Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 236 papers published in subject: since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. Detection of image operation chains by residual-based hybrid features | |||
HU Lipin,YANG Gaobo | |||
Information Science and System Science 06 May 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Most existing image forensics approaches can effectively reveal image forgery by single image manipulation. However, two or more image manipulations, which are referred to be image operation chains, are usually involved in actual image tampering. In this paper, an image forensics approach is proposed to identify an image operation chain, which is possibly made up of three typical image manipulations including image sharping, scaling and median filtering. Since different image manipulations leave their distinct fingerprints, there also exist specific traces formed by interaction or superposition of different fingerprints left by multiple image manipulations in a specific order. Inspired by the rich image steganalytic features, we attempt to identify image operation chain by combining residue-based features in spatial domain and DCT domain. Experimental results show that the proposed approach achieves good detection result, which effectively discriminate multiple operation chains among different combinations of sharpening, scaling and median filtering. Moreover, the proposed method has good robustness against JPEG compression. | |||
TO cite this article:HU Lipin,YANG Gaobo. Detection of image operation chains by residual-based hybrid features[OL].[ 6 May 2020] http://en.paper.edu.cn/en_releasepaper/content/4751889 |
2. Kernel Correlation Filter Tracking based on Spatial Constraint | |||
LI Zhi-Yong,Chen Li | |||
Information Science and System Science 25 April 2018 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Correlation filter (CF) based trackers have become quite popular in video tracking because of their impressive performance and high frame rates. A large amount of recent research focuses on the improvement of training model of correlation filter to get a tracker with better discriminative power. However, this only helps the tracker to discriminate the target object from background within a small neighborhood, which is not suitable for fast motion scenes. In this paper, we propose a new detection model to dig out the potential of the correlation filter to deal with the challenge of fast motion. The model performs detection operations on multiple small search areas within a large one. Thus, our tracker can accurately localize the target object in a larger search area. In addition, we also added space constraints to boost the tracking performance of the model. The extensive experimental results demonstrate that the proposed tracker outperforms several state-of-the-art trackers on the challenging benchmark dataset with 51 sequences. | |||
TO cite this article:LI Zhi-Yong,Chen Li. Kernel Correlation Filter Tracking based on Spatial Constraint[OL].[25 April 2018] http://en.paper.edu.cn/en_releasepaper/content/4744779 |
3. Modelling and optimal control of a conveyor-serviced production station with dynamic pickup point | |||
Hao Tang, Panfei Wu, Li Quan, Qi Tan, Jing Sun | |||
Information Science and System Science 22 December 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In this paper, we propose an optimal control strategy for a production line composed of a conveyor-serviced production station. The station is equipped with an industrial robot used to unload parts from the conveyor belt considering dynamic pickup points. Compared to traditional stations with fixed pickup points, both the mathematical model and optimal control of the lookahead ranges are more complicated when considering dynamic pickup points. In fact, the randomness of part arrival and processing implies that the unloading and service operations are stochastic. Therefore, we established a semi-Markov decision process model for optimisation problem by defining the buffer vacancy and position of the robot gripper as the system states, and the lookahead range as the control variable. From this process, both numerical and learning-based optimisation methods can be applied to determine optimal or suboptimal lookahead policies depending on the availability of system parameters. We validated the effectiveness of the proposed control strategy from simulations. The results suggest that production considering a dynamic pickup point outperforms that considering a fixed pickup point in various aspects, including the expected long-run average cost, production rate, and cycle time. | |||
TO cite this article:Hao Tang, Panfei Wu, Li Quan, et al. Modelling and optimal control of a conveyor-serviced production station with dynamic pickup point[OL].[22 December 2017] http://en.paper.edu.cn/en_releasepaper/content/4742948 |
4. The Depth Estimation Based on Acitve Vision | |||
Lin Anping,Sun Wei | |||
Information Science and System Science 05 May 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In the eye-in-hand system, the depth is very important for visual positioning system. The image of the object moves as the camera moving, according to the image position change of the same object and the distance the camera made, the depth can be estimated. This paper deduced the relation between camera moving and the image of object moving, adopted centroid method and local voting method to detecting circle. Then used the table tennis to do the radial and the axial motion experiments and estimate the depth. The experiments proved that moving camera alongside either radial or axis direction and taking photos in different position, the depth can be calculated according to the distance the camera moved and the image changes of the same object. | |||
TO cite this article:Lin Anping,Sun Wei. The Depth Estimation Based on Acitve Vision[OL].[ 5 May 2017] http://en.paper.edu.cn/en_releasepaper/content/4730728 |
5. Statistical Modeling for Multiple Modes Facial Images using GND-PCA | |||
Qiao Xu | |||
Information Science and System Science 04 May 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract: In this paper, we proposed a new approach called generalized N-dimensional principal component analysis (GND-PCA) for statistical appearance modeling of facial images with multiple modes including different people, different pose and different illumination. The facial images with multiple modes can be considered as high-dimensional data. GND-PCA can be used to treat the high-order dimensional data as a series of high-order tensors and calculate the bases on each mode-subspace in order to approximate the tensor accurately. GND-PCA can represent the high-order dimensional data of image ensembles more efficiently compared to the recently proposed ND-PCA method. MaVIC Database (KAO-Ritsumeikan Multi-angle View, Illumination and Cosmetic Facial Database) is used in our experiments and the results are compared with those obtained by conventional PCA and ND-PCA. | |||
