Pixel-Region Adjacency Graphs for Tiled Watershed Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Marker-based watershed segmentation algorithms consume excessive computational resources when applied to large images generated by scientific instruments, and existing techniques fail to generate region adjacency graphs (RAGs) in a tiled context, leading to inconsistencies and 'leaks' in segmentation results.

Innovation Solution

The method involves constructing pixel-region adjacency graphs (PRAGs) by converting image tiles into pixel adjacency graphs (PAGs), generating minimum spanning forests, flagging border and interior trees, and merging these into a region adjacency graph (RAG) through border region merging and interior region condensation, enabling marker-based watershed segmentation in a tiled fashion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If marker-based watershed segmentation is applied to large images, then segmentation accuracy is improved, but computational resource consumption increases excessively

Engineering Contradiction:

Improvesegmentation accuracyVSAvoidcomputational resource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The large image is divided into multiple smaller tiles, and the RAG construction is performed independently on each tile. This segmentation approach reduces the computational burden on each processing unit while maintaining overall segmentation accuracy through coordinated merging of results from adjacent tiles.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces a hierarchical dimension by constructing RAG at two levels: pixel-region adjacency graphs at the tile level, and then merging them into a global region adjacency graph. This dimensional transformation allows efficient local processing while preserving global contextual relationships.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Productivity

If existing techniques are used to generate region adjacency graphs, then processing speed is maintained, but segmentation consistency deteriorates due to leaks and inconsistencies

Engineering Contradiction:

Improveprocessing speedVSAvoidsegmentation consistency

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

Border regions are identified and flagged during the local RAG construction phase before merging. This preliminary action ensures that adjacent tiles can properly connect their border regions, preventing segmentation leaks and maintaining consistency across tile boundaries without requiring reprocessing.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The merging process incorporates feedback from border region analysis, where information about adjacent tiles' border regions is used to adjust and refine the global RAG structure. This feedback mechanism ensures that segmentation boundaries remain consistent across tile boundaries.

Inventive Principle:

Principle #23Feedback

Data Source

PatentEP4618015A1Tiled region adjacency graph computation via pixel-region adjacency graphs

Publication Date: 2025.09.17 FEI CO

Figure 1
Figure 2
Figure 3

AI summary

Systems or techniques are provided for facilitating tiled region adjacency graph computation via pixel-region adjacency graphs. In various embodiments, a system can access an image generated by a scientific instrument. In various aspects, the system can perform marker-based watershed segmentation on a region adjacency graph of the image, wherein the region adjacency graph can be constructed from a plurality of pixel-region adjacency graphs respectively corresponding to a plurality of tiles of the image.