Image Blurring Method Using Disparity-Based Depth Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing technologies face challenges in effectively performing blur operations on images, leading to increased complexity and deteriorated image quality, particularly in highlighting main objects by blurring backgrounds, as they do not efficiently utilize depth information from pixel values to control the strength of the blur operation.
Innovation Solution
An image processing device and method that determine in-focus and out-of-focus areas based on pixel values, calculate disparity values between sub-images in the out-of-focus area, and control the strength of the blur operation using these values, applying a Gaussian filter with varying sharpness to generate a blurred image only on the out-of-focus area.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a blur operation is performed on the entire image to highlight the main object, then the main object is highlighted, but the complexity of image processing operations increases and image quality deteriorates
Solution Approach 1:
The image is segmented into multiple sub-images based on depth information, with each sub-image corresponding to a specific depth range. The blur operation is then applied selectively to only those sub-images that correspond to out-of-focus areas, rather than applying blur to the entire image. This segmentation approach reduces unnecessary computational complexity while maintaining the highlighting effect.
Solution Approach 2:
Different regions of the image are treated differently based on their depth characteristics. Sub-images corresponding to in-focus areas retain their original clarity, while sub-images corresponding to out-of-focus areas undergo blur processing. This local differentiation optimizes image quality by applying blur only where needed, avoiding the deterioration that would occur with global blur application.
2Ease of manufacture
If a blur operation is performed on the entire image to highlight the main object, then the main object is highlighted, but image quality deteriorates
Solution Approach 1:
The image is divided into multiple sub-images based on depth information, allowing selective blur application. By segmenting the image into in-focus and out-of-focus regions, the system can maintain high image quality in the in-focus areas while applying blur only to the out-of-focus areas, thus avoiding the overall quality deterioration that would result from global blur processing.
Solution Approach 2:
The system applies different processing qualities to different regions: sharp processing for in-focus areas and blurred processing for out-of-focus areas. This local quality differentiation preserves image quality where it matters most (on the main object) while still achieving the desired background blur effect, thereby avoiding the quality deterioration associated with applying blur to the entire image.
3Measurement precision
If depth information is used to control blur strength, then the accuracy of depth-based blur operations improves, but the complexity of calculating disparity values increases
Solution Approach 1:
The image is segmented into multiple sub-images based on depth information, with each sub-image representing a specific depth range. By organizing the processing this way, the system can calculate disparity values and apply blur strength selectively to each segment, improving depth-based blur accuracy while managing computational complexity through structured processing.
Solution Approach 2:
The blur strength is made dynamic and variable across different regions of the image, rather than applying a uniform blur. The system adjusts blur strength based on the depth information and disparity values calculated for each sub-image, allowing more accurate depth-based blur control. This dynamic approach, while increasing calculation complexity, enables precise control over the blur effect according to the actual depth distribution in the scene.
Data Source
AI summary
An image processing device for performing an image blurring method includes an image preprocessor configured to determine an in-focus area and an out-of-focus area for sub-images of an externally received image, the sub-images generated based on pixel values of the externally received image. The image processor is also configured to calculate disparity values between the sub-images in the out-of-focus area. The image processing device further includes an image combiner configured to perform a blur operation on the out-of-focus area depending on a strength of the blur operation determined based on the disparity values and to sum sub-images on which the blur operation is performed.