检索结果-内蒙古大学图书馆

Novel way achieving 3D reconstruction of actual human face using multi images

学校读者我要写书评

暂无评论

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2008年第4期36卷 661-666页

作者： Hou, Wen-Guang Chan, Tai-Wai Ding, Ming-Yue Image Processing and Intelligent Control Key Laboratory Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Industrial Centre Hong Kong Polytechnic University Hong Kong Hong Kong

A novel way achieving geometrical reconstruction of actual human face through projecting two types of texture on face in short time is advanced. The first type texture is stripe which is used to establish parallax grid between images. Taking into account of its results, the second type projecting texture is used to match by virtue of its abundant traits. After realizing geometrical reconstruction, the paper provides a general way about achieving actual texture reconstruction by the outer spherical surface surrounding object. In order to uniform color, it deals with parts of images in conjunct region and makes the color change meeting a certain function on condition of keeping their original information mostly. Results show this way can improve reconstruction quality and decrease complicacy of algorithm.

关键词： image reconstruction

Generalization Properties of hyper-RKHS and its Applications

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Liu, Fanghui Shi, Lei Huang, Xiaolin Yang, Jie Suykens, Johan A.K. Department of Electrical Engineering ESAT-STADIUS KU Leuven Kasteelpark Arenberg 10 LeuvenB-3001 Belgium Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai200433 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view. Algorithmically, we consider two regularized regression models with bivariate forms in this space, including kernel ridge regression (KRR) and support vector regression (SVR) endowed with hyper-RKHS, and further combine divide-and-conquer with Nyström approximation for scalability in large sample cases. This framework is general: the underlying kernel is learned from a broad class, and can be positive definite or not, which adapts to various requirements in kernel learning. Theoretically, we study the convergence behavior of regularized regression algorithms in hyper-RKHS and derive the learning rates, which goes beyond the classical analysis on RKHS due to the non-trivial independence of pairwise samples and the characterisation of hyper-RKHS. Experimentally, results on several benchmarks suggest that the employed framework is able to learn a general kernel function form an arbitrary similarity matrix, and thus achieves a satisfactory performance on classification tasks. Copyright © 2018, The Authors. All rights reserved.

关键词： Approximation theory

Boosting discriminative model for moving cast shadow detection

学校读者我要写书评

暂无评论

Jisuanji Xuebao/Chinese Journal of Computers 2007年第8期30卷 1295-1301页

作者： Zha, Yu-Fei Chu, Ying Wang, Xun Ma, Shi-Ping Bi, Du-Yan Signal and Information Processing Laboratory Engineering College Air Force Engineering University Xi'an 710038 China Key Laboratory for Image Processing and Intelligent Control Institute of Pattern Recognition and Artificial Intelligence Huazhong Univ. of Sci. and Technol. Wuhan 430074 China

Moving cast shadow causes serious problem while segmenting and extracting foreground from image sequences, due to the misclassification of moving shadow as foreground. This paper proposes a Boosting discriminative model to eliminate cast shadow on Discriminative Random Fields (DRFs). The method combines different features for Boosting to discriminate cast shadow from moving objects, then temporal and spatial coherence of shadow and foreground are incorporated on Discriminative Random Fields and the problem can be solved by graph cut. Firstly, moving objects are obtained by background subtraction;secondly, shadow candidates can be derived through pre-processing moving objects, in terms of the shadow physical property;thirdly, color information and texture information is derived by comparing shadow and foreground points in current image with corresponding points in background image, which are selected as features for Boosting;finally, temporal and spatial coherence of shadow and foreground is employed on Discriminative Random Fields and discriminate shadow and foreground by graph cut accurately.

关键词： image processing

Predicting functional impact of single amino acid polymorphisms by integrating sequence and structural features

学校读者我要写书评

暂无评论

Predicting functional impact of single amino acid polymorphi...

IEEE International Conference on Systems Biology

作者： Mingjun Wang Hong-Bin Shen Tatsuya Akutsu Jiangning Song State Engineering Laboratory for Industrial Enzymes Tianjin Institute of Industrial Biotechnology Chinese Academy of Sciences (CAS) Tianjin China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Bioinformatics Center Institute for Chemical Research Kyoto University Uji Kyoto Japan Department of Biochemistry and Molecular Biology Faculty of Medicine Monash University Melbourne VIC Australia

Single amino acid polymorphisms (SAPs) are the most abundant form of known genetic variations associated with human diseases. It is of great interest to study the sequence-structure-function relationship underlying SAPs. In this work, we collected the human variant data from three databases and divided them into three categories, i.e. cancer somatic mutations (CSM), Mendelian disease-related variant (SVD) and neutral polymorphisms (SVP). We built support vector machine (SVM) classifiers to predict these three classes of SAPs, using the optimal features selected by a random forest algorithm. Consequently, 280 sequence-derived and structural features were initially extracted from the curated datasets from which 18 optimal candidate features were further selected by random forest. Furthermore, we performed a stepwise feature selection to select characteristic sequence and structural features that are important for predicting each SAPs class. As a result, our predictors achieved a prediction accuracy (ACC) of 84.97, 96.93, 86.98 and 88.24%, for the three classes, CSM, SVD and SVP, respