Polygonal Boundary Definition for Image Objects

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for identifying image object boundaries in digital images are time-consuming and computationally inefficient, limiting the use of 2D image element hot linking in various applications.

Innovation Solution

A system and method that starts with a known point in an image object, identifies adjacent pixels sharing a characteristic like color, builds a list of boundary pixels, and recursively adds contiguous region boundaries to define a polygon, with optional reduction of the list to simplify the boundary representation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual boundary identification is used, then boundary definition accuracy is achieved, but time consumption increases significantly

Engineering Contradiction:
Improveboundary definition accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical boundary identification with an automated computer-based system that uses image processing algorithms to automatically detect and define object boundaries, eliminating the need for manual pixel-by-pixel analysis while maintaining accuracy

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

Solution Approach 2:

The system enables self-service boundary identification by automatically analyzing image data, detecting edges, and generating boundary definitions without human intervention, allowing the computer to perform the task independently and efficiently

Inventive Principle:
Principle #25Self-service

2Measurement precision

If complex algorithms are used for boundary identification, then boundary accuracy is improved, but computational efficiency deteriorates

Engineering Contradiction:
Improveboundary identification accuracyVSAvoidcomputational efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent segments the boundary identification process into distinct computational stages including edge detection, boundary tracing, and polygon approximation, allowing each stage to be optimized independently and processed efficiently rather than using a single complex algorithm

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system uses simplified boundary representation models that approximate complex boundaries with polygons of limited precision, sacrificing minimal accuracy for significant gains in computational speed and ease of processing

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

3Measurement precision

If detailed boundary pixel lists are maintained, then boundary precision is preserved, but data storage and processing requirements increase

Engineering Contradiction:
Improveboundary precisionVSAvoiddata storage requirements
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential boundary-defining pixels from the complete set of boundary pixels, removing redundant intermediate pixels that do not contribute to the final boundary definition, thereby reducing data storage requirements while preserving boundary accuracy

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system dynamically adjusts the level of boundary detail based on application requirements, allowing the boundary representation to be simplified or refined as needed rather than maintaining fixed high-detail pixel lists for all cases

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS7734099B2Method and system for generating polygonal boundary definitions for image objects
Publication Date: 2010.06.08 BUNKER HILL TECHNOLOGIES LLC
  • US7734099B2 patent drawing
  • US7734099B2 patent drawing
  • US7734099B2 patent drawing

AI summary

Image objects within two-dimensional images are identified by locating boundary points that describe line segments that define a polygon outlining each object. Processing follows lines of pixels between boundary points to determine whether additional pixels are a part of the same image object by reference to a discriminator, such as color. Boundary points are thus identified for contiguous pixels and contiguous lines. Arm-like regions are identified by recursive analysis in a similar manner. The resulting boundary point list may serve to identify the image object, such as for labeling or tagging in web-based manuals, catalogs, and so forth.