Image Variation Engine Duplicate Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting duplicate images are inefficient and lack scalability, especially when dealing with varying image sizes, orientations, and distortions, which complicates the process of identifying identical or similar images.
Innovation Solution
A computing device processes images by determining a best fit size, resizing them, generating an image frame, and comparing pixels using intensity coding to identify duplicates, with features like anti-aliasing and skew correction to handle variations in image quality and orientation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If images are compared directly without preprocessing, then the comparison process is simple, but the detection accuracy is poor due to varying sizes, orientations, and distortions
Solution Approach 1:
The patent applies preliminary actions by performing preprocessing operations (resizing, orientation correction, distortion normalization) on images before comparison. This ensures that images are standardized to a common format and orientation, enabling accurate duplicate detection while maintaining a systematic workflow that balances complexity and effectiveness
2Productivity
If all images are resized to a uniform size, then the comparison efficiency is improved, but the image quality and detail may be lost
Solution Approach 1:
The patent changes parameters by implementing a hierarchical comparison approach: first comparing images at a reduced resolution for quick filtering, then proceeding to full-resolution comparison only for potentially duplicate images. This parameter adjustment optimizes processing efficiency while preserving image quality by avoiding unnecessary full-resolution comparisons
3Measurement precision
If pixel-by-pixel comparison is performed on high-resolution images, then the detection accuracy is high, but the processing time and computational resources increase significantly
Solution Approach 1:
The patent applies segmentation by dividing the comparison process into multiple stages: initial filtering using hash-based methods, intermediate comparison at reduced resolution, and final verification at full resolution. This segmented approach maintains high detection accuracy by performing detailed pixel-by-pixel comparison only on candidate duplicates, significantly reducing overall processing time
4Reliability
If the system processes and stores all images in original format, then the image quality is preserved, but the storage requirements and processing complexity increase
Solution Approach 1:
The patent uses copying by creating standardized versions of images (resized, normalized orientation) for storage and comparison purposes, while preserving the original images only when necessary. This approach maintains image data integrity for critical operations while reducing overall storage requirements through selective preservation of original formats
Data Source
AI summary
Various features described herein may include ways of processing multiple images to determine whether any duplicates are among the multiple images. A hashing algorithm may be used to create a hash key of an image. Multiple hash keys corresponding to multiple images may be compared to determine whether those images are duplicate images. A root mean square algorithm may be used to further identify whether multiple images are duplicate images. An image variation engine, which uses intensity coding, may be used to display differences between images. For example, similar areas in images may be drawn with low intensity or high opacity, while different areas in images may be drawn with high intensity or low opacity.