TO cite this article:Qiao Xu. Statistical Modeling for Multiple Modes Facial Images using GND-PCA[OL].[ 4 May 2017] http://en.paper.edu.cn/en_releasepaper/content/4732187 |
6. Some notes on Input-output Finite-time Stability of Discrete-time Switched Systems | |||
ZHANG Guang-Chen, WANG Wei-Qun, GAO Jing-Bo | |||
Information Science and System Science 02 May 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper contains a discussion on input-output finite-time stability (I-O FTS) issues related to switched systems featuring arbitrary switching and restricted switching. For switched systems under arbitrary switching, sufficient conditions are separately obtained for input signals $mathcal{W}_2$ and $mathcal{W}_infty$, respectively. The I-O FTS issues for switched systems under restricted switching are then addressed, including cases of switching signals with known instants and average dwell time; corresponding sufficient conditions are proposed via solvable LMIs constraints. To conclude the paper, the effectiveness of the proposed results are illustrated through numerical examples. | |||
TO cite this article:ZHANG Guang-Chen, WANG Wei-Qun, GAO Jing-Bo. Some notes on Input-output Finite-time Stability of Discrete-time Switched Systems[OL].[ 2 May 2017] http://en.paper.edu.cn/en_releasepaper/content/4727410 |
7. A Review of Regularization Based Feature Selection Algorithms | |||
Kai Xiong, Junwei Han | |||
Information Science and System Science 22 April 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Feature selection plays a significant role in pattern recognition, machine learning and other related fields. It can be used in data preprocessing step to achieve efficient dimensionality reduction by selecting a subset of discriminant and informative features. In recent years, regularization based feature selection has attracted great interest and many algorithms have been proposed. The common idea of these methods is to choose a proper norm such as $ell_1$-norm, $ell_1/ell_infty$-norm and $ell_{2,1}$-norm for the selection vector or selection matrix to achieve sparseness, and the non-zero entries or rows correspond to the selected features. This paper aims to review the recently proposed representative works, provides insight into the differences and connections between these methods, and discusses the challenges and possible directions of future work. | |||
TO cite this article:Kai Xiong, Junwei Han. A Review of Regularization Based Feature Selection Algorithms[OL].[22 April 2017] http://en.paper.edu.cn/en_releasepaper/content/4728212 |
8. Electronic phase diagram of oxygen-deficient SmNiO3-δ epitaxial thin films | |||
CHEN Binjie,SUN Yan,YANG Nan,ZHONG Ni,ZHANG Yuanyuan,BAI Wei,SUN Lin,TANG Xiaodong,YANG Pinxiong,XIANG Pinghua,DUAN Chungang | |||
Information Science and System Science 16 April 2017 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Epitaxial SmNiO3-δ thin films were fabricated under various oxygen partial pressures (PO2) on (001)-oriented LaAlO3 substrates by pulsed laser deposition method. Continuous control of the metal-insulator transition temperature (TMI) from 350 K to 85 K has been achieved by varying PO2 from 26 Pa to 0.5 Pa. The reduction of TMI can be attributed to the straightening out of the out-of-plane Ni-O-Ni bond angle due to the elongation of unit cell volume with decrease of PO2. When PO2 > 3 Pa, the resistivity anomalies around 200 K are observed in the insulating phase of strained SmNiO3-δ films, suggesting the onset of antiferromagnetic ordering of the Ni sublattices. Based on the results of the transport measurements, an electronic phase diagram of the oxygen deficient SmNiO3-δ films has been established in this work. | |||
TO cite this article:CHEN Binjie,SUN Yan,YANG Nan, et al. Electronic phase diagram of oxygen-deficient SmNiO3-δ epitaxial thin films[OL].[16 April 2017] http://en.paper.edu.cn/en_releasepaper/content/4725913 |
9. A New Filtering Algorithm for Stochastic Dynamical Systems with State-Dependent Observation Noise | |||
TANG Jian-Fang, LI Jian-Bo, ZHOU Jie | |||
Information Science and System Science 12 December 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Much research on extensions of Kalman filtering for models with state-dependent noise has been done in the past decades. This paper discusses a dynamic system with observation noise dependent on estimated state, where the correlation between them is described by a nonzero covariance matrix. We propose a new filtering algorithm, which shows a better performance than the standard Kalman filtering in this case. Numerical example is provided to verify its performance. | |||
TO cite this article:TANG Jian-Fang, LI Jian-Bo, ZHOU Jie. A New Filtering Algorithm for Stochastic Dynamical Systems with State-Dependent Observation Noise[OL].[12 December 2016] http://en.paper.edu.cn/en_releasepaper/content/4712079 |
10. A Satellite Network Prediction Method Based on nonlinear Optimized SVM | |||
Zhu Runtao,Li Ning | |||
Information Science and System Science 02 December 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:According to the limited processing ability of satellite, a network traffic prediction model based on wavelet transformation and nonlinear optimization SVM is proposed. First wavelet transform was carried out on the network traffic to get scale coefficients and the wavelet coefficients. Then Using nonlinear quantum particle swarm optimization algorithm to optimize the SVM. Through the SVM regression model, the wavelet component regression analysis is done. Finally do wavelet reconstruction and obtain prediction results. The experimental results show that the improved prediction algorithm has better generalization ability and is suitable for short-term prediction. Its prediction accuracy is much better than traditional forecasting methods. | |||
TO cite this article:Zhu Runtao,Li Ning. A Satellite Network Prediction Method Based on nonlinear Optimized SVM[OL].[ 2 December 2016] http://en.paper.edu.cn/en_releasepaper/content/4712110 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated