Microscope Image Stitching Using Track Lines for Pixel Accuracy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image stitching methods lack measurement standards, leading to difficulties in achieving high accuracy for large-scale image stitching, particularly in gene sequencing applications.

Innovation Solution

An image stitching method utilizing unique track line features to construct an absolute reference frame, incorporating track cross and track line detection algorithms for precise coordinate adjustments, ensuring pixel-level accuracy and high operational efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If image stitching is performed using conventional methods, then the stitching process can be completed, but the accuracy is insufficient due to cumulative errors from multiple stitching processes

Engineering Contradiction:
Improveimage stitching accuracyVSAvoidstitching process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the stitching process into two distinct stages: first stitching multiple sub-images into an intermediate image, then stitching multiple intermediate images into a final panoramic image. This segmentation allows error correction between stages and prevents cumulative errors from propagating throughout the entire stitching process, thereby improving overall stitching accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by establishing reference lines and calculating transformation parameters before actual image stitching occurs. By pre-calculating the geometric relationships and transformation matrices between images, the system prepares accurate alignment data in advance, which significantly improves stitching precision while reducing computational complexity during the actual stitching operation.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If multiple stitching processes are performed to achieve high accuracy, then stitching accuracy improves, but the time consumption increases

Engineering Contradiction:
Improveimage stitching accuracyVSAvoidstitching time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent divides the stitching operation into segmented stages (sub-image to intermediate image, then intermediate images to final panoramic image), allowing parallel processing of multiple intermediate images simultaneously. This segmentation strategy reduces overall processing time while maintaining high accuracy through staged error correction.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary calculations of transformation parameters and reference lines before the actual stitching operation. By pre-computing alignment data and transformation matrices, the system reduces the computational burden during the stitching execution phase, thereby decreasing time consumption while preserving stitching accuracy.

Inventive Principle:
Principle #10Preliminary action

3Ease of manufacture

If conventional stitching methods are used, then the process is simpler, but the generated panoramic image has lower quality

Engineering Contradiction:
Improvestitching process simplicityVSAvoidpanoramic image quality
Core Design Contradiction:
Ease of manufactureVSManufacturing precision

Solution Approach 1:

The patent implements a segmented two-stage stitching process that maintains relative simplicity while dramatically improving output quality. The first stage creates intermediate images from sub-images, and the second stage combines intermediate images into the final panoramic image. This segmentation enables quality improvement through error correction at each stage without requiring overly complex processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent incorporates feedback mechanisms by using detected reference lines and calculated transformation parameters to correct alignment errors between stitching stages. The system continuously refines the positioning and orientation of images based on feedback from feature detection and matching, thereby improving panoramic image quality while maintaining a relatively simple overall process structure.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4550255B1Image stitching method, and gene sequencing system and corresponding gene sequencer
Publication Date: 2026.05.06 BGI SHENZHEN CO LTD
  • EP4550255B1 patent drawingFigure 1
  • EP4550255B1 patent drawingFigure 2~3
  • EP4550255B1 patent drawingFigure 4~5b

AI summary

The present disclosure provides a method for image stitching, the method comprises: obtaining multiple first images of a sample and template information about the track line or track cross of the sample; pre-stitching the multiple first images to obtain the pre-stitching coordinates of the multiple first images; selecting at least one second image from the multiple first images based on the characteristic of track line or track cross, and deriving a global template based on the template information of the sample and the pre-stitching coordinates of the second image; and for a third image other than the second image among the multiple first images , calculating the offset between the pre-stitching coordinates of the third image and the corresponding template coordinates of the third image in the global template, and adjusting the coordinates of the third image based on the offset, so as to stitch and generate a stitched image about the sample. The present disclosure further provides a gene sequencing system, a gene sequencer, a computer device, and a computer storage medium. By using the image stitching method of the present invention, it can enable the stitched images of the microscope to reach higher accuracy, reduce stitching errors, and improve stitching efficiency through the recognition of track line features in the images, and thus can become a reliable standard in the field of image stitching.