Barcode Decoding Algorithms for Portable Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional barcode decoding methods on portable devices face challenges with images that are out of focus due to device movement or auto-focus issues, leading to poor decoding performance, especially with curved or distorted barcodes, and require significant processing capacity and bandwidth.
Innovation Solution
The development of robust algorithms that create and use two-dimensional templates for pattern matching, capable of handling variations in image quality and distortion, allowing for efficient decoding of barcodes like UPC-A, EAN-13, UPC-E, and EAN-8 formats on portable devices with minimal resources, and optional remote server analysis for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional barcode decoding algorithms are used on portable devices, then the device can decode barcodes, but the processing capacity and power consumption requirements are too high for small portable devices
Solution Approach 1:
The patent segments the barcode decoding process into distinct functional modules: image capture, preprocessing (grayscale conversion, blur detection), template generation, and pattern matching. This segmentation allows each module to be optimized independently, reducing overall processing requirements and power consumption while maintaining decoding accuracy.
Solution Approach 2:
The patent performs preliminary actions by pre-generating templates for various barcode formats and conditions (including blurred and curved variations) and storing them for quick comparison. This eliminates the need for complex real-time analysis during decoding, significantly reducing processing capacity and power requirements on portable devices.
2Productivity
If images are captured with device movement or auto-focus issues, then the capture process is faster and more practical, but the image quality becomes blurred leading to poor decoding performance
Solution Approach 1:
The patent converts the harmful effect of image blur into a benefit by generating and storing templates that explicitly account for blurred conditions. Instead of requiring perfectly focused images, the system creates templates that match blurred barcode patterns, allowing accurate decoding even when images are out of focus due to device movement or auto-focus issues.
Solution Approach 2:
The patent changes the parameter of template variety by generating templates across a range of blur levels and curve deviations. This allows the matching algorithm to find appropriate templates even when image quality varies, maintaining decoding accuracy without requiring precise focus control during capture.
3Reliability
If robust algorithms handling various image qualities are implemented, then decoding accuracy improves, but processing overhead increases
Solution Approach 1:
The patent uses copying by creating multiple template versions representing different barcode formats, blur levels, and curve deviations. Instead of implementing complex real-time image processing algorithms, the system copies and stores pre-computed templates that can be quickly matched against captured images, reducing algorithmic complexity while maintaining robustness.
Solution Approach 2:
The patent performs preliminary action by pre-generating comprehensive templates for various barcode conditions before runtime. This shifts the computational burden from runtime processing to offline template generation, reducing the complexity of algorithms executed on portable devices while ensuring accurate decoding across diverse image qualities.
4Reliability
If central server analysis is used for barcode decoding, then decoding accuracy can be maintained, but bandwidth requirements and upload time increase significantly
Solution Approach 1:
The patent enables self-service by implementing the complete barcode decoding functionality directly on portable devices. The device captures images, processes them through the template matching algorithm, and decodes barcodes locally without requiring server communication. This eliminates bandwidth consumption and upload time while maintaining decoding accuracy through the robust template matching approach.
Data Source
AI summary
Various algorithms are presented that enable an image of a machine-readable code, captured by a camera of an electronic device, to be decoded on the device without need to upload the image information to a server for processing. The algorithms can account for variations in focus of the image, as may result in blur due to move movement or auto-focus features. The approaches can handle multiple machine-readable code formats, and can handle machine-readable code on curved surfaces, machine-readable code with damaged areas, or machine-readable code that are otherwise uneven. Such algorithms are highly accurate while being fast and lightweight enough to execute on portable electronic devices, such as tablet computers and smart phones.