Under-Resolved Barcode Decoding via Spatial Mapping and Iterative Module Value Determination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques struggle to decode under-resolved two-dimensional barcodes due to their exponentially larger possible solution set compared to one-dimensional symbols, and are ineffective in decoding large portions of multi-width one-dimensional barcodes without splitting into separate characters.
Innovation Solution
The development of alternative techniques that determine an initial set of modules in a barcode based on known aspects and mathematical relationships between the modules and pixels, allowing for the iterative determination of remaining module values to decode the symbol, including spatial mapping, causal relationships, and testing valid combinations of neighboring module values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing techniques are used to decode two-dimensional barcodes, then decoding can be performed under normal resolution conditions, but decoding fails when the symbol is under-resolved due to the exponentially larger possible solution set
Solution Approach 1:
The patent applies preliminary action by determining an initial set of module values before fully decoding the under-resolved symbol. This initial determination uses known aspects of the symbol structure and mathematical relationships between pixels and modules to establish a foundation that constrains the exponentially large solution space, making subsequent decoding feasible even when the symbol is captured at resolutions under one pixel per module
Solution Approach 2:
The patent changes parameters by iteratively refining module values based on feedback from pixel data. The system adjusts module values in iterations, using the initial set and pixel influences to progressively converge on the correct decoding, transforming the intractable exponential problem into a manageable iterative optimization process
2Measurement precision
If existing techniques are used to decode large portions of multi-width one-dimensional barcodes, then complete decoding can be achieved, but the process requires splitting the barcode into separate characters which increases complexity
Solution Approach 1:
The patent merges the decoding process by determining module values across large portions of multi-width barcodes without requiring splits into separate characters. The system treats extended portions of the barcode as a continuous structure, using spatial mapping and causal relationships between neighboring modules to decode across character boundaries, thereby reducing processing complexity while maintaining complete decoding accuracy
3Loss of information
If readers attempt to decode under-resolved barcodes with low sampling rates or blur, then more information can be recovered, but the decoding accuracy decreases due to poor focus and motion effects
Solution Approach 1:
The patent applies feedback by using pixel data to iteratively refine module value determinations. The system continuously compares predicted pixel values based on current module estimates with actual pixel measurements, using the discrepancy to adjust module values in subsequent iterations. This feedback mechanism enables accurate decoding of under-resolved symbols by compensating for information loss due to low sampling rates and blur
Solution Approach 2:
The system performs preliminary determination of an initial set of module values using known symbol aspects and mathematical relationships before iterative refinement. This preliminary structure provides a constrained starting point that prevents the iterative process from diverging even when input images are blurred or under-sampled, maintaining decoding accuracy despite poor focus or motion effects
Data Source
AI summary
The techniques described herein relate to methods, apparatus, and computer readable media configured to decode a symbol in a digital image. A digital image of a portion of a symbol is received, which includes a grid of pixels and the symbol includes a grid of modules. A spatial mapping is determined between a contiguous subset of modules in the grid of modules to the grid of pixels. Causal relationships are determined, using the spatial mapping, between each module and the grid of pixels. A set of valid combinations of values of neighboring modules in the contiguous subset of modules are tested against the grid of pixels using the causal relationships. A value of at least one module of the two or more neighboring modules is determined based on the tested set of valid combinations. The symbol is decoded based on the determined value of the at least one module.