Real-time abnormal eye blinking eye detection using y-unet

Sathiya Priya S.; J. G. R. Sathiaseelan

Author(s)

Sathiya Priya S. Department of Computer Science, Bishop Heber College,Trichy,India

J. G. R. Sathiaseelan Department of Computer Science, Bishop Heber College,Trichy,India

Abstract

The Yolov5 uses the self-adaptive anchor method instead of the traditional calculation method. Instead of calculating the anchor size based on the dataset label, it can also set the anchor size as a parameter. Unet is popularly used in medical image segmentation. In this article, we will introduce a new approach for the end-to-end extraction of the eyelid. It is a process that involves three steps, namely, de-noising, preliminary extraction, and precise eyelid segmentation. Y-UNet are both useful tools for identifying small targets. In addition, their ability to effectively segment or adhesive eyelid has been optimized. We optimized the overlap between U-Net and YOLOv5 for eye blinking. The objects detected in the yolov5 model that is higher version of Yolo should be masked on the images processed by the U-Net model with color segmentation of each objects. Moreover, in a preprocessing stage we use Kalman filter is very fast and are well suited for real time problems and embedded systems. This filter is a simple algorithm that predicts and separates random signals from noise. It can also detect the presence of noise and prevent it from generating an error. Automatic eye blinking detection is an important component of glaucoma diagnosis. In this research, Human eye blinking ratio calculation mainly used for detection of abnormal eye at early stage using our proposed Y-Unet model.

Publication Details

Page(s) 742-750

DOI DOI not available

Published Journal: ARPN Journal of Engineering and Applied Sciences, Volume: 17, Issue: 7, Year: 2022

Request the full text from PASTIC

Keywords

Kalman Filter, U-Net, sensitive mirror analyzer and retina tracker (SMART) system, yolov5

References

Redmon J.,Divvala S.,Girshick R.,Farhadi A. .2016 .You Only Look Once: Unified, Real-Time Object Detection. , : .

Malta A.,Mendes M.,Farinha T. .221 .Augmented Reality Maintenance Assistant Using YOLOv5. Applied Sciences, 11(11) : 4758.

Liu K.,Tang H.,He S.,Yu Q.,Xiong Y.,Wang N. .2021 .Performance Validation of Yolo Variants for Object detection. Bioinformatics and Intelligent Computing., : .

Bochkovskiy Alexey .2004 .YOLOv4: Optimal Speed and Accuracy of Object Detection. , : .

Buric M.,Pobar M.,Ivasic-Kos M.,Mask R-CNN M. .2018 .Ball Detection Using Yolo. Computational Science and Computational Intelligence., : .

Huang He .2019 .TF-YOLO: An Improved Incremental Network for Real-Time Object Detection. Applied Sciences, 9(16) : 3225.

Pan L.,Liu M.,Hartley R. .2020 .Single Image Optical Flow Estimation with an Event Camera. , : .

Locke A.,Fitzgerald S.,Mahadevan-Jansen A. .2020 .Advances in Optical Detection of HumanAssociated Pathogenic Bacteria. , 25(22) : 5256.

Ryan C.,O'Sullivan B.,Elrasad A.,Cahill A.,Lemley J.,Kielty P.,Perot E . .Real-time face & eye tracking and blink detection using event cameras. Neural Networks, Elsevier, 141 : 87-97.

Wentao Liu,Bin Zhou Ziren,Gong Ziren .2021 .Real-time Signal Light Detection based on Yolov5 for Railway. IOP Conference Series: Earth and Environmental Science. Sci, 769 : .

Malta A.,Mendes M.,Farinha T. .2021 .Augmented Reality Maintenance Assistant Using YOLOv5. Applied Sciences, 11(11) : 4758.

Yang G.,Feng W.,Jin J.,Lei Q.,Li X.,Gui G.,Wang W. .2021 .Face Mask Recognition System with YOLOV5 Based on Image Recognition. , : .

Amran Hossain,Almutairi Ali F. .2021 .A Deep Learning Model to Clssify and Detect Brain Abnormalities in Portable Microwave Based Imaging System. , : .

Linlin Zhu,Li Zheng,Liu Chun .2021 .Improving YOLOv5 with Attention Mechanism for Detecting Boulders from Planetary Images. Remote Sens, 13 : 3776.

Liu K.,Tang H.,He S.,Yu Q.,Xiong Y.,Wang N. .2021 .Performance Validation of Yolo Variants for Object Detection. Proceedings of the 2021 International Conference on Bioinformatics and Intelligent Computing, : 22-24.

Yu Luo,Chen Xiaohui .2021 .Intelligent Solutions in Chest Abnormality Detection Based on YOLOv5 and ResNet50. , : .

Yao J.,Qi J.,Shao H.,Yang J.,Li X. . .A Real-Time Detection Algorithm for Kiwifruit Defects Based on YOLOv5. Electronics, 10(14) : 1711.

Bai H.,Lu C.,Chen W.,Xu F,Han Z.-B F .2020 .Chromosome Extraction Based on U-Net and YOLOv3. IEEE Access, 8 : 178563-178569.

Araújo T.,Aresta G.,Galdran A.,Costa P.,Mendonça A. M.,Campilho A. .2018 .. Object Detection and Segmentation in Biomedical Images. Lecture Notes in Computer Science, 165 : 173.

Orban de Xivry J.-J. ,Coppe S.,Blohm G.,Lefevre P. .2013 .Kalman Filtering Naturally Accounts for Visually Guided and Predictive Smooth Pursuit Dynamics. Journal of Neuroscience, 33(44) : 17301-17313.

Afef Salhi,Fakhfakh Ahmed .2020 .Estimation for Motion in Tracking and Detection Objects with Kalman Filter. , : .

Lee D ,Shin J.-S.,Jung J.-H.,Park S J.-H.,Oh S J.-H.,Lee I.-S. .2017 .Real-time lane detection and tracking system using simple filter and Kalman filter. 2017 Ubiquitous and Future Networks (ICUFN).. , : .

Lamba P. S.,Virmani D.,Castillo O. .2020 .Multimodal human eye blink recognition method using feature level fusion for exigency detection. Soft Computing, 24(22) : 16829-16845.

Rahman A.,Sirshar M.,Khan A. .2015 .Real time drowsiness detection using eye blink monitoring. National Software Engineering., : .

Ousler G.,Abelson M. B.,Johnston P. R.,Rodriguez J.,Lane K.,Smith L. M. .2014 .Blink patterns and lid-contact times in dry-eye and normal subjects. Clinical Ophthalmology, 10 : .

Priya S. Sathiya,Seelan Dr. J.G.R. Sathia .2020 .Ocular Perceiver Blink Interval through SMART system with RDDS using Deep Learning. Adalya Journal, 1301(2) : .