Two-Step Keypoint Verification for Human Body Image Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing systems face inefficiencies in search processing for similar images based on feature values of human body keypoints, leading to reduced work efficiency due to prolonged processing times.
Innovation Solution
An image processing system comprising a target image acquisition unit, a skeleton structure detection unit, a first verification unit, and a second verification unit, which acquires and processes images to extract reference images that satisfy specific extraction conditions, narrowing down search targets in two separate steps to enhance processing speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search processing is performed by repeatedly adjusting conditions and performing full verification on all reference images, then search accuracy is improved, but processing time increases significantly
Solution Approach 1:
The patent divides the search processing into two distinct segments: a first verification process that performs coarse filtering using simplified criteria, and a second verification process that performs detailed verification only on candidates passing the first stage. This segmentation allows the system to maintain search accuracy while dramatically reducing processing time by avoiding full verification on all reference images.
Solution Approach 2:
The first verification process serves as a preliminary action that pre-filters reference images before they undergo the more time-consuming second verification. By performing this preliminary filtering step, the system eliminates obviously unsuitable candidates early, reducing the number of images requiring full verification and thus reducing overall processing time while maintaining accuracy.
2Reliability
If full verification is performed on all reference images, then search reliability is improved, but productivity decreases
Solution Approach 1:
The patent segments the verification process into two reliability-guaranteeing stages: first verification that establishes basic suitability criteria, and second verification that confirms final match quality. This segmented approach maintains search reliability by ensuring all candidates undergo appropriate verification while improving productivity by avoiding redundant full verification on all images.
Solution Approach 2:
The patent applies partial verification action by performing complete detailed verification only on reference images that pass the first verification filter, rather than performing full verification on all images. This partial action approach maintains reliability for the final selected matches while significantly improving productivity by reducing the total number of computationally expensive verification operations.
Data Source
AI summary
To achieve faster search processing in the search processing of a similar image, based on a feature value of each of a plurality of keypoints of a human body included in an image, the present invention provides an image processing system 10 including: a target image acquisition unit 11 that acquires a target image; a skeleton structure detection unit 12 that performs processing of detecting a keypoint of a human body included in the target image; a first verification unit 13 that extracts a first reference image whose relationship with the target image satisfies a first extraction condition, from among a plurality of reference images, based on the detected keypoint; and a second verification unit 14 that extracts a second reference image whose relationship with the target image satisfies a second extraction condition, from among the first reference images, based on the detected keypoint.