Sparse Path Code Decoding With Start-Code Detection and Error Correction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing sparse path codes lack effective methods for accurately locating start codes and do not provide error correction or efficient encoding strategies for payload data, leading to potential misreading and ambiguity in decoding.

Innovation Solution

Implementing improved methods for locating start codes using Laplacian filters and convolutional neural networks, employing error-correcting codes like Hamming and BCH codes, and utilizing convolutional neural networks for accurate detection and decoding of sparse path codes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If sparse path codes are used to encode payload data, then data representation capability is improved, but methods for accurately locating start codes and error correction are lacking

Engineering Contradiction:

Improvepayload data representationVSAvoidcode detection accuracy

Core Design Contradiction:

Loss of informationVSReliability

Solution Approach 1:

The patent applies Laplacian filters and convolutional neural networks to pre-process and locate start codes before decoding the payload data. This preliminary action of enhancing start code detection ensures accurate positioning and synchronization, preventing misreading of the sparse path code structure and enabling reliable payload extraction.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements error-correcting codes (Hamming and BCH codes) that provide feedback mechanisms for detecting and correcting errors in the decoded payload data. This feedback system compares expected code structures with actual readings, identifies discrepancies, and corrects errors to ensure accurate data recovery even in noisy conditions.

Inventive Principle:

Principle #23Feedback

2Reliability

If error-correcting codes are implemented, then decoding reliability is improved, but code complexity increases

Engineering Contradiction:

Improvedecoding accuracyVSAvoidencoding and decoding complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent employs established error-correcting code schemes (Hamming and BCH codes) with predefined parameters and structures. By utilizing these standardized codes with known complexity characteristics, the system achieves reliable error correction without requiring custom complex algorithms, thus balancing reliability improvement with manageable implementation complexity.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If convolutional neural networks are used for detection, then detection accuracy is improved, but computational requirements increase

Engineering Contradiction:

Improvestart code location accuracyVSAvoidcomputational energy consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent uses convolutional neural networks to pre-detect and locate start codes before full payload decoding. This preliminary detection step using CNNs achieves high positioning accuracy with relatively low computational cost compared to full-image processing, enabling efficient resource utilization by focusing computational power only on critical start code identification.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12525991B1Sparse path codes and methods

Publication Date: 2026.01.13 DIGIMARC CORP

AI summary

A series of marks and absences of marks (voids) arrayed along one or a few mathematically-defined paths, define a message-conveying sparse path code. Multiple improvements in the forms of such codes, and related encoding and reading techniques, are detailed. Some such improvements provide greatly increased robustness and decreased visibility. A variety of other features and arrangements are also detailed.