检索结果-内蒙古大学图书馆

A screen-shooting resilient document image watermarking scheme using deep neural network

IET image processing 2023年第2期17卷 323-336页

作者： Ge, Sulong Fei, Jianwei Xia, Zhihua Tong, Yao Weng, Jian Liu, Jianan Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing Peoples R China Nanjing Univ Informat Sci & Technol Engn Res Ctr Digital Forens Nanjing Peoples R China Jinan Univ Coll Cyber Secur Guangzhou Peoples R China Guangzhou Fongwell Data Ltd Co Guangzhou Peoples R China

With the advent of the screen-reading era, the confidential documents displayed on the screen can be easily captured by a camera without leaving any traces. Thus, this paper proposes a novel screen-shooting resilient watermarking scheme for document image using deep neural network. By applying this scheme, when the watermarked image is displayed on the screen and captured by a camera, the watermark can be still extracted from the captured photographs. Specifically, the scheme is an end-to-end neural network with an encoder to embed watermark and a decoder to extract watermark. During the training process, a distortion layer between encoder and decoder is added to simulate the distortions introduced by screen-shooting process in real scenes, such as camera distortion, shooting distortion, and light source distortion. Furthermore, a background sensitive loss and a lpips loss are used to improve visual quality of the watermarked document images in the training process. Besides, a strength factor adjustment strategy is also designed to improve the visual quality with little loss of bit extraction accuracy. The experimental results show that the proposed scheme has higher visual quality and robustness than the other two recent state-of-the-art methods.

关键词： feature extraction shooting distortion background sensitive loss camera distortion screen-shooting resilient document image watermarking distortion layer Document processing and analysis techniques image and video coding bit extraction Neural nets image watermarking computer vision and image processing techniques strength factor adjustment end-to-end neural network confidential documents deep learning (artificial intelligence) document image processing Data security deep neural network watermark extraction lpips loss light source distortion screen-reading era visual quality

来源：评论

学校读者我要写书评

暂无评论

Characterisation framework for epileptic signals

引用

IET image processing 2012年第9期6卷 1227-1235页

作者： Vazquez, D. M. Rubio, J. J. Pacheco, J. Inst Politecn Nacl ESIME Azcapotzalco Secc Estudios Posgrad & Invest Mexico City 02250 DF Mexico

In this study, two epileptic signals are extracted from scanned images and three algorithms are proposed to characterise epileptic signals: the modified least squares, modified nearest neighbour, and slopes algorithms... 详细信息

关键词： modified least squares slopes algorithms computer vision and image processing techniques image processing scanned images Signal processing and detection characterisation framework Optical, image and video signal processing modified nearest neighbour epileptic signals

来源：评论

学校读者我要写书评

暂无评论

Edge detection of colour image based on quaternion fractional differential

引用

IET image processing 2011年第3期5卷 261-272页

作者： Gao, C. B. Zhou, J. L. Hu, J. R. Lang, F. N. Sichuan Univ Sch Comp Sci Chengdu 610064 Peoples R China Chengdu Univ Coll Comp Sci & Technol Chengdu 610106 Peoples R China Chengdu Univ Lab Commun & Informat Syst Chengdu 610106 Peoples R China

According to the development of the real fractional differential and its applications in the modern signal processing, the authors extend it to quaternion body and put forward a new concept: quaternion fractional differential (QFD), and apply it to edge detection of colour image. This method is called edge detection based on QFD. Simulation experiments indicate that this method has special advantages. Furthermore, the authors give an indicator to evaluate the effectiveness of different edge filters. Comparing with Sobel and mix edges of real fractional differential to every channels of colour image, they discover that QFD has fewer false negatives in the textured regions and is also better at detecting edges that are partially defined by texture, which means the authors can obtain much better results in the interesting regions using QFD and is more consistent with the characteristics of human visual system.

关键词： modern signal processing edge detection quaternion fractional differential image recognition computer vision and image processing techniques quaternion body colour image Filtering methods in signal processing image texture filtering theory image colour analysis edge filters human visual system

来源：评论

学校读者我要写书评

暂无评论

Characterisation of tool marks on cartridge cases by combining multiple images

引用

IET image processing 2012年第7期6卷 854-862页

作者： Leloglu, U. M. TUBITAK UZAY TR-06531 Ankara Turkey

The characteristic marks left by firearms on cartridge cases (CCs) during firing are used by forensic experts to identify CCs fired from the same firearm;however, the nature of the tool marks on the CCs is not well understood. The objective of this study is to separate the tool marks i.e., the signal, from the background signal and the noise and thereby understand its peculiarities. To extract the signal, which is much weaker than the noise, second-order derivatives of three-dimensional images of the surfaces of a series of CCs fired from the same firearm were used. Instead of using rigid body transformation, the images are first registered based on estimated planar homographies;then unwanted areas, including the headstamp are masked out. Aligned images are merged by weighted averaging using estimated signal and noise variances, which are also used for calculating signal and noise spectra. Wiener filtering is applied to further increase the signal-to-noise ratio. The effectiveness of the method is demonstrated on real data. It is also shown that breech face marks exist on the outer ring, a feature typically ignored in automatic matching. In addition, visual results obtained by reconstructing the surface from second-order derivatives are presented.

关键词： forensic experts Filtering methods in signal processing Military circuits, components, and equipment firearm second order derivatives computer vision and image processing techniques image processing planar homographies estimation Optical, image and video signal processing Wiener filters weapons noise variances three-dimensional images background signal signal-to-noise ratio CC automatic matching law Military engineering computing tool mark characterisation noise spectra signal extraction Wiener filtering military computing cartridge cases

来源：评论

学校读者我要写书评

暂无评论

Dual-view 3D human pose estimation without camera parameters for action recognition

引用

IET image processing 2021年第14期15卷 3433-3440页

作者： Liu, Long Yang, Le Chen, Wanjun Gao, Xin Xian Univ Technol Sch Automat & Informat Engn 5 Jinhua South Rd Xian Shaanxi Peoples R China Xian Univ Technol Dept Informat Sci Xian Shaanxi Peoples R China

The purpose of 3D human pose estimation is to estimate the 3D coordinates of key points of the human body directly from images. Although multi-view based methods have better performance and higher precision of coordinate estimation than a single-view based, they need to know the camera parameters. In order to effectively avoid the restriction of this constraint and improve the generalizability of the model, a dual-view single-person 3D pose estimation method without camera parameters is proposed. This method first uses the 2D pose estimation network HR-net to estimate the 2D joint point coordinates from two images with different views, and then inputs them into the 3D regression network to generate the final 3D joint point coordinates. In order to make the 3D regression network fully learn the spatial structure relationship of the human body and the transformation projection relationship between different views, a self-supervised training method is designed based on a 3D human pose orthogonal projection model to generate the virtual views. In the pose estimation experiments on the Human3.6 dataset, this method achieves a significantly improved estimation error of 34.5 mm. Furthermore, an action recognition based on the human poses extracted by the proposed method is conducted, and an accuracy of 83.19% is obtained.

关键词： image recognition image sensors computer vision and image processing techniques Regression analysis Regression analysis Machine learning (artificial intelligence)

来源：评论

学校读者我要写书评

暂无评论

Removal of non-uniform complex and compound shadows from textured surfaces using adaptive directional smoothing and the thin plate model

引用

IET image processing 2011年第3期5卷 233-248页

作者： McFeely, R. Hughes, C. Jones, E. Glavin, M. Natl Univ Ireland Connaught Automot Res Grp Coll Engn & Informat Galway Ireland Valeo Vis Syst Tuam Co Galway Ireland

In this study, the authors propose a novel algorithm for removing complex shadows from textured surfaces within a single image. Previous shadow removal methods have attempted to solve this problem under a range of criteria, such as the type and number of light sources and shadow structure. Some methods require that the shadow umbra and penumbra be well defined. They have been shown to work best when the umbra is relatively large and when the penumbra is of a limited size and shape. However, these methods can fail if the shadow shape or form diverges from the norm. Many methods also require user intervention to locate whole or parts of the shadow. The authors propose a flexible shadow removal model which is capable of functioning without these limiting assumptions, or the need for user intervention. It is also capable of dealing with shadows cast on a wide range of textured surfaces. It uses a directional differential filter along with directional smoothing to find the shadow and a thin plate reconstruction model to remove shadows from an image surface. Results have shown that the proposed algorithm generates high-quality shadow-free images over a range of scenarios, such as multiple light sources, occlusions and textures.

关键词： nonuniform complex shadow removal textured surfaces thin plate model directional differential filter computer vision and image processing techniques adaptive directional smoothing nonuniform compound shadow removal Filtering methods in signal processing image texture Optical, image and video signal processing filtering theory smoothing methods

来源：评论

学校读者我要写书评

暂无评论

Features detection assisted spectrum sensing in wireless regional area network cognitive radio systems

引用

IET COMMUNICATIONS 2012年第8期6卷 810-818页

作者： Chin, W. -L. Kuo, H. -C. Chen, H. -H. Natl Cheng Kung Univ Dept Engn Sci Tainan 70101 Taiwan

Spectrum sensing is a key enabling technique for implementing cognitive radio (CR) networks. Based on the detection of primary users' signals, a CR can fully exploit wireless radio resources, thus to increase spectrum efficiency and allow opportunistic transmissions for secondary users. This work presents a spectrum sensing approach for its applications in a wireless regional area network (WRAN) based on features detection of advanced television systems committee (ATSC) digital TV and WRAN signals over a Rayleigh fading channel. The scheme aims at detecting and identifying both ATSC and WRAN signals. To improve spectrum sensing performance in low-signal-to-noise ratio (SNR) regions, the characteristics of both ATSC and WRAN signals are exploited in spectrum sensing algorithms based on a correlation-based feature identification approach. In this study, real working scenarios of a WRAN CR network are considered. The effectiveness of the proposed detector has been verified by simulations.

关键词： computer vision and image processing techniques correlation-based feature identification opportunistic transmissions cognitive radio systems Television and video equipment, systems and applications advanced television systems committee Optical, image and video signal processing wireless regional area network feature extraction feature detection wireless radio resources WRAN signals digital TV spectrum sensing algorithms secondary users digital television Radio links and equipment cognitive radio low-signal-to-noise ratio Rayleigh fading channel Rayleigh channels ATSC

来源：评论

学校读者我要写书评

暂无评论

Speckle reduction with edges preservation for ultrasound images: using function spaces approach

引用

IET image processing 2012年第7期6卷 813-821页

作者： Lee, M. -S. Yen, C. -L. Ueng, S. -K. Natl Taiwan Ocean Univ Dept Comp Sci & Engn Keelung Taiwan Keelung Chang Gung Mem Hosp Dept Internal Med Keelung Taiwan

In this study, a novel speckle reduction method is proposed for ultrasound images. This denoising method is designed to preserve both the edges and structural details of the image. Speckle noise is suppressed, without smearing the edges, by extending the smoothness of the image in the wavelet-based Holder spaces. A comparison of smoothing speckles with the other well-known methods is provided via the size of Besov norm. The authors validate the proposed method using synthetic data, simulated and real ultrasound images. Experiments demonstrate the performance improvement of the proposed method over other state-of-the-art methods in terms of image quality and edge preservation indices.

关键词： real ultrasound images ultrasonic imaging synthetic data Besov norm image quality Patient diagnostic methods and instrumentation speckle noise suppression edge preservation indices denoising method speckle smoothing function space approach Sonic and ultrasonic radiation (medical uses) Biology and medical computing wavelet-based Holder spaces computer vision and image processing techniques Optical, image and video signal processing Sonic and ultrasonic radiation (biomedical imaging/measurement) smoothing methods speckle reduction method image structural details medical image processing image denoising image smoothness simulated ultrasound images

来源：评论

学校读者我要写书评

暂无评论

Scale trees far stereo vision

引用

IEE PROCEEDINGS-vision image AND SIGNAL processing 2000年第4期147卷 363-370页

作者： Moravec, K Harvey, R Bangham, JA Univ E Anglia Sch Informat Syst Norwich NR4 7TJ Norfolk England

The image trees described hierarchically organise image segments according to scale, with the coarsest scale, the scale of the image itself as the root of the tree and the finest scales as the leaves. The segmentation algorithm used to form the tree nodes is the sieve, a nonlinear morphological scale-space operator. The trees are a transform, so it is possible to reconstruct the associated image without loss. Scale trees may have more nodes than are needed but the trees may be simplified using a standard statistical test to reduce the number of nodes without affecting the reconstructed image significantly. These simplified trees may be used to generate regions for a stereo algorithm that reduces the errors in the resulting disparity map, particularly within sharp-edged regions with low texture - conditions where conventional methods often fail.

关键词： segmentation algorithm image segmentation image matching sharp-edged regions computer vision and image processing techniques tree nodes texture conditions stereo image processing transform disparity map nonlinear morphological scale-space operator tree data structures Optical, image and video signal processing image texture image segments reconstructed image image trees statistical test scale trees image reconstruction mathematical operators mathematical morphology stereo vision

来源：评论

学校读者我要写书评

暂无评论

ERROR-DETECTION AND CORRECTION OF VECTOR QUANTIZED DIGITAL imageS

引用

IEE PROCEEDINGS-I COMMUNICATIONS SPEECH AND vision 1990年第6期137卷 417-423页

作者： CHUA, KC WONG, WC NGAN, KN NATL UNIV SINGAPORE DEPT ELECT ENGNSINGAPORE 0511SINGAPORE

The performance of a low bit-rate digital image codec based on a product vector quantiser (VQ) is examined in a noisy transmission channel environment. The VQ codec is a separating gain/shape type providing good data compression at about 1.25 bits per pixel. For small image subblock sizes, there is sufficient interblock correlation in the mean, standard deviation and shape information to facilitate crude error detection mechanisms to be implemented. We reinforce these error detection capabilities with a subblock boundary continuity testing algorithm. Erroneous subblocks are then estimated by extrapolating intensity contours from neighbouring subblocks. Using such an error detection and correction technique, noisy recovered VQ images can be considerably improved. At a bit error rate of 0.01, we obtained an improvement in the normalised mean square error of about 0.013, or equivalently about 6 dB in signal-to-noise ratio.

关键词： Stations and subscriber equipment Pattern recognition error detection product vector quantiser data compression normalised mean square error low bit-rate bit error rate Codes vector quantised digital images interblock correlation signal-to-noise ratio Optical information, image and video signal processing noisy transmission channel digital image codec codecs computerised picture processing computer vision and image processing techniques subblock boundary continuity testing algorithm error correction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：