Hybrid Intensity Mapping for Digital Image Normalization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing digital-image processing methods face challenges in normalizing intensities between images to accurately detect meaningful changes, as systematic intensity variations and noise can obscure subtle differences, making it difficult to extract relevant information from comparisons.

Innovation Solution

The implementation of a genetic optimization approach to determine and refine model parameters for a hybrid intensity mapping that adjusts intensities in one image to match those in another, using a mapping model that combines both calculated and directly compared intensity mappings, thereby reducing systematic variations while preserving meaningful differences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If intensity normalization is applied to reduce systematic variations between images, then measurement precision of intensity differences is improved, but device complexity increases due to the need for mapping models and optimization algorithms

Engineering Contradiction:

Improveprecision of intensity difference detectionVSAvoidcomplexity of normalization system

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent transforms the complex normalization problem into a parameter optimization problem by representing intensity mappings through adjustable parameters in a mapping model. Genetic algorithms are used to optimize these parameters, converting a complex image processing task into a parameter search problem that can be systematically solved.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces traditional mechanical/image-processing approaches with computational methods. Instead of direct pixel manipulation, the system uses genetic algorithms and mapping models to achieve normalization, substituting physical image processing with mathematical and computational techniques.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If genetic optimization is used to refine mapping model parameters, then manufacturing precision of intensity mapping is improved, but loss of time increases due to iterative optimization processes

Engineering Contradiction:

Improveprecision of intensity mappingVSAvoidtime for parameter optimization

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by initializing mapping model parameters before the main optimization process. The genetic algorithm starts with an initial population of parameter sets, and the system pre-processes image data to prepare for efficient optimization, reducing the overall time required for achieving precise mappings.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The optimization process maintains continuity by iteratively refining parameters across generations without interrupting the search for optimal mappings. The genetic algorithm continuously evolves parameter sets, maintaining useful computational actions throughout the optimization process rather than stopping and restarting.

Inventive Principle:

Principle #20Continuity of useful action

3Reliability

If hybrid intensity mapping is applied to preserve meaningful differences, then reliability of image comparison is improved, but difficulty of detecting and measuring increases due to the complexity of distinguishing meaningful vs. noise variations

Engineering Contradiction:

Improvereliability of image comparisonVSAvoiddifficulty of identifying meaningful intensity differences

Core Design Contradiction:

ReliabilityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent implements feedback mechanisms where the optimization process continuously evaluates mapping quality based on comparison results. The genetic algorithm uses fitness functions that assess whether intensity differences are preserved meaningfully, providing feedback that guides parameter refinement and helps distinguish between noise and meaningful variations.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The mapping model serves as an intermediary between raw image intensities and normalized output. This intermediate representation allows the system to systematically control and adjust intensity relationships, making it easier to detect and measure meaningful differences while filtering out noise through the structured transformation process.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS10672113B2Methods and systems for normalizing images

Publication Date: 2020.06.02 AI ANALYSIS INC

AI summary

The current document is directed to digital-image-normalization methods and systems that generate accurate intensity mappings between the intensities in two digital images. The intensity mapping generated from two digital images is used to normalize or adjust the intensities in one image in order to produce a pair of normalized digital images to which various types of change-detection methodologies can be applied in order to extract differential data. In one approach, a mapping model is selected to provide a basis for statistically meaningful intensity normalization. In this implementation, a genetic optimization approach is used to determine and refine model parameters. The implementation produces a hybrid intensity mapping that includes both intensity mappings calculated by application of the mapping model and intensity mappings obtained directly from comparison of the images.