A strabismus nine-orientation image classification method and system

By introducing eye pose correction and iris localization mechanisms into the nine-directional strabismus image classification, and combining the mutual exclusion characteristics among the nine directions, the problem of poor reliability in eye image classification is solved, and accurate localization and classification of the iris position in eye images are achieved.

CN122416097APending Publication Date: 2026-07-17ZHONGSHAN OPHTHALMIC CENT SUN YAT SEN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610411656.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-31
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

In the current technology for classification of strabismus images in nine directions, the reliability of eye image classification is poor. This is mainly because eye images contain a lot of irrelevant information and key features are not obvious, resulting in small differences between images of different eye positions and interference from shadows or other anatomical structures.

Method used

The eye image boundary is identified in a preset coordinate system by a preset recognition algorithm. An eye pose correction mechanism and an iris localization mechanism are introduced to calculate the iris centroid. The classification is performed by combining the mutual exclusion characteristics between the nine directions to improve the reliability of eye image classification.

Benefits of technology

It achieves accurate localization and classification of the iris position in eye images, reduces interference from irrelevant information, and improves the reliability of eye image classification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122416097A_ABST
    Figure CN122416097A_ABST
Patent Text Reader

Abstract

The application provides a strabismus nine-orientation image classification method and system, which comprises the following steps: based on a preset recognition algorithm and a pre-constructed coordinate system, boundary recognition is performed on a pre-acquired eye image to obtain initial left eye boundary box coordinates and initial right eye boundary box coordinates, a deviation angle is calculated and the eye image is corrected according to the deviation angle to obtain target left eye boundary box coordinates and target right eye boundary box coordinates; based on a preset centroid algorithm and the corrected eye image, target left eye iris centroid coordinates and target right eye iris centroid coordinates are calculated; a preset prediction model is used to obtain a nine-orientation distribution probability of the eye image; based on preset nine-orientation mutual exclusion requirements and the nine-orientation distribution probability of the eye image, the eye image is classified to obtain a strabismus nine-orientation image classification result. The application realizes accurate positioning of the iris position of the eye image, reduces irrelevant information interference, and classifies the iris by combining the mutual exclusion characteristics among the nine orientations, thereby improving the reliability of the eye image classification.
Need to check novelty before this filing date? Find Prior Art