Ink Color Selection via Superpixel Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing screen printing algorithms are computationally intensive and fail to accurately consider pixel locations and neighboring colors, leading to improper ink color selection due to compression effects and anti-aliasing artifacts.
Innovation Solution
The method selects a subset of sample pixels within the image, determining their colors and those of neighboring pixels to choose representative ink colors, using quantization techniques to filter out artifacts and reduce computational load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If histogram approaches are used to analyze each pixel in the image, then comprehensive color analysis is achieved, but computation time increases significantly
Solution Approach 1:
The image is divided into superpixels (groups of adjacent pixels) rather than analyzing each individual pixel. This segmentation reduces the number of analysis units from potentially millions of pixels to thousands of superpixels, dramatically reducing computation time while preserving color information through superpixel representative colors.
Solution Approach 2:
The method extracts only the most relevant color information by selecting representative colors from each superpixel and filtering out colors that are likely artifacts (such as anti-aliasing pixels). This extraction focuses computational resources on meaningful color data rather than processing every pixel uniformly.
2Reliability
If all pixels in the image are considered for ink color selection, then complete color coverage is achieved, but the impact of compression effects and anti-aliasing artifacts increases
Solution Approach 1:
The algorithm applies different treatment to different regions by analyzing the spatial distribution and color similarity within superpixels. It identifies and filters out pixels with excessive color variation that are likely artifacts, while preserving pixels with consistent colors that represent true image content. This local quality assessment allows selective filtering of harmful artifacts.
Solution Approach 2:
The method converts the potential harm of compression artifacts and anti-aliasing into a beneficial filtering mechanism. By analyzing color variation within superpixels, the algorithm identifies artifact pixels (which show excessive variation) and excludes them from ink color selection, thereby improving accuracy. The artifacts become identifiable markers for exclusion rather than sources of error.
3Quantity of substance
If traditional histogram methods are used, then all color data is captured, but the locations of pixels and neighboring pixel colors are insufficiently considered
Solution Approach 1:
The algorithm transitions from traditional histogram analysis (which only considers color values) to a spatially-aware approach by organizing pixels into superpixels based on both color similarity and spatial proximity. This adds a spatial dimension to the color analysis, allowing the algorithm to consider neighboring pixel relationships and location information alongside color data.
Data Source
AI summary
Implementations of the present disclosure are directed to a method, system, and computer-readable medium for choosing ink colors for a screen printing process. An image to be reproduced with the screen printing process is obtained, and sample pixels within the image are selected. For each sample pixel, if the color of the sample pixel is not similar to an already chosen ink color, neighboring pixels around the sample pixel are identified. When the colors of the sample pixel and its neighboring pixels are similar, an ink color is chosen to be a representative color of the sample pixel and its neighboring pixels.