Adaptive Image Binarization via Histogram Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image binarization methods, such as the Otsu method, are inefficient for processing images with complex distributions, as they rely on a single global threshold and fail to effectively handle images with multiple classes or varying pixel values, leading to suboptimal binarization results.
Innovation Solution
An approach that selects between global and local thresholding methods based on histogram analysis, using characteristics like spike count, kurtosis, and cluster number to determine appropriate thresholding strategies, allowing for multiple threshold values to be applied across different image sub-blocks or the entire image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single global threshold is used for binarization, then the processing is simple and fast, but the binarization accuracy deteriorates for images with complex distributions
Solution Approach 1:
The patent divides the image into multiple sub-blocks and applies different thresholding methods to each sub-block based on its local histogram characteristics. This segmentation allows the system to maintain simple global processing while achieving accurate local binarization for complex images with multiple distributions.
Solution Approach 2:
The patent dynamically selects between global and local thresholding methods based on histogram analysis of the image or sub-block. The selection is not fixed but adapts to the actual image characteristics, choosing the most appropriate method (global or local) for each specific case to balance speed and accuracy.
2Adaptability or versatility
If the Otsu method is used for threshold selection, then bi-modal images are processed efficiently, but other types of images with complex distributions cannot be handled effectively
Solution Approach 1:
The patent creates a universal threshold determination system that can handle multiple image types (bi-modal, multi-modal, complex distributions) by supporting both global and local thresholding methods. The system automatically selects the appropriate method based on histogram characteristics, making it versatile across different image types without requiring separate specialized algorithms.
Solution Approach 2:
The patent changes the parameter of threshold determination from a single fixed method (Otsu) to a selectable family of methods (global and local variants). By analyzing histogram parameters like modality and distribution complexity, the system adjusts which thresholding approach to use, effectively changing the determination parameter to match the image characteristics.
3Measurement precision
If local thresholding is applied to all image sub-blocks, then binarization accuracy for complex images is improved, but processing complexity and time increase
Solution Approach 1:
The patent applies local thresholding only to sub-blocks that require it based on their specific histogram characteristics, rather than uniformly to all sub-blocks. This local quality approach ensures high accuracy for complex regions while maintaining simpler processing for regions that don't require local analysis, reducing overall processing complexity.
Solution Approach 2:
The patent performs partial local thresholding by selecting only certain sub-blocks for local processing based on histogram analysis, rather than applying local thresholding to the entire image. This partial action approach achieves necessary accuracy improvements while avoiding the excessive processing complexity that would result from universal local thresholding.
Data Source
AI summary
A threshold determination method is selected from among a plurality of alternative global thresholding determination methods and, optionally, a local thresholding determination method based on characteristics of a histogram of grayscales values representing an image. When it is determined to use a global thresholding method, a single global binarization threshold value is determined using the selected global thresholding method. Various alternative global binarization threshold values include a predetermined constant, an average value of the two grayscale values, an Otsu method based threshold value, a Newton method based threshold value, and an Otsu method based threshold value based on a truncated version of the histogram. When it is determined to use local thresholding, a plurality of local binarization threshold values are determined corresponding to different non-overlapping blocks of the image. The determined binarization threshold(s) are applied to the gray scale pixel values to obtain a set of binary pixel values.