What does this research mean for the field?

An automated pupil-position tracking and fundus autofocusing system utilizing a YOLO-based detector and image sharpness metrics enables high-speed (15 fps) and highly accurate (121 μm alignment error) fundus image acquisition for portable cameras. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Develop an automated pupil tracking and autofocusing system using a compact fundus camera to enable reliable retinal disease screening in teleophthalmology.

August 27, 2026Journal of the korean society of manufacturing technology engineersOpen Access

Automated Pupil Center Tacking Method and Autofocusing Algorithm for Fundus Image Acquisition

View Full Paper

Ask AI

Bookmark

Authors

YKYongsang Kim MCMin-June Cho KKKihyun Kım

Discussion

Member takes

Overview

Experimental validation demonstrates real-time pupil tracking and rapid autofocusing in a portable fundus camera system, highlighting improved accessibility for retinal disease screening.

Key Points

Develop an automated pupil tracking and autofocusing system using a compact fundus camera to enable reliable retinal disease screening in teleophthalmology.
Integrated a portable fundus camera, a motorized stage, and a processing computer into an automated prototype.
Implemented real-time pupil center localization using a YOLO-based bounding box detector.
Conducted autofocusing via infrared image sharpness metrics combined with moving average smoothing and open-loop motorized stage control.
Achieved an operational control speed of 15 frames per second.
Attained an optical axis alignment error of approximately 22 pixels (~121 μm).
Produced final white-light fundus images with only 1.7% metric degradation compared to ideal focus conditions.

Cite This Study

Kim et al. (2026) studied this question.

synapsesocial.com/papers/6a8fe9da10c91c1e92621d2e https://doi.org/10.7735/ksmte.2026.35.4.300

View Full Paper

Ask AI

Bookmark

August 27, 2026Journal of the korean society of manufacturing technology engineersOpen Access

Automated Pupil Center Tacking Method and Autofocusing Algorithm for Fundus Image Acquisition

View Full Paper

Ask AI

Bookmark

Authors

YKYongsang Kim MCMin-June Cho KKKihyun Kım

Discussion

Member takes

Overview

Experimental validation demonstrates real-time pupil tracking and rapid autofocusing in a portable fundus camera system, highlighting improved accessibility for retinal disease screening.

Key Points

Develop an automated pupil tracking and autofocusing system using a compact fundus camera to enable reliable retinal disease screening in teleophthalmology.
Integrated a portable fundus camera, a motorized stage, and a processing computer into an automated prototype.
Implemented real-time pupil center localization using a YOLO-based bounding box detector.
Conducted autofocusing via infrared image sharpness metrics combined with moving average smoothing and open-loop motorized stage control.
Achieved an operational control speed of 15 frames per second.
Attained an optical axis alignment error of approximately 22 pixels (~121 μm).
Produced final white-light fundus images with only 1.7% metric degradation compared to ideal focus conditions.

Cite This Study

Kim et al. (2026) studied this question.

synapsesocial.com/papers/6a8fe9da10c91c1e92621d2e https://doi.org/10.7735/ksmte.2026.35.4.300

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark