Image Blur Evaluation Using Subject–Background Difference

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image blurring evaluation techniques struggle to appropriately assess the degree of background blurring relative to the subject and fail to consider the impact of imaging location, particularly outdoors vs. indoors.

Innovation Solution

An image processing device and method that calculates a difference in blurring between subject and background regions, considers the imaging location, and adjusts the evaluation value based on outdoor probability, using machine learning models to quantify blurring scores and outdoor information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the blurring evaluation is performed using only subject and background region division, then the evaluation can be completed with simple processing, but the evaluation cannot appropriately reflect the imaging location context (outdoors vs indoors)

Engineering Contradiction:

Improveadaptability to imaging location contextVSAvoidcomplexity of evaluation processing

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the image into subject region and background region, then further segments the background into outdoor background and indoor background. This segmentation allows the system to apply different evaluation criteria based on the specific background type, thereby improving adaptability to imaging location context without requiring complete redesign of the evaluation system.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies different blurring evaluation criteria to different regions based on their local characteristics. Specifically, it uses separate evaluation methods for outdoor backgrounds and indoor backgrounds, allowing each region to be evaluated according to its specific quality requirements. This local quality approach enables the system to adapt to different imaging contexts while maintaining a unified evaluation framework.

Inventive Principle:

Principle #3Local quality

2Measurement precision

If the background is evaluated with high precision, then the evaluation can detect subtle blurring differences, but the processing time and computational load increase

Engineering Contradiction:

Improveprecision of background blurring measurementVSAvoidprocessing time for blurring evaluation

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial action by focusing the high-precision evaluation only on the background regions that require it (outdoor and indoor backgrounds), while using simpler evaluation methods for the subject region. This selective application of evaluation precision allows the system to maintain high measurement precision where needed without unnecessarily increasing processing time across the entire image.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12462361B2Image processing device, image processing method, program, and recording medium

Publication Date: 2025.11.04 FUJIFILM CORP

AI summary

Provided are an image processing device, an image processing method, a program, and a recording medium for appropriately evaluating blurring of an image according to a background in the image.The image processing device of an embodiment of the present invention includes a processor, and the processor acquires an image, specifies a subject region in which a selected subject is captured and a background region except for the subject region, in the image, calculates a difference between a degree of blurring in the subject region and a degree of blurring in the background region, acquires information as to whether or not an imaging location of the image is outdoors, and calculates an evaluation value regarding blurring of the image on the basis of the difference and the information.