Key Laboratory of Pattern Recognition and Intelligent Information Processing

Chengdu, China

Key Laboratory of Pattern Recognition and Intelligent Information Processing

Chengdu, China

Time filter

Source Type

Shao Z.,Sichuan University | Shao Z.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Liang M.,Guangxi University | He J.,Guangxi Academy of science | Xu X.,Guangxi Academy of science
2011 International Conference on Computer and Management, CAMAN 2011 | Year: 2011

For a graph G, G → (a1, a2, · · ·, ar)v means that in every r-coloring of the vertices in G, there exists a monochromatic ai-clique of color i for some i∈{1, 2, · · ·, r}. The vertex Folkman number is defined as Fv(a1, a2, ···, ar; k) = min{|V(G)|: G → (a1, a2, ···, ar)v and Kk ⊈G}. In general, computing lower and upper bounds for vertex Folkman numbers is difficult. In this note, based on theoretical analysis and computation, we show that Fv(2, 3, 3;4) ≥ 19 and Fv(3, 3, 3;4) ≥ 24, and suggest a cyclic graph of order 91 which may give an upper bound for Fv(3, 3, 3;4). ©2011 IEEE.


Gao C.,Sichuan University | Gao C.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Zhou J.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Zhou J.,Sichuan University | And 2 more authors.
Journal of Computational and Theoretical Nanoscience | Year: 2013

According to the development of the real fractional differentiation and its applications in the modern signal processing, we extend it to quaternion field and put forward a new concept, quaternion fractional directional differentiation, QFDD for short, and corresponding theories. To achieve the numerical calculation, we deduce two algorithms, QFDD1 algorithm and QFDD2 algorithm, and discuss their numerical computation rules for a digital image. Finally, we apply this new theory to enhance images and transform color images into gray-scale images. Experiments show that, for texture-rich digital images, the capability of nonlinearly enhancing image by QFDD algorithms is very obvious. For quantity analysis, we particularly take the five classical parameters from gray level cooccurrence matrix, which are angle matrix, contrast, correlation, energy and homogeneity, calculate information entropy and average gradient, draw the graphics of power spectrum and take also the vertical projection of gray-level. By these evaluating indicators, the effect of image enhancement by QFDD algorithms is evident. In addition, we give a new method of color to gray, QFDD algorithms. Compared with photoshop, the gray image obtained by QFDD algorithms is clearer. Copyright © 2013 American Scientific Publishers All rights reserved.


Zhang H.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Zhang H.,Sichuan University | Shen Y.,University of Science and Technology of China | Li Z.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | And 3 more authors.
Journal of Information and Computational Science | Year: 2015

Center nodes have a bigger load and burden with lots of routing in an Ad Hoc Network Model. Congestion of the nodes' packets has a great impact on network performance, especially in wireless networks. This paper proposes a multi-dimensional perception of adaptive routing algorithms based on the loading of MAC, in particular its utility. Through calculating the probabilities of packet arrival, distribution and intensity of interference, conicting nodes and adjusting the contracting strength of packets would optimize network performance. Our simulated experiments show that this algorithm improves the success rate of data transmission, reduces the delay of packet transmission and improves network throughputs. Copyright © 2015 Binary Information Press.


Zhang H.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Zhang H.,Sichuan University | Hu J.,Beijing Jiaotong University | Hu J.,Chengdu University of Technology | Shen Y.,University of Science and Technology of China
Journal of Computational Information Systems | Year: 2015

In order to verify the network traffic decline because by node breakdown, this paper proposes a new type of prediction algorithm (Prediction algorithm based on Discrete-Queue for FARIMA model, PDF). At first, the mathematic formula for queuing situation and average queue length in steady state is derived with queuing theory in this algorithm based on discrete time, and the prediction method is established by FARIMA Model. Then, a simulation was conducted to research on the relationships between average queue length and service rate. The result shows that it has good adaptability, and the standard deviation between prediction traffic and original traffic is 10.18. ©, 2015, Binary Information Press. All right reserved.


Gao C.,Sichuan University | Gao C.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Zhou J.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Zhou J.,Sichuan University | And 3 more authors.
Journal of Computational Information Systems | Year: 2011

In this paper, according to the development of the fractional differentiation and its applications in the modern signal processing, we improve the numerical calculation of fractional differentiation by piecewise quadratic interpolation equation, that is, improved fractional differentiation, IFD for short, and propose a new corresponding operator, IFD operator. And we apply this new operator to image enhancement. Experiments show that, for texture-rich digital image, the capability of nonlinearly enhancing comprehensive texture details by IFD is very obvious. For quantity analysis, we particularly calculate the information entropy and average gradient. Comparing with fractional differentiation, the image obtained by IFD is clearer. © 2011 Binary Information Press.


Yan T.,Sichuan University | Yan T.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Liu C.,Sichuan University | Liu C.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | And 2 more authors.
Advanced Materials Research | Year: 2013

In order to settle incremental learning and preserve the space information of images, this paper proposes an incremental tensor discriminant analysis for facial image detection. The proposed algorithm employs tensor representation to preserve the structure information and introduces the incremental learning to solve the on-line learning for new added samples. The experiments have shown that our method achieves better classification performance and reduces the computational cost effectively compared with other algorithms. © (2013) Trans Tech Publications, Switzerland.


Zhao W.D.,Sichuan University | Zhao W.D.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Liu C.,Sichuan University | Liu C.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | And 2 more authors.
Advanced Materials Research | Year: 2013

Aiming at the disadvantages of the traditional off-line vector-based learning algorithm, this paper proposes a kind of Incremental Tensor Principal Component Analysis (ITPCA) algorithm. It represents an image as a tensor data and processes incremental principal component analysis learning based on update-SVD technique. On the one hand, the proposed algorithm is helpful to preserve the structure information of the image. On the other hand, it solves the training problem for new samples. The experiments on handwritten numeral recognition have demonstrated that the algorithm has achieved better performance than traditional vector-based Incremental Principal Component Analysis (IPCA) and Multi-linear Principal Component Analysis (MPCA) algorithms. © (2013) Trans Tech Publications, Switzerland.


Zhang H.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Zhang H.,Chengdu University of Technology | Zhang H.,Sichuan University | Shen Y.C.,University of Science and Technology of China | Hu J.,Chengdu University of Technology
Computing, Control, Information and Education Engineering - Proceedings of the 2015 2nd International Conference on Computer, Intelligent and Education Technology, CICET 2015 | Year: 2015

This paper puts forward a new network flow Prediction algorithm (Prediction algorithm based-FARIMA model for Discrete Time, PFDT) in view of the network node congestion or Link disconnected. The algorithm deduces the mathematical expressions of average queue length when the queue exists a failure node with the theory of discrete time and establishes the prediction model by FARIMA. The simulation results show that the algorithm has good adaptability and the standard deviation is 10.28 compared with the original. © 2015 Taylor & Francis Group, London.


Liu C.,Sichuan University | Liu C.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Zhou J.,Sichuan University | Zhou J.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | And 4 more authors.
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | Year: 2011

In order to overcome the curse of dimensionality and small sample size problem, a large number of tensor algorithms are proposed and better performance is achieved in face recognition. However, the neighboring classes overlap easily in low dimensional space for existing tensor algorithms. Therefore, this paper proposes a weighted discriminative locally multi-linear embedding algorithm. Because the algorithm considers a face image as a high-order tensor, it contains the structure of the image, avoids the curse of dimensionality and relieves the sample size problem. Moreover the algorithm preserves the local manifold structure within the same class, and increases the separability between different classes using Gaussian Basis Function as the weighted function. The algorithm also solves the out-of-sample problem effectively. Face recognition experiments demonstrate that the algorithm proposed in this paper is robust for the variation of illumination, facial expression and poses, and achieves better performance compared with many popular face recognition algorithms.


Shang Z.-W.,Chongqing University | Zhang F.,Chongqing University | Lang F.-N.,Key Laboratory of Pattern Recognition and Intelligent Information Processing | Yuan B.,Chongqing University | Li J.,Chongqing University
Chongqing Daxue Xuebao/Journal of Chongqing University | Year: 2011

Based on the dependency of the PDTDFB coefficients across the interscale and interdirection and the statistical properties of HMT for the correlation properties, a new HMT in PDTDFB domain was put forward. Compared with the other typical denoising methods, the experimental results demonstrate that the proposed method shows better performance in image denoising, especially in edge maintenance.

Loading Key Laboratory of Pattern Recognition and Intelligent Information Processing collaborators
Loading Key Laboratory of Pattern Recognition and Intelligent Information Processing collaborators