Assistive Outline Tracing for Accurate Raster-to-Vector Paths

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing vector-based design applications face limitations in flexibility and operational efficiency when tracing and converting raster images to vector content, often requiring manual input and lacking real-time contextual feedback, leading to inefficient and inaccurate vector path generation.

Innovation Solution

An assistive vector trace system utilizing deep learning for semantic analysis and segmentation to generate object masks, employing an outline matching model with hit detection to provide real-time assistive guides and auto-complete vector paths based on client device input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If manual conversion of raster image to vector content is performed, then accuracy of vector path generation is improved, but operational efficiency and productivity deteriorate

Engineering Contradiction:

Improveaccuracy of vector path generationVSAvoidoperational efficiency

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The system enables automatic vector path generation by allowing the computer to perform tracing operations autonomously using machine learning models, eliminating the need for manual conversion while maintaining accuracy through adaptive assistive guides that learn from user interactions

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical tracing operations with an automated machine learning-based system that uses neural networks and outline matching algorithms to generate vector paths automatically, substituting human effort with computational intelligence

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automated vector path generation is implemented, then productivity is improved, but manufacturing precision and accuracy deteriorate

Engineering Contradiction:

Improveoperational efficiencyVSAvoidaccuracy of vector path generation

Core Design Contradiction:

ProductivityVSManufacturing precision

Solution Approach 1:

The system incorporates real-time feedback through assistive guides that provide contextual suggestions during the tracing process, allowing the automated system to adapt and refine its output based on user corrections and interactions, thereby maintaining high accuracy while preserving productivity

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary analysis of the raster image using deep learning models to generate candidate outlines and predict user intent before final vector path creation, enabling accurate automated generation by preparing multiple potential solutions in advance

Inventive Principle:

Principle #10Preliminary action

3Ease of operation

If real-time assistive guides are provided, then ease of operation is improved, but device complexity increases

Engineering Contradiction:

Improveuser interface intuitivenessVSAvoidsystem architecture complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary layer of assistive guides that mediate between the complex automated vector generation system and the user, translating complex computational processes into simple, intuitive visual suggestions that ease operation without exposing underlying system complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

4Manufacturing precision

If deep learning models are used for semantic analysis, then manufacturing precision is improved, but use of energy and computational resources increases

Engineering Contradiction:

Improveaccuracy of image segmentationVSAvoidcomputational resource consumption

Core Design Contradiction:

Manufacturing precisionVSUse of energy by moving object

Solution Approach 1:

The system segments the image processing task into distinct stages performed by specialized models (object detection, instance segmentation, outline generation), allowing efficient resource utilization by processing only relevant portions of the image with appropriate models rather than applying heavy computation uniformly

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250363684A1Generating assistive guides of candidate paths in an image for user tracing inputs

Publication Date: 2025.11.27 ADOBE INC

AI summary

The present disclosure is directed toward systems, methods, and non-transitory computer readable media that provide assistive guides for path tracing of raster images. In particular, in one or more implementations, the disclosed systems determine a set of outlines corresponding to boundaries of a set of segments within a raster image. The disclosed systems select, from the set of outlines, an outline corresponding to a segment in response to a client device input indicating point(s) located within a threshold distance of the outline. The disclosed systems provide, for display within a graphical user interface of a client device, a highlighted indication of the outline corresponding to the segment. The disclosed systems generate, within a vector image, a vector path based on the outline corresponding to the segment in response to a selection of the outline via the graphical user interface.