arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.13864cs.CVeess.IV
收藏

图像分类中的非均匀散焦消除

Nonuniform Defocus Removal for Image Classification

Delft University of Technology(代尔夫特理工大学);Can Tho University(芹苴大学);Flexible Optical B.V.

Nguyen Hieu Thao, Oleg Soloviev, Jacques Noom, Michel Verhaegen

摘要:

提出并研究了基于机器学习算法的单帧非等晕反卷积图像分类问题,即非均匀散焦去除(NDR)问题。对NDR问题进行了数学分析,提出了解决该问题的散焦消除算法。DR算法的全局收敛性建立在不施加任何不可验证的假设。仿真数据的数值结果显示DR的显着特点,包括可解性,噪声鲁棒性,收敛性,模型不敏感性和计算效率。实验数据验证了NDR问题的物理相关性和DR算法的实用性。回到应用程序,最初动机的NDR问题的调查,我们表明,DR算法可以提高使用卷积神经网络分类失真图像的准确性。本文的主要区别相比,大多数现有的单帧非等晕反卷积的工作是,新的方法不需要的数据图像分解成等晕子区域。因此,解决方案的方法划分成等晕区的图像是不适用于NDR问题和那些处理整个图像,如DR算法需要开发和分析。

英文摘要:

We propose and study the single-frame anisoplanatic deconvolution problem associated with image classification using machine learning algorithms, named the nonuniform defocus removal (NDR) problem. Mathematical analysis of the NDR problem is done and the so-called defocus removal (DR) algorithm for solving it is proposed. Global convergence of the DR algorithm is established without imposing any unverifiable assumption. Numerical results on simulation data show significant features of DR including solvability, noise robustness, convergence, model insensitivity and computational efficiency. Physical relevance of the NDR problem and practicability of the DR algorithm are tested on experimental data. Back to the application that originally motivated the investigation of the NDR problem, we show that the DR algorithm can improve the accuracy of classifying distorted images using convolutional neural networks. The key difference of this paper compared to most existing works on single-frame anisoplanatic deconvolution is that the new method does not require the data image to be decomposable into isoplanatic subregions. Therefore, solution approaches partitioning the image into isoplanatic zones are not applicable to the NDR problem and those handling the entire image such as the DR algorithm need to be developed and analyzed.

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。

↑