arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.10029eess.IVphysics.optics
收藏

基于深度学习的低光子数相位恢复

Low Photon Count Phase Retrieval Using Deep Learning

Alexandre Goy, Kwabena Arthur, Shuai Li, George Barbastathis

摘要:

成像系统在低光强下的性能受到散粒噪声的影响,散粒噪声随着光源功率的降低而变得越来越强。在本文中,我们通过实验证明了使用深度神经网络来恢复弱光照射的物体,并在等效信噪比方面表现出比经典Gerchberg-Saxton相位恢复算法更好的性能。关于对象的先验知识隐含地包含在训练数据集中,并且对于接近1的信噪比,特征检测是可能的。我们应用这一原则的相位恢复问题,并成功地恢复对象的最显着的特点,平均每个探测器像素在照明光束中的一个光子。我们还表明,通过用对象的初始估计来训练神经网络,而不是用原始强度测量来训练它,相位重建得到了显着改善。

英文摘要:

Imaging systems' performance at low light intensity is affected by shot noise, which becomes increasingly strong as the power of the light source decreases. In this paper we experimentally demonstrate the use of deep neural networks to recover objects illuminated with weak light and demonstrate better performance than with the classical Gerchberg-Saxton phase retrieval algorithm for equivalent signal over noise ratio. Prior knowledge about the object is implicitly contained in the training data set and feature detection is possible for a signal over noise ratio close to one. We apply this principle to a phase retrieval problem and show successful recovery of the object's most salient features with as little as one photon per detector pixel on average in the illumination beam. We also show that the phase reconstruction is significantly improved by training the neural network with an initial estimate of the object, as opposed as training it with the raw intensity measurement.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