Image Processing Apparatus Distance-Based Composite Area Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing image processing technologies fail to determine areas in a main image to combine with a sub image when no face is detected, particularly in scenarios where the background, such as a commemorative photo, is undesired to be hidden.

Innovation Solution

An image processing apparatus that uses distance information to determine a composite area within the main image for combining with a sub image, employing evaluation values based on luminance, color, and distance information to select areas of low importance for overlaying the sub image.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a sub image is combined with a main image based on face detection, then the composite image can be generated effectively when faces are present, but the technique fails when no face is detected in the main image

Engineering Contradiction:

Improvecomposite image generation reliabilityVSAvoidapplicability to different image types

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent changes the parameter basis for determining composite areas from face detection to distance information evaluation. By using distance information to calculate evaluation values for multiple partial areas, the system can determine composite areas in various image types including landscapes and commemorative photos where no faces are present, thereby improving both reliability and adaptability

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent creates a universal composite image generation system that works across multiple image types by introducing a multi-criteria evaluation mechanism. The system can handle face-containing images, landscape images, commemorative photos, and other image types by evaluating distance information and importance levels of different partial areas, making the technology applicable to diverse scenarios

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Area of stationary object

If the entire background area is combined with a sub image, then the composite image coverage is maximized, but important background elements like tourist spots are obscured

Engineering Contradiction:

Improvecomposite area coverageVSAvoidobscuration of important background elements

Core Design Contradiction:

Area of stationary objectVSObject-affected harmful factors

Solution Approach 1:

The patent applies local quality by assigning different importance levels to different partial areas of the main image based on their distance information. Areas with high importance (such as those containing important background elements) are excluded from composite areas even if they are in the background, while areas with low importance are selected for composite image placement. This ensures that important elements are not obscured while still achieving effective composite image integration

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent introduces an intermediary evaluation mechanism that mediates between the need for composite image coverage and the need to preserve important background elements. By calculating evaluation values based on distance information and using these values to determine composite areas, the system acts as an intermediary that balances coverage requirements with preservation of important elements

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS10116877B2Image processing apparatus and image processing method

Publication Date: 2018.10.30 CANON KK

AI summary

An image processing apparatus combines a partial area of a first image with a second image. The partial area to be combined with the second image is determined based on distance information with regard to a plurality of partial areas of the first image.