Dynamic Sub-Image Binarization for Uneven Luminance

Solution Overview

Problem

Existing image binarization methods, particularly in surveillance contexts, face challenges in producing high-quality binarized images from grayscale images with uneven luminance, as they often result in unrecognizable backgrounds and fail to provide sufficient detail in a timely manner.

Innovation Solution

The method employs dynamic sub-image division, where each pixel is evaluated based on its neighboring pixels to determine a local threshold, allowing for smooth transitions and optimal binarization by creating sub-images that are dynamically sized to ensure even luminance and sufficient information content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If global threshold binarization is used, then the processing is simple and fast, but the binarized image quality deteriorates in unevenly lit regions

Engineering Contradiction:

Improveprocessing speedVSAvoidbinarized image quality

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The image is divided into multiple sub-images or blocks, and each sub-image is binarized independently using its own threshold. This segmentation allows different regions with different luminance characteristics to be processed separately, improving binarization quality in unevenly lit areas while maintaining reasonable processing speed through parallel processing of sub-images.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Different threshold values are applied to different regions of the image based on local luminance characteristics. The threshold for each sub-image is determined by analyzing the specific luminance distribution in that region, ensuring optimal binarization quality for each local area rather than using a single global threshold for the entire image.

Inventive Principle:

Principle #3Local quality

2Manufacturing precision

If adaptive thresholding with multiple sub-images is used, then the binarized image quality improves, but the device complexity increases

Engineering Contradiction:

Improvebinarized image qualityVSAvoidprocessing complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The image is divided into multiple sub-images or blocks, and each sub-image is binarized independently using its own threshold. This segmentation allows different regions with different luminance characteristics to be processed separately, improving binarization quality in unevenly lit areas while maintaining reasonable processing speed through parallel processing of sub-images.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Different threshold values are applied to different regions of the image based on local luminance characteristics. The threshold for each sub-image is determined by analyzing the specific luminance distribution in that region, ensuring optimal binarization quality for each local area rather than using a single global threshold for the entire image.

Inventive Principle:

Principle #3Local quality

3Manufacturing precision

If adaptive thresholding with multiple sub-images is used, then the binarized image quality improves, but the processing time increases

Engineering Contradiction:

Improvebinarized image qualityVSAvoidprocessing time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The image is divided into multiple sub-images or blocks, and each sub-image is binarized independently using its own threshold. This segmentation allows different regions with different luminance characteristics to be processed separately, improving binarization quality in unevenly lit areas while maintaining reasonable processing speed through parallel processing of sub-images.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Instead of performing complex adaptive thresholding on the entire image, the method applies simplified thresholding to each sub-image independently. This partial action approach processes only the necessary portions of the image with appropriate complexity, reducing overall processing time while maintaining quality through localized optimization.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS9332154B2Image binarization using dynamic sub-image division

Publication Date: 2016.05.03 IMDS AMERICA

AI summary

Image binarization method and device for converting a grayscale image into a black and white binary image are provided. The grayscale image is divided into sub-images dynamically created from pixel to pixel containing a given pixel as well as neighboring pixels. A threshold for each pixel is determined based on the color values of all the pixels in the sub-image. Therefore, at a certain color value, this given pixel is converted to white and at another color value the pixel is converted black. The foregoing is effectuated pixel by pixel in a dynamic fashion evaluating each pixel relative to its neighboring pixels in order to produce a binary image.