Cascade learning from adversarial synthetic images for accurate pupil detection
Cascade learning from adversarial synthetic images for accurate pupil detection
复制标题
从对抗性合成图像中进行级联学习，以实现准确的瞳孔检测
DOI：
10.1016/j.patcog.2018.12.014
复制
发表时间：
2019-04-01
影响因子：
8
通讯作者：
Ji, Qiang
中科院分区：
文献类型：
--
作者：
Gou, Chao;Zhang, Hui;Ji, Qiang
基于图像的瞳孔检测是当前计算机视觉领域的一个研究热点，其目的是在图像中确定瞳孔的位置。基于学习的方法可以在大量的训练数据中获得较好的效果。然而，具有准确眼中心注释的公开可用数据集有限，手动标记大量训练数据是不可靠且耗时的。在本文中，受并行视觉框架中的合成数据学习的启发，我们引入了一个基于生成对抗网络（GAN）的并行成像步骤来生成对抗合成图像。特别地，我们使用对抗训练方案通过改进的SimGAN来细化合成的眼睛图像。对于计算实验，我们进一步提出了一个从粗到细的瞳孔检测框架，该框架基于从对抗性合成图像学习的形状增强级联回归模型。在BioID、GI4E和LFW基准数据库上的实验表明，通过利用级联回归和对抗性图像合成的能力，所提出的工作比其他最先进的方法表现得更好。(C)2018爱思唯尔有限公司版权所有。
Image-based pupil detection, which aims to find the pupil location in an image, has been an active research topic in computer vision community. Learning-based approaches can achieve preferable results given large amounts of training data with eye center annotations. However, there are limited publicly available datasets with accurate eye center annotations and it is unreliable and time-consuming for manually labeling large amounts of training data. In this paper, inspired by learning from synthetic data in Parallel Vision framework, we introduce a step of parallel imaging built upon Generative Adversarial Networks (GANs) to generate adversarial synthetic images. In particular, we refine the synthetic eye images by the improved SimGAN using adversarial training scheme. For the computational experiments, we further propose a coarse-to-fine pupil detection framework based on shape augmented cascade regression models learning from the adversarial synthetic images. Experiments on benchmark databases of BioID, GI4E, and LFW show that the proposed work performs significantly better over other state-of-the-art methods by leveraging the power of cascade regression and adversarial image synthesis. (C) 2018 Elsevier Ltd. All rights reserved.