Pupil localization for ophthalmic diagnosis using anchor ellipse regression

Horng Horng Lin, Zheng Yi Li, Min-Hsiu Shih, Yung-Nien Sun, Ting Li Shen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent developments of deep neural networks, such as Mask R-CNN, have shown significant advances in simultaneous object detection and segmentation. We thus apply deep learning to pupil localization for ophthalmic diagnosis and propose a novel anchor ellipse regression approach based on region proposal network and Mask R-CNN for detecting pupils, estimating pupil shape parameters, and segmenting pupil regions at the same time in infrared images. This new extension of anchor ellipse regression for Mask R-CNN is demonstrated to be effective in size and rotation estimations of elliptical objects, as well as in object detections and segmentations, by experiments. Temporal pupil size estimations by using the proposed approach for normal and abnormal subjects give meaningful indices of pupil size changes for ophthalmic diagnosis.

Original languageEnglish
Title of host publicationProceedings of the 16th International Conference on Machine Vision Applications, MVA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9784901122184
DOIs
Publication statusPublished - 2019 May 1
Event16th International Conference on Machine Vision Applications, MVA 2019 - Tokyo, Japan
Duration: 2019 May 272019 May 31

Publication series

NameProceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

Conference

Conference16th International Conference on Machine Vision Applications, MVA 2019
CountryJapan
CityTokyo
Period19-05-2719-05-31

Fingerprint

Anchors
Masks
Infrared radiation
Experiments
Object detection

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Lin, H. H., Li, Z. Y., Shih, M-H., Sun, Y-N., & Shen, T. L. (2019). Pupil localization for ophthalmic diagnosis using anchor ellipse regression. In Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019 [8757976] (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/MVA.2019.8757976
Lin, Horng Horng ; Li, Zheng Yi ; Shih, Min-Hsiu ; Sun, Yung-Nien ; Shen, Ting Li. / Pupil localization for ophthalmic diagnosis using anchor ellipse regression. Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019).
@inproceedings{fb8583261fca4c7083ff47935fa9e729,
title = "Pupil localization for ophthalmic diagnosis using anchor ellipse regression",
abstract = "Recent developments of deep neural networks, such as Mask R-CNN, have shown significant advances in simultaneous object detection and segmentation. We thus apply deep learning to pupil localization for ophthalmic diagnosis and propose a novel anchor ellipse regression approach based on region proposal network and Mask R-CNN for detecting pupils, estimating pupil shape parameters, and segmenting pupil regions at the same time in infrared images. This new extension of anchor ellipse regression for Mask R-CNN is demonstrated to be effective in size and rotation estimations of elliptical objects, as well as in object detections and segmentations, by experiments. Temporal pupil size estimations by using the proposed approach for normal and abnormal subjects give meaningful indices of pupil size changes for ophthalmic diagnosis.",
author = "Lin, {Horng Horng} and Li, {Zheng Yi} and Min-Hsiu Shih and Yung-Nien Sun and Shen, {Ting Li}",
year = "2019",
month = "5",
day = "1",
doi = "10.23919/MVA.2019.8757976",
language = "English",
series = "Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019",
address = "United States",

}

Lin, HH, Li, ZY, Shih, M-H, Sun, Y-N & Shen, TL 2019, Pupil localization for ophthalmic diagnosis using anchor ellipse regression. in Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019., 8757976, Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019, Institute of Electrical and Electronics Engineers Inc., 16th International Conference on Machine Vision Applications, MVA 2019, Tokyo, Japan, 19-05-27. https://doi.org/10.23919/MVA.2019.8757976

Pupil localization for ophthalmic diagnosis using anchor ellipse regression. / Lin, Horng Horng; Li, Zheng Yi; Shih, Min-Hsiu; Sun, Yung-Nien; Shen, Ting Li.

Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8757976 (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Pupil localization for ophthalmic diagnosis using anchor ellipse regression

AU - Lin, Horng Horng

AU - Li, Zheng Yi

AU - Shih, Min-Hsiu

AU - Sun, Yung-Nien

AU - Shen, Ting Li

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Recent developments of deep neural networks, such as Mask R-CNN, have shown significant advances in simultaneous object detection and segmentation. We thus apply deep learning to pupil localization for ophthalmic diagnosis and propose a novel anchor ellipse regression approach based on region proposal network and Mask R-CNN for detecting pupils, estimating pupil shape parameters, and segmenting pupil regions at the same time in infrared images. This new extension of anchor ellipse regression for Mask R-CNN is demonstrated to be effective in size and rotation estimations of elliptical objects, as well as in object detections and segmentations, by experiments. Temporal pupil size estimations by using the proposed approach for normal and abnormal subjects give meaningful indices of pupil size changes for ophthalmic diagnosis.

AB - Recent developments of deep neural networks, such as Mask R-CNN, have shown significant advances in simultaneous object detection and segmentation. We thus apply deep learning to pupil localization for ophthalmic diagnosis and propose a novel anchor ellipse regression approach based on region proposal network and Mask R-CNN for detecting pupils, estimating pupil shape parameters, and segmenting pupil regions at the same time in infrared images. This new extension of anchor ellipse regression for Mask R-CNN is demonstrated to be effective in size and rotation estimations of elliptical objects, as well as in object detections and segmentations, by experiments. Temporal pupil size estimations by using the proposed approach for normal and abnormal subjects give meaningful indices of pupil size changes for ophthalmic diagnosis.

UR - http://www.scopus.com/inward/record.url?scp=85070477800&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070477800&partnerID=8YFLogxK

U2 - 10.23919/MVA.2019.8757976

DO - 10.23919/MVA.2019.8757976

M3 - Conference contribution

AN - SCOPUS:85070477800

T3 - Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

BT - Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lin HH, Li ZY, Shih M-H, Sun Y-N, Shen TL. Pupil localization for ophthalmic diagnosis using anchor ellipse regression. In Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8757976. (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019). https://doi.org/10.23919/MVA.2019.8757976