Global Tone Mapping with Face Detection Gain Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital image and video processing technologies face challenges in effectively reducing video noise, preventing highlight clipping, and achieving optimal global tone mapping, which can result in images that are either overexposed, underexposed, or suffer from artifacts.
Innovation Solution
The implementation of a system that includes a Bayer scaler for adjusting the color model of digital images, a clipping corrector for managing highlight clipping, and a global tone mapper for enhancing the global contrast of images, all of which work together to improve image quality by reducing noise and optimizing exposure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If noise reduction methods are applied to improve image quality, then the qualitative appearance is improved, but certain details in the image are sacrificed and artifacts are generated
Solution Approach 1:
The patent applies different noise reduction strategies to different regions of the image based on their characteristics. High-pass filtered regions (edges, textures) are processed differently from low-pass filtered regions (smooth areas), allowing noise reduction while preserving important details and reducing artifacts in each region appropriately
Solution Approach 2:
The noise reduction process is divided into multiple stages with different filtering approaches. The patent segments the processing into high-pass and low-pass filtering stages, allowing each stage to address specific types of noise and details separately, thereby reducing overall artifacts while maintaining image quality
2Loss of information
If exposure settings are adjusted to capture more dynamic range, then highlight clipping is prevented, but the camera's limited dynamic range still causes blown out or too dark areas
Solution Approach 1:
The patent applies tone mapping and exposure adjustment operations before the final image output. By pre-adjusting the tone distribution and exposure settings, the system prevents highlight clipping and optimizes the use of available dynamic range, ensuring that critical highlight information is preserved even with limited camera dynamic range
Solution Approach 2:
The system dynamically adjusts exposure parameters and tone mapping curves based on the image content and lighting conditions. By changing these parameters adaptively, the camera optimizes its limited dynamic range to capture the full range of intensities, preventing both blown out highlights and too dark areas
Data Source
AI summary
A non-transitory computer-readable storage medium stores executable instructions that, when executed by a processor, cause performance of operations comprising operations to access an image captured by an image sensor, obtain a transfer function for mapping pixel values, determine a faces indication that reflects a proportion of a scene depicted in the image that includes one or more human faces, and modify the transfer function based on the faces indication. Modifying the transfer function based on the faces indication comprises adjusting a gain of the transfer function to move the gain closer to unity. The operations include to apply the transfer function to pixel values of the image to produce a tone mapped image and output the tone mapped image.