# ORCNet: A context-based network to simultaneously segment the ocular region components

arXiv: https://arxiv.org/abs/2204.07456 · HTML: https://mlsanity.com/paper/2204.07456/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 98 references that are in the map.
- First posted on arXiv 15 Apr 2022.

## Builds on (most cited first, 14 of 14)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark](https://mlsanity.com/paper/1909.00133/) (2019)
- [Context Encoding for Semantic Segmentation](https://mlsanity.com/paper/1803.08904/) (2018)
- [MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving](https://mlsanity.com/paper/1612.07695/) (2016)
- [Deep TEN: Texture Encoding Network](https://mlsanity.com/paper/1612.02844/) (2016)
- [Ocular Recognition Databases and Competitions: A Survey](https://mlsanity.com/paper/1911.09646/) (2019)
- [A Benchmark for Iris Location and a Deep Learning Detector Evaluation](https://mlsanity.com/paper/1803.01250/) (2018)
- [Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks](https://mlsanity.com/paper/1809.00769/) (2018)
- [Fully Convolutional Networks and Generative Adversarial Networks Applied to Sclera Segmentation](https://mlsanity.com/paper/1806.08722/) (2018)
- [The Impact of Preprocessing on Deep Representations for Iris Recognition on Unconstrained Environments](https://mlsanity.com/paper/1808.10032/) (2018)
- [Simultaneous Iris and Periocular Region Detection Using Coarse Annotations](https://mlsanity.com/paper/1908.00069/) (2019)
- [Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization](https://mlsanity.com/paper/2002.03985/) (2020)

## Abstract (arXiv)

Accurate extraction of the Region of Interest is critical for successful ocular region-based biometrics. In this direction, we propose a new context-based segmentation approach, entitled Ocular Region Context Network (ORCNet), introducing a specific loss function, i.e., he Punish Context Loss (PC-Loss). The PC-Loss punishes the segmentation losses of a network by using a percentage difference value between the ground truth and the segmented masks. We obtain the percentage difference by taking into account Biederman's semantic relationship concepts, in which we use three contexts (semantic, spatial, and scale) to evaluate the relationships of the objects in an image. Our proposal achieved promising results in the evaluated scenarios: iris, sclera, and ALL (iris + sclera) segmentations, utperforming the literature baseline techniques. The ORCNet with ResNet-152 outperforms the best baseline (EncNet with ResNet-152) on average by 2.27%, 28.26% and 6.43% in terms of F-Score, Error Rate and Intersection Over Union, respectively. We also provide (for research purposes) 3,191 manually labeled masks for the MICHE-I database, as another contribution of our work.