Elastic Block-Wise Image Comparison for Ad Version Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional advertisement version detection techniques are largely manual and prone to false highlighting due to post-production alterations, making it difficult to accurately identify differences between image versions.

Innovation Solution

The use of elastic block-wise image comparison and transformation techniques to ignore resolvable differences caused by post-production alterations, focusing on unresolvable blocks to identify actual content differences between advertisement versions, with automated recognition of version-specific regions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If pixel-wise comparison techniques are used to detect differences between advertisement images, then the detection process becomes automated and faster, but false highlighting occurs due to post-production alterations

Engineering Contradiction:
Improvedetection speedVSAvoiddetection accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent divides the image comparison process into multiple processing stages: initial pixel-wise comparison to identify candidate difference regions, followed by block-wise comparison with transformation operations to verify and filter these regions. This segmentation allows the system to quickly identify potential differences while systematically eliminating false positives through hierarchical verification.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary pixel-wise comparison across the entire image to identify candidate difference regions before conducting more computationally intensive block-wise analysis with transformation operations. This preliminary action filters out obviously matching regions, allowing the system to focus computational resources only on regions that require detailed verification.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If manual visual comparison is used to identify advertisement versions, then detection accuracy is maintained, but the process becomes entirely manual and time-consuming

Engineering Contradiction:
Improvedetection accuracyVSAvoidanalysis time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent introduces an automated intermediary system that performs initial pixel-wise comparison and block-wise verification with transformation operations. This intermediary process handles the bulk of the comparison work automatically, filtering and validating difference regions before presenting only the most significant findings for potential manual review, thus reducing overall analysis time while maintaining accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If block-wise comparison with transformation operations is used, then false positives from post-production alterations are reduced, but the device complexity increases

Engineering Contradiction:
Improvefalse positive reductionVSAvoidprocessing complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic block resolution selection, where the system adjusts the size and granularity of blocks based on the specific image characteristics and detected difference patterns. This dynamic adaptation allows the system to use coarser blocks for regions with expected post-production variations and finer blocks for regions requiring precise comparison, optimizing the balance between false positive reduction and processing complexity.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS9342756B2Methods and apparatus to detect differences between images
Publication Date: 2016.05.17 THE NIELSEN CO (US) LLC

AI summary

Methods and apparatus to detect differences between images are disclosed. Example methods disclosed herein include determining whether a difference between a block of pixels of a first image represented by a first signature and a block of pixels of a reference image represented by a second signature matching the first signature is resolvable using a transformation operation. Example methods disclosed herein also include, in response to determining the difference is unresolvable using the transformation operation, including the block of pixels of the first image in a difference region of the first image. Example methods disclosed herein further include generating a third signature different from the difference region of the first image to represent the difference region of the first image, and storing the third signature with version information associated with first image.