会议专题

Iterative First-Order Reverse Image Filtering

  In this paper,we study an unconventional but practically mean-ingful problem reverse image filtering,which aims at removing the filtering effects with the given image filter.We propose an iterative first-order reverse image filtering algorithm based on the Newton-Raphson method.The convergence of the proposed iterative proce-dure is verified via extensive experiments.The experimental results show that our method could effectively reverse many prevalent image filters.Our method finds its practical usage in many ap-plications,such as non-blind image deblurring and image details recovery.Furthermore,our method could probe the behaviors of black-box image filtering systems,which poses security concerns on the protection for the privately commercial image filters.

Reverse image filtering Newton-Raphson method

Li Dong Jiantao Zhou Cuiming Zou Yulong Wang

Faculty of Electrical Engineering and Computer Science Ningbo University,Ningbo,China Department of Computer and Information Science University of Macau,Macau,China School of Information Science and Engineering Chengdu University,Chengdu,China

国际会议

2019国图灵大会(ACM Turing Celebration conference-China 2019 )

成都

英文

883-887

2019-05-17(万方平台首次上网日期,不代表论文的发表时间)