Image Sameness Determination via Area Difference Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining whether two images are the same struggle to accurately assess differences in image quality, particularly in cases where differences in hues or color tone are subtle and not perceptible to the human eye.
Innovation Solution
An information processing device generates difference information by comparing a first image and a second image, dividing the images into multiple areas, and calculating total area difference amounts. It then determines whether the images are the same based on these total area difference amounts, using a threshold value to assess perceptibility to the human eye.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods for determining whether two images are the same are used, then the determination process is simple, but the accuracy of assessing subtle differences in image quality deteriorates
Solution Approach 1:
The image is divided into multiple areas (e.g., multiple blocks or regions) rather than treating it as a single unit. Difference information is calculated separately for each area, and total area difference amounts are obtained by summing differences within each area. This segmentation approach enables more precise detection of subtle image quality differences while maintaining a manageable determination process through systematic regional analysis.
2Measurement precision
If difference information is calculated for the entire image as a whole, then the calculation process is simple, but the ability to detect subtle localized differences deteriorates
Solution Approach 1:
The image is divided into multiple areas (e.g., multiple blocks or regions) rather than treating it as a single unit. Difference information is calculated separately for each area, and total area difference amounts are obtained by summing differences within each area. This segmentation approach enables more precise detection of subtle image quality differences while maintaining a manageable determination process through systematic regional analysis.
Solution Approach 2:
Different areas of the image are analyzed independently with their own difference calculations. By focusing on local regions rather than the entire image uniformly, the method can detect subtle localized differences in specific areas while maintaining overall image comparison capability.
3Measurement precision
If traditional image comparison methods are used, then computational resources are conserved, but the accuracy of determining image sameness deteriorates
Solution Approach 1:
The image is divided into multiple areas (e.g., multiple blocks or regions) rather than treating it as a single unit. Difference information is calculated separately for each area, and total area difference amounts are obtained by summing differences within each area. This segmentation approach enables more precise detection of subtle image quality differences while maintaining a manageable determination process through systematic regional analysis.
Solution Approach 2:
The method calculates difference information for multiple areas and obtains total area difference amounts, which provides more comprehensive analysis than traditional single-value comparison. This partial excess action (calculating more difference metrics than minimum required) improves determination accuracy by capturing nuanced variations across different image regions.
Data Source
AI summary
An information processing device includes circuitry to generate difference information related to a difference between a first image and a second image. The difference information has a plurality of areas. The circuitry further obtains a total value of differences in each of the plurality of areas as one of a plurality of total area difference amounts and determines whether the first image is same as the second image based on each of the plurality of total area difference amounts.


