Tone Curve Generation via Model Parameter Association
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing technologies face challenges in generating an optimum tone curve for images, requiring skilled users and involving a trial-and-error process, especially when dealing with images of different exposures, as previously generated tone curves are not easily adaptable to new images.
Innovation Solution
An image processing apparatus that models the distribution of pixel values using a probability distribution model to acquire model parameters, generates a tone curve by associating these parameters with target values, and corrects images based on this tone curve, allowing for automatic extraction of image features and generation of optimal tone curves without requiring extensive user expertise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a tone curve is generated manually with multiple control points to achieve optimal image correction, then image correction quality is improved, but user skill requirement and time consumption increase
Solution Approach 1:
The system automatically analyzes the processing object image to extract feature parameters (highlight ratio, medium tone ratio, shadow ratio) and autonomously generates the tone curve by associating these parameters with target values from a reference image. This self-service mechanism eliminates the need for manual control point setting by users, resolving the contradiction between high correction quality and ease of operation
Solution Approach 2:
The invention changes the approach from manually setting control point positions to automatically determining tone curve characteristics through image feature parameter analysis. By extracting parameters such as highlight ratio, medium tone ratio, and shadow ratio from the processing object image and associating them with target values, the system generates an optimized tone curve without requiring users to adjust individual control points, thus improving ease of operation while maintaining correction quality
2Manufacturing precision
If a tone curve is generated manually with multiple control points to achieve optimal image correction, then image correction quality is improved, but processing time increases due to trial and error
Solution Approach 1:
The system performs preliminary analysis of the processing object image to extract feature parameters (highlight ratio, medium tone ratio, shadow ratio) before generating the tone curve. By pre-determining these characteristic parameters and their association with target values from the reference image, the system eliminates the need for iterative trial and error adjustments, significantly reducing processing time while ensuring optimal correction quality
Solution Approach 2:
The system uses feedback from image feature parameter analysis to automatically adjust and generate the tone curve. By continuously monitoring the extracted parameters (highlight ratio, medium tone ratio, shadow ratio) and comparing them with target values, the system iteratively optimizes the tone curve generation process without requiring manual intervention, thus reducing processing time while maintaining high correction quality
3Ease of operation
If the same tone curve is used for images with different exposures, then processing simplicity is improved, but correction effectiveness deteriorates
Solution Approach 1:
The system analyzes local characteristics of the processing object image by extracting feature parameters (highlight ratio, medium tone ratio, shadow ratio) that specifically represent the exposure conditions of that image. By associating these local features with corresponding target values from the reference image, the system generates a customized tone curve that effectively handles different exposure conditions, resolving the contradiction between processing simplicity and correction effectiveness
Solution Approach 2:
The tone curve generation process is made dynamic by automatically adapting to the specific exposure characteristics of each processing object image. The system extracts feature parameters that reflect the image's unique exposure conditions and dynamically generates an appropriate tone curve, eliminating the need for users to manually select different curves for different exposures while maintaining high correction effectiveness
Data Source
AI summary
An image processing apparatus includes an image analyzing unit, a tone-curve generating unit, and an image correcting unit. The image analyzing unit acquires a model parameter by modeling data distribution of an image with a probability distribution model. The tone-curve generating unit generates a tone curve on the basis of control information in which the model parameter acquired by modeling the data distribution of the image to be processed is associated with a target value of the model parameter. The image correcting unit corrects the image to be processed by using the generated tone curve.