Principal Object Extraction for Image Exposure and White Balance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional imaging devices cannot perform exposure control based on the position and size of a principal object within an image, nor do they provide white balance correction, limiting their ability to optimize image quality.

Innovation Solution

An image processing apparatus that extracts the shape of a principal object, divides the image into weighted areas, calculates photometric and colorimetric values for each area, and applies exposure correction and white balance adjustments based on these values and their corresponding weighting factors, reflecting the object's shape and position.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional photometric systems (centerweighted, partial, spot, split) are used, then exposure control can be performed, but the system cannot optimize exposure based on the shape and position of the principal object

Engineering Contradiction:
Improveexposure control precisionVSAvoidadaptability to principal object shape and position
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The imaging device divides the image into multiple regions of interest (ROIs) based on the detected shape and position of the principal object. Each ROI is assigned a weighting factor that reflects its importance for exposure control, allowing the system to optimize exposure specifically for the principal object's location and shape rather than using conventional uniform or simple centerweighted approaches

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different weighting factors to different regions of the image based on their spatial relationship to the principal object. Regions closer to or containing the principal object receive higher weighting factors, while distant regions receive lower weights. This local differentiation enables the system to optimize exposure control according to the specific shape and position of the principal object, resolving the contradiction between measurement precision and adaptability

Inventive Principle:
Principle #3Local quality

2Measurement precision

If conventional photometric systems are used, then exposure control is possible, but white balance correction cannot be performed

Engineering Contradiction:
Improveexposure control precisionVSAvoidwhite balance correction capability
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The imaging device integrates both exposure control and white balance correction into a single unified system based on the same principal object detection and ROI weighting mechanism. The weighting factors determined for exposure control are also applied to colorimetric measurements, enabling the system to perform both functions simultaneously with optimized precision for the principal object, thereby eliminating the contradiction between exposure control capability and white balance correction capability

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Productivity

If the entire image is used for photometry, then exposure control can be performed, but the shape and position information of the principal object is not utilized

Engineering Contradiction:
Improveexposure control efficiencyVSAvoidloss of principal object shape and position information
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The imaging device segments the image into multiple regions based on the detected principal object shape and position, creating distinct ROIs that preserve spatial information. This segmentation allows the system to maintain productivity in exposure control while preventing loss of shape and position information, as the segmented regions explicitly encode spatial relationships

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension of spatial weighting by assigning different weighting factors to different ROIs based on their distance from or proximity to the principal object. This dimensional approach to weighting preserves and utilizes shape and position information while maintaining efficient exposure control, resolving the contradiction between productivity and information retention

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS7778481B2Apparatus and method for image processing including photometry and colorimetry
Publication Date: 2010.08.17 FUJIFILM CORP
  • US7778481B2 patent drawing
  • US7778481B2 patent drawing
  • US7778481B2 patent drawing

AI summary

The present invention provides an image processing apparatus comprising: a principal object extraction device which extracts a shape of a principal object from an overall screen of an image entered, a weighted area determining device which determines a plurality of areas including the area of the principal object that matches the shape of the extracted principal object as a weighted area, a weighting factor determining device which determines a weighting factor for each of the determined weighted areas, a measuring device which divides the overall screen into a plurality of areas and calculates measured values of divided photometry and/or divided colorimetry for each divided area, and a correction device which performs exposure correction and/or white balance correction based on a measured value calculated for each divided area and a weighting factor determined for each of the weighted areas to which the divided area of each measured value belongs.