved surfaces using a laser, then direct marking without stickers is achieved (resource conservation), but the codes become distorted making them difficult to read

Engineering Contradiction:
Improvemarking processVSAvoidcode distortion
Core Design Contradiction:
Ease of manufactureVSDifficulty of detecting and measuring

Solution Approach 1:

The patent changes the parameters of the captured image through various transformations including geometric corrections, contrast adjustments, and reflection reductions. These parameter changes adapt the distorted image data to a state suitable for decoding, effectively compensating for the curvature-induced distortions while maintaining the simplicity of direct laser marking.

Inventive Principle:
Principle #35Parameter changes

3Ease of manufacture

If optically readable codes are applied to smooth surfaces, then direct marking is achieved (resource conservation), but reflections from ambient light occur during reading complicating the process

Engineering Contradiction:
Improvemarking processVSAvoidlight reflections
Core Design Contradiction:
Ease of manufactureVSObject-affected harmful factors

Solution Approach 1:

The patent converts the harmful effect of reflections into a manageable parameter by detecting and correcting reflection patterns in the captured image. The image processing system identifies reflection artifacts and applies transformations to remove or reduce their impact, effectively converting the harmful reflection effect into a correctable image characteristic that does not prevent decoding.

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

Data Source

PatentEP4202856B1Reading of optically readable codes
Publication Date: 2026.01.28 BAYER AG
  • EP4202856B1 patent drawingFigure 1(a)~1(d)
  • EP4202856B1 patent drawingFigure 2
  • EP4202856B1 patent drawingFigure 3

AI summary

The present invention relates to the technical field of marking objects with optically readable codes and reading (decoding) these codes. The invention comprises a method, a system, and a computer program for decoding optically readable codes embedded in the surfaces of objects.