Piecewise Object-Stroke Vectorization for Fewer Extraneous Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional vectorization techniques result in extraneous paths, computational inefficiencies, visual inaccuracies, and extraneous power consumption due to the failure to detect and integrate semantically related strokes into a single path, leading to inefficient conversion of raster images to vector images.
Innovation Solution
A computing device employs a deep neural network to detect and combine visually separated and semantically related strokes, generating a single path that accurately represents the object's boundary by piecewise deconstruction, thereby reducing computational inefficiencies and power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional vectorization techniques are used to convert raster images to vector images, then the conversion process is performed, but extraneous paths are generated and computational inefficiencies occur
Solution Approach 1:
The patent segments the vectorization process into distinct phases: stroke detection, semantic relationship analysis, and path generation. By dividing the boundary into semantically related stroke groups rather than treating all strokes independently, the system generates fewer extraneous paths while maintaining conversion capability
Solution Approach 2:
The patent merges visually separated but semantically related strokes into unified paths. By analyzing semantic relationships between strokes and combining them appropriately, the system reduces the total number of paths generated while preserving the visual accuracy of the vectorized image
2Reliability
If conventional vectorization techniques process all strokes independently, then complete coverage is achieved, but computational inefficiencies and extraneous power consumption occur
Solution Approach 1:
The patent combines processing of semantically related strokes into unified operations. By identifying strokes that belong to the same semantic group and processing them together rather than independently, the system reduces computational overhead and power consumption while ensuring complete boundary coverage
Solution Approach 2:
The patent changes the processing parameters by introducing semantic relationship analysis as a new dimension for organizing stroke processing. This allows the system to optimize computational resources by grouping strokes based on their semantic relationships rather than processing them in a uniform manner
3Quantity of substance
If conventional vectorization techniques generate multiple separate paths for visually separated strokes, then all visual elements are captured, but visual inaccuracies occur
Solution Approach 1:
The patent merges visually separated strokes that are semantically related into single coherent paths. By analyzing the semantic relationships between strokes and combining those that belong together, the system maintains complete capture of visual elements while improving the accuracy of the resulting vector representation
Data Source
AI summary
In implementation of techniques for vectorizing by piecewise deconstruction of object strokes, a computing device implements an image processing system to receive an input to initiate the generation of a boundary of an object in a digital image, such as a raster image. The image processing system detects a set of visually separated but semantically related strokes that represent the object's boundary. Based on the set of visually separated but semantically related strokes, the image processing system forms a combined stroke and generates the boundary of the object as a path based on the combined stroke. The resulting path mimics the visual appearance of the object in the digital image in a vector space.