Adaptive Thresholding for Portable Document Imagery Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional document readers are expensive and bulky, making them unsuitable for low-cost, lightweight applications in detecting and analyzing machine-readable documents.

Innovation Solution

A portable document reader apparatus that includes an image data acquisition means, an image data conversion means, and an adaptive thresholding means to detect and analyze imagery within a machine-readable zone, utilizing an imager, aimer, lens, processor, and adaptive thresholding algorithm to convert grayscale images into bi-tonal frames for enhanced binary contrast.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional document readers are used to capture and scan machine-readable documents, then detection and analysis functionality is achieved, but the device becomes expensive and bulky

Engineering Contradiction:
Improvedetection and analysis functionalityVSAvoiddevice weight and size
Core Design Contradiction:
ReliabilityVSWeight of stationary object

Solution Approach 1:

The conventional document reader is divided into three functional segments: image data acquisition means (imager), image data conversion means (processor performing grayscale conversion), and adaptive thresholding means (processor performing binary conversion). This segmentation allows each component to be optimized independently, enabling the system to achieve full document reading functionality while using lighter, more compact components than a traditional integrated document reader.

Inventive Principle:
Principle #1Segmentation

2Reliability

If conventional document readers are used to capture and scan machine-readable documents, then detection and analysis functionality is achieved, but the device becomes expensive

Engineering Contradiction:
Improvedetection and analysis functionalityVSAvoiddevice cost
Core Design Contradiction:
ReliabilityVSEase of manufacture

Solution Approach 1:

The patent replaces complex mechanical document reader systems with a streamlined digital processing system. Instead of using traditional mechanical scanners and readers, the invention uses an imager to capture image data, which is then processed through grayscale conversion and adaptive thresholding algorithms to extract machine-readable information. This substitution of mechanical systems with digital processing reduces manufacturing costs while maintaining detection and analysis functionality.

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

3Measurement precision

If grayscale image conversion is performed followed by adaptive thresholding, then binary contrast is enhanced for machine-readable data detection, but processing complexity increases

Engineering Contradiction:
Improvebinary contrast enhancementVSAvoidprocessing algorithm complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies parameter changes through a two-stage processing approach: first converting image data to grayscale (changing the luminance parameter representation), then applying adaptive thresholding (changing the intensity parameter to binary values). This systematic parameter transformation enhances the contrast of machine-readable data by progressively simplifying the image data from full grayscale to binary, making the detection process more precise while keeping the processing steps methodical and manageable.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS7813547B1Apparatus and method for detection and analysis of imagery
Publication Date: 2010.10.12 UNISYS CORP
  • US7813547B1 patent drawing
  • US7813547B1 patent drawing
  • US7813547B1 patent drawing

AI summary

An apparatus and method for detecting and analyzing imagery, wherein the apparatus includes an image data acquisition means, an image data conversion means, and an adaptive thresholding means. The image data acquisition means acquires image data from a document. The acquired image data is converted into a grayscale image frame by the image data conversion means. In addition, the adaptive thresholding means converts the grayscale image frame into a bi-tonal frame.