Document Decomposition via Iterative Visual Layering

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing document decomposition techniques struggle to accurately detect underlying content objects in documents with visually overlapping layers, common in graphics design and creative fields.

Innovation Solution

The techniques involve iteratively decomposing a document into its constituent content objects based on determined logical visual layering, where content objects in the visual foreground are identified and removed at each iteration, allowing for accurate detection of underlying content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing document decomposition techniques are used on visually layered documents, then the decomposition process is simple and fast, but the detection accuracy of underlying content objects deteriorates

Engineering Contradiction:

Improvedetection accuracy of underlying content objectsVSAvoiddecomposition process complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the document decomposition process into multiple iterations, where each iteration detects and removes foreground content objects before the next iteration. This segmentation allows the system to progressively reveal and detect underlying content objects that would otherwise be obscured, directly resolving the contradiction between detection accuracy and process complexity by breaking down the complex task of detecting overlapped objects into manageable sequential steps

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies preliminary action by detecting and removing foreground content objects in earlier iterations before attempting to detect underlying objects. This preliminary removal of obscuring elements enables more accurate detection of previously hidden content in subsequent iterations, improving overall detection accuracy without requiring overly complex simultaneous detection algorithms

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If foreground content objects are removed iteratively to detect underlying objects, then detection accuracy improves, but processing time increases

Engineering Contradiction:

Improvedetection accuracy of underlying content objectsVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial action by performing document decomposition in multiple iterations rather than attempting to detect all objects simultaneously. Each iteration performs a partial decomposition by removing only the detected foreground objects, which enables accurate detection of underlying objects without requiring the excessive computational resources of a fully simultaneous multi-object detection approach

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12340166B2Document decomposition based on determined logical visual layering of document content

Publication Date: 2025.06.24 ADOBE INC

AI summary

Techniques for document decomposition based on determined logical visual layering of document content. The techniques include iteratively identifying a plurality of logical visual layers of a document resulting in each logical visual layer being associated with one or more document content objects of the document. The one or more document content objects associated with each logical visual layer are annotated to be indicative of the associated logical visual layer. The document is then displayed with an indication of one or more of the annotated document objects.