A new eye segmentation method based on improved U2Net in TCM eye diagnosis

TL;DR

This paper introduces an improved U2Net-based Res-UNet model for eye segmentation in Chinese medicine diagnosis, achieving high accuracy and efficiency on public datasets, and providing a foundation for further visual diagnostic applications.

Contribution

The paper proposes a novel Res-UNet architecture based on U2Net, combined with data augmentation, to enhance eye segmentation accuracy and reduce model size for Chinese medicine diagnosis.

Findings

Miou reaches 97.8% on UBIVIS.V1 dataset

F1-Score reaches 99.09% with RGB 320x320 images

Small-scale Res-UNet achieves similar performance with fewer parameters

Abstract

For the diagnosis of Chinese medicine, tongue segmentation has reached a fairly mature point, but it has little application in the eye diagnosis of Chinese medicine.First, this time we propose Res-UNet based on the architecture of the U2Net network, and use the Data Enhancement Toolkit based on small datasets, Finally, the feature blocks after noise reduction are fused with the high-level features.Finally, the number of network parameters and inference time are used as evaluation indicators to evaluate the model. At the same time, different eye data segmentation frames were compared using Miou, Precision, Recall, F1-Score and FLOPS. To convince people, we cite the UBIVIS. V1 public dataset this time, in which Miou reaches 97.8%, S-measure reaches 97.7%, F1-Score reaches 99.09% and for 320*320 RGB input images, the total parameter volume is 167.83 MB,Due to the excessive number of parameters, we experimented with a small-scale U2Net combined with a Res module with a parameter volume of 4.63 MB, which is similar to U2Net in related indicators, which verifies the effectiveness of our structure.which achieves the best segmentation effect in all the comparison networks and lays a foundation for the application of subsequent visual apparatus recognition symptoms.