Image Correlation Analysis Using Feature Orientation and Reliability Estimation

Solution Overview

Problem

Conventional methods for analyzing correlations between images or between an image and a video are inefficient due to the large number of feature points required, leading to excessive data processing and prolonged computation times, which hinders prompt and reliable comparison and search operations.

Innovation Solution

An apparatus and method that generate feature data with orientation information for feature points, using a reliability estimation unit to determine the reliability of correlations based on probability density functions, allowing for efficient comparison and search operations by reducing the number of feature points and using binary feature vectors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional feature point extraction methods (SIFT, SURF) are used to ensure accurate image correlation analysis, then measurement precision is improved, but the amount of data to be processed increases excessively and operation time is greatly lengthened

Engineering Contradiction:

Improveaccuracy of image correlation analysisVSAvoidcomputation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts only the essential orientation information from feature points while discarding redundant data. By focusing solely on orientation angles rather than full feature descriptors, the system maintains correlation analysis accuracy while dramatically reducing data volume and processing time.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms the feature representation by changing from high-dimensional feature vectors (256 dimensions in SIFT, 64 in SURF) to simple orientation angle parameters. This parameter transformation reduces computational complexity while preserving the essential information needed for image correlation.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If conventional feature point extraction methods are used to ensure accurate image correlation analysis, then measurement precision is improved, but device complexity increases due to complicated operation processes

Engineering Contradiction:

Improveaccuracy of image correlation analysisVSAvoidcomplexity of operation process

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential orientation information from feature points while discarding redundant data. By focusing solely on orientation angles rather than full feature descriptors, the system maintains correlation analysis accuracy while dramatically reducing data volume and processing time.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms the feature representation by changing from high-dimensional feature vectors (256 dimensions in SIFT, 64 in SURF) to simple orientation angle parameters. This parameter transformation reduces computational complexity while preserving the essential information needed for image correlation.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If a large number of feature points are extracted from images to ensure reliable correlation analysis, then reliability is improved, but the amount of data to be processed becomes excessive

Engineering Contradiction:

Improvereliability of correlation analysisVSAvoidamount of feature data

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential orientation information from feature points while discarding redundant data. By focusing solely on orientation angles rather than full feature descriptors, the system maintains correlation analysis accuracy while dramatically reducing data volume and processing time.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms the feature representation by changing from high-dimensional feature vectors (256 dimensions in SIFT, 64 in SURF) to simple orientation angle parameters. This parameter transformation reduces computational complexity while preserving the essential information needed for image correlation.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS9665789B2Device and method for analyzing the correlation between an image and another image or between an image and a video

Publication Date: 2017.05.30 ENSWERS CO LTD

AI summary

The present invention relates to a device and method for analyzing the correlation between an image and another image or between an image and a video. The device for analyzing the correlation between images and the method for using same include: a feature data generating unit for determining a feature point of an image and generating feature data which includes feature point orientation information on each determined feature point; and a relation analyzing unit for analyzing the correlation between an image and another image using feature data generated from the feature data generating unit. The relation analyzing unit includes: a unit for determining corresponding feature points, which determines a pair of corresponding feature points between compared images using feature data generated from the feature data generating unit; and a reliability estimating unit for estimating the reliability of the analysis of the relation between images on the basis of feature point orientation information on a feature point, in pairs of feature points determined by the unit for determining corresponding feature points. According to the present invention, provided are a device and method for quickly and efficiently analyzing a correlation, such as whether or not there is a similarity between an image and another image or between an image and a video, wherein said video includes an image, or a frame of said video corresponds to an image.