Pigment Detection via Spectral Response Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing skin pigment detection technologies face poor applicability due to the inability to accurately detect pigments in diverse scenarios without prior training on specific skin images, leading to suboptimal performance in complex detection environments.
Innovation Solution
A method that extracts a body reflection component from RGB skin images using spectral response curves to separate pigments like melanin and hemoglobin, allowing for pigment detection across various scenarios without the need for prior training, and generates a pseudo-color image for improved visualization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If offline training is performed using skin images from different scenarios to obtain a detection model, then the detection model can separate skin pigment, but the detection model has poor applicability in complex variable scenarios because it is impossible to acquire skin images in all scenarios for training
Solution Approach 1:
The patent changes the approach from training-based parameter adaptation to physics-based spectral response modeling. By establishing a mathematical model that relates the spectral response curves of pigments to the RGB channel responses, the system can directly compute pigment concentrations without requiring scenario-specific training data, thereby achieving both accuracy and broad applicability across different scenarios
Solution Approach 2:
The patent introduces spectral response curves as an intermediary between the physical properties of pigments and the digital image data. This intermediary model bridges the gap between theoretical pigment properties and practical image measurement, enabling accurate pigment detection without direct training on diverse scenarios
2Reliability
If a detection model is trained using skin images from specific scenarios, then the model can accurately detect pigments in those scenarios, but the model cannot be applied to other scenarios with complex variables
Solution Approach 1:
The patent creates a universal detection model based on the physical spectral response properties of pigments rather than scenario-specific training. The mathematical model using spectral response curves and RGB channel relationships can be applied across all scenarios regardless of lighting conditions, background, or subject characteristics, achieving both reliability and generalization simultaneously
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the applicability and accuracy of skin pigment detection by effectively separating pigments in RGB skin images, regardless of the scenario, and provides a clear, intuitive representation through pseudo-color imaging.
Implementation Method 1
extracting a pigment from an R channel, a B channel, and a G channel of the first image based on a correspondence between a first spectral response curve of the pigment and a second spectral response curve of the device having the RGB image photographing function
Data Source
AI summary
A pigment detection method includes: extracting a first image from a to-be-detected RGB skin image, where the first image is used to represent a body reflection component in the RGB skin image, and the RGB skin image is photographed by a device having an RGB image photographing function; extracting a pigment from an R channel, a B channel, and a G channel of the first image based on a correspondence between a first spectral response curve of the pigment and a second spectral response curve of the device having the RGB image photographing function; and generating a pseudo-color image based on the extracted pigment, and displaying the pseudo-color image.