Image Contrast Classification via Pixel Intensity Probability Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing techniques fail to accurately classify images based on overall contrast levels, as they primarily measure differences between the darkest and lightest values, leading to poor separation of contrast classes and subjective, time-consuming manual identification.
Innovation Solution
A method and apparatus that utilize a trained machine learning model to classify images into high, low, or normal contrast classes by analyzing pixel intensity values, luminance, and spread values, providing a systematic approach to contrast scoring through probability distributions and machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional contrast evaluation methods (Michelson, RMS, Weber) are used to measure the difference between darkest and lightest values, then the measurement process is simple, but the contrast class separation is poor and classification accuracy deteriorates
Solution Approach 1:
The patent segments the image processing into distinct stages: extracting intensity values for each pixel, calculating probability distribution functions for intensity values, determining spread values representing series of pixel values, and classifying based on these segmented features. This segmentation allows for more precise contrast measurement while maintaining organized processing complexity
Solution Approach 2:
The patent transitions from traditional 1D contrast measurement (difference between max and min values) to a multi-dimensional approach by calculating probability distribution functions across intensity values and determining spread values that represent series of pixel values. This dimensional expansion enables better contrast class separation while systematically managing processing complexity
2Reliability
If manual identification of contrast levels is performed, then subjective assessment can be applied, but the process is time-consuming and inconsistent
Solution Approach 1:
The patent implements an automated system where the image processing apparatus independently extracts intensity values, calculates probability distributions, determines spread values, and classifies contrast levels without human intervention. This self-service approach eliminates time-consuming manual assessment while ensuring consistent, reliable classification results through standardized algorithms
Solution Approach 2:
The patent replaces the mechanical/manual process of subjective contrast assessment with an automated computational system that uses probability distribution functions and spread value calculations. This substitution eliminates human subjectivity and time constraints while maintaining or improving classification reliability through consistent algorithmic processing
Data Source
AI summary
An apparatus for classifying a contrast level of an image is provided. One or more processors execute instructions stored in one or more memory devices which configure the one or more processors to obtain an image from an image source, extract intensity values for each pixel of the obtained image, calculate a probability distribution for the obtained image representing a number of pixels at each unique pixel value, determine, from the calculated probability distribution, a spread value representing a series pixel values including at least a predetermined number of pixels at each pixel value in the series of pixel values and classify the obtained image a member of one of three classes based on the calculated probability distribution and the determined spread value.