PECSA Net: Pupil Segmentation Using Attention Integrated Encoder-based Multi-Level Feature Extractor for Analysis of Ocular Dynamics
- 1Indian Institute of Information Technology, Design and Manufacturing, KancheepuramChennai, India
Abstract
Pupillometry is considered as an emerging technique for analysing the dynamic variations of pupil structure non-invasively. Delineation of the pupil region from ocular images plays a crucial role in the prediction of microexpressions and subtle variations during the analysis. Occlusions, deformations, and motion artifacts are more prevalent during the capture of micro-ocular expressions and often resulting in a suboptimal pupil mask with minimal structural similarity. This proposed study introduces a Swin incorporated modified encoder-decoder paradigm, “PECSA Net” for reliable segmentation of the pupil region. The local features including boundaries and edges, are captured through convolutional layers in the PECSA Net. Moreover, the contextual features including the overall spatial relationship within the ocular images, are captured using the deeper layers consist of an attention-enhanced multiscale contextual information module. Experimental results on CASIA dataset shows that the framework achieves superior performance in occluded conditions compared to conventional neural network-based approaches with a dice score of 0.97. Further, the model is validated with a multifaceted eye tracking dataset captured using high speed camera to evaluate the generalization capability, achieving a dice score of 0.79. Extensive architecture-based ablation studies are also carried out to identify the significance of each component of PECSA Net. Thus, by integrating attention enhanced multi-level feature extractor with an encoder-decoder paradigm, the proposed study provides a robust segmentation under challenging conditions, enabling reliable extraction of features for analyzing pupil dynamics.
Related
- Asymmetric encoder-decoder U-net with hybrid attention and residual dilated convolution for brain tumor segmentation
- Vehicle lane change prediction with explainable soft mask attention mechanism and heterogeneous information encoder
- Automated corneal endothelial cell detection and segmentation in specular microscopy images using Attention and Faster U-Net
- AMF-U-Net: an adaptive multimodal fusion residual attention 3D U-Net for boundary-aware brain tumour segmentation
- Hybrid feature pyramid attention and capsule network (FpaNet+CapsNet) for enhanced spatial and contextual feature extraction for improved brain tumor segmentation
BibTeX
@article{arya2026pecsa,
title = {{PECSA Net: Pupil Segmentation Using Attention Integrated Encoder-based Multi-Level Feature Extractor for Analysis of Ocular Dynamics}},
author = {Choyichivayalil Arya and Veluswamy Pandiyarasan and Palanisamy Rohini},
journal = {Current Directions in Biomedical Engineering},
year = {2026},
month = oct,
doi = {10.1515/cdbme-2026-0123},
url = {https://doi.org/10.1515/cdbme-2026-0123},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - PECSA Net: Pupil Segmentation Using Attention Integrated Encoder-based Multi-Level Feature Extractor for Analysis of Ocular Dynamics
AU - Choyichivayalil Arya
AU - Veluswamy Pandiyarasan
AU - Palanisamy Rohini
PY - 2026
DA - 2026/10/26
JO - Current Directions in Biomedical Engineering
DO - 10.1515/cdbme-2026-0123
UR - https://doi.org/10.1515/cdbme-2026-0123
AB - Pupillometry is considered as an emerging technique for analysing the dynamic variations of pupil structure non-invasively. Delineation of the pupil region from ocular images plays a crucial role in the prediction of microexpressions and subtle variations during the analysis. Occlusions, deformations, and motion artifacts are more prevalent during the capture of micro-ocular expressions and often resulting in a suboptimal pupil mask with minimal structural similarity. This proposed study introduces a Swin incorporated modified encoder-decoder paradigm, “PECSA Net” for reliable segmentation of the pupil region. The local features including boundaries and edges, are captured through convolutional layers in the PECSA Net. Moreover, the contextual features including the overall spatial relationship within the ocular images, are captured using the deeper layers consist of an attention-enhanced multiscale contextual information module. Experimental results on CASIA dataset shows that the framework achieves superior performance in occluded conditions compared to conventional neural network-based approaches with a dice score of 0.97. Further, the model is validated with a multifaceted eye tracking dataset captured using high speed camera to evaluate the generalization capability, achieving a dice score of 0.79. Extensive architecture-based ablation studies are also carried out to identify the significance of each component of PECSA Net. Thus, by integrating attention enhanced multi-level feature extractor with an encoder-decoder paradigm, the proposed study provides a robust segmentation under challenging conditions, enabling reliable extraction of features for analyzing pupil dynamics.
SN - 2364-5504
ER -