Auto-Exposure Control via Dynamic Face and Scene Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing auto-exposure operations in personal electronic devices often result in suboptimal image capture, with images being washed out due to bright backgrounds or under-exposed due to large areas of darkness, as they either meter the scene as a whole or focus solely on faces.
Innovation Solution
A method to automatically adjust the exposure settings of a digital image capture device by combining dynamically weighted exposure values based on detected faces and the image as a whole, using measured and target exposure values calculated from image statistics such as histograms and luminance matrices, to achieve optimal exposure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If the camera meters the scene as a whole, then the overall scene exposure is captured, but the image becomes washed out due to bright backgrounds
Solution Approach 1:
The patent divides the image into multiple regions including face regions and non-face regions. Each region is metered separately to calculate region-specific exposure values. This segmentation allows the system to avoid being dominated by bright backgrounds in the overall scene metering, while still capturing appropriate exposure for important subjects like faces.
Solution Approach 2:
The patent applies different exposure weighting to different regions of the image. Face regions are given different exposure targets and weighting factors compared to non-face regions. This local quality approach ensures that critical subjects (faces) receive optimal exposure while allowing other regions to be exposed according to their local characteristics, preventing washed-out appearances.
2Manufacturing precision
If the camera concentrates exposure on faces, then face exposure is optimized, but the image becomes under-exposed due to large areas of darkness
Solution Approach 1:
The patent merges multiple exposure values from different regions (face regions and non-face regions) into a combined exposure determination. The system calculates exposure values for face regions, non-face regions, and potentially other regions, then combines these using weighting factors to produce an overall exposure decision. This merging ensures that while faces are prioritized, the overall scene brightness is also considered to avoid under-exposure in dark areas.
Solution Approach 2:
The patent dynamically adjusts the weighting factors applied to different region exposure values based on scene conditions. The weighting factors are not fixed but can be modified based on the relative importance of different regions, the lighting conditions, and the desired artistic effect. This dynamic adjustment allows the system to balance face exposure optimization with overall scene brightness preservation.
3Manufacturing precision
If multiple regions are metered and combined, then exposure accuracy is improved, but the computational complexity increases
Solution Approach 1:
The patent implements a multi-region metering system that goes beyond simple scene or face-only metering by dividing the image into multiple regions with different exposure targets and weighting factors. This partial action approach processes only the most critical regions (faces, non-face areas) rather than every pixel, achieving improved exposure accuracy while maintaining computational efficiency through selective region analysis rather than full-image processing.
Data Source
AI summary
Systems, methods, and computer readable media for performing auto-exposure operations in a digital image capture device. An image capture device's auto-exposure settings may be automatically adjusted by generating and then combining, in a dynamically weighted fashion, two sets of exposure values. One set of exposure values may be based on detected faces while the other set may be based on the image as a whole. Each set of exposure values may include a “measured” value and a “target” value, wherein each of these values may, in turn, be based on one or more (different) aspects of the image. Illustrative digital image capture devices in which the disclosed technology may be used include, but are not limited, to portable digital cameras, mobile telephones, personal digital assistants, mobile music and video devices, and portable computer platforms such as notebook and tablet computers.