Shadows in document images are undesirable yet inevitable.They can decrease the clarity and readability of the images.The existing methods for removing shadows from documents still face some challenges,such as the tra...Shadows in document images are undesirable yet inevitable.They can decrease the clarity and readability of the images.The existing methods for removing shadows from documents still face some challenges,such as the traditional heuristics lack universality and the optimization goal of subnetworks is not consistent for multistage deep learning methods.In this paper,we introduce an end-to-end direct document shadow removal network(DDSR-Net),where we employ a 3-layer UNet++as the backbone to extract features from diverse scales.To further improve the performance of DDSR-Net,we integrate the multi-scale attention(MSA)blocks into each node.The MSA block allocates different weights to feature vectors at different positions,achieving automatic feature alignment and significantly enhancing the end-to-end network's ability to handle shadow processing.To verify the effectiveness of the proposed DDSR-Net,qualitative and quantitative experiments are conducted on multiple open-source document shadow removal datasets.The experimental results demonstrate that our method outperforms the existing state-of-the-art methods on these datasets.Our code and models will be released to the public.展开更多
The leakage of sensitive data occurs on a large scale and with increasingly serious impact. It may cause privacy disclosure or even property damage. Password leakage is one of the fundamental reasons for information l...The leakage of sensitive data occurs on a large scale and with increasingly serious impact. It may cause privacy disclosure or even property damage. Password leakage is one of the fundamental reasons for information leakage, and its importance is must be emphasized because users are likely to use the same passwords for different Web application accounts. Existing approaches use a password manager and encrypted Web application to protect passwords and other sensitive data; however, they may be compromised or lack accessibility. The paper presents SecureWeb, which is a secure, practical, and user-controllable framework for mitigating the leakage of sensitive data. SecureWeb protects users＇ passwords and aims to provide a unified protection solution to diverse sensitive data. The efficiency of the developed schemes is demonstrated and the results indicate that it has a low overhead and are of practical use.展开更多
基金supported by the National Natural Science Foundation of China,Youth Fund,China(No.62102318)the Basic Research Programs of Taicang,China,2023(No.TC2023JC23)+2 种基金funded in part by the National Natural Science Foundation of China(No.92267203)in part by the Science and Technology Major Project of Guangzhou,China(No.202007030006)in part by the Program for Guangdong Introducing Innovative and Entrepreneurial Teams,China(No.2019ZT08X214).
文摘Shadows in document images are undesirable yet inevitable.They can decrease the clarity and readability of the images.The existing methods for removing shadows from documents still face some challenges,such as the traditional heuristics lack universality and the optimization goal of subnetworks is not consistent for multistage deep learning methods.In this paper,we introduce an end-to-end direct document shadow removal network(DDSR-Net),where we employ a 3-layer UNet++as the backbone to extract features from diverse scales.To further improve the performance of DDSR-Net,we integrate the multi-scale attention(MSA)blocks into each node.The MSA block allocates different weights to feature vectors at different positions,achieving automatic feature alignment and significantly enhancing the end-to-end network's ability to handle shadow processing.To verify the effectiveness of the proposed DDSR-Net,qualitative and quantitative experiments are conducted on multiple open-source document shadow removal datasets.The experimental results demonstrate that our method outperforms the existing state-of-the-art methods on these datasets.Our code and models will be released to the public.
基金supported by the National Key Basic Research Program of China (No. 2013CB834204)the National Natural Science Foundation of China (Nos. 61672300 and 61772291)+1 种基金the Natural Science Foundation of Tianjin, China (Nos. 16JCYBJC15500 and 17JCZDJC30500)the Open Project Foundation of Information Security Evaluation Center of Civil Aviation, and Civil Aviation University of China (No. CAACISECCA-201702)
文摘The leakage of sensitive data occurs on a large scale and with increasingly serious impact. It may cause privacy disclosure or even property damage. Password leakage is one of the fundamental reasons for information leakage, and its importance is must be emphasized because users are likely to use the same passwords for different Web application accounts. Existing approaches use a password manager and encrypted Web application to protect passwords and other sensitive data; however, they may be compromised or lack accessibility. The paper presents SecureWeb, which is a secure, practical, and user-controllable framework for mitigating the leakage of sensitive data. SecureWeb protects users＇ passwords and aims to provide a unified protection solution to diverse sensitive data. The efficiency of the developed schemes is demonstrated and the results indicate that it has a low overhead and are of practical use.
