Exposure Determination for Face Detection in Backlit Scenes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional imaging systems face challenges in accurately determining exposure settings for face and human body detection in images, particularly in backlit scenes where background luminance can incorrectly influence face detection, leading to under or overexposure issues.
Innovation Solution
An information processing apparatus with detection units for face and human body detection, along with exposure determination, calculates average luminance values for both the subject and background regions to adjust exposure settings using specific equations and parameters, ensuring accurate exposure correction based on the detected regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If background luminance is used for exposure determination, then overall image brightness can be controlled, but face detection accuracy deteriorates in backlit scenes
Solution Approach 1:
The patent segments the image into subject region and background region, calculating separate average luminance values for each. The exposure determination unit then uses these segmented luminance values to determine exposure amounts specifically for the subject region, preventing background luminance from incorrectly influencing face detection accuracy.
2Device complexity
If single exposure amount is used for entire image, then processing is simplified, but exposure accuracy for specific regions deteriorates
Solution Approach 1:
The patent determines different exposure amounts for different regions (subject region and background region) based on their respective average luminance values. This local quality approach ensures that each region receives appropriate exposure treatment, with the subject region receiving exposure optimized for face detection accuracy while the background receives appropriate exposure for overall image brightness.
Data Source
AI summary
An information processing apparatus includes an image acquisition unit configured to acquire an image, a first detection unit configured to detect a specific object from the image, a second detection unit configured to detect a part of the specific object from the image, an exposure determination unit configured to determine a first exposure amount with respect to the specific object detected by the first detection unit, and to determine a second exposure amount with respect to the part of the specific object detected by the second detection unit, and a parameter determination unit configured to determine a parameter regarding at least one of the first detection unit, the second detection unit, and the exposure determination unit.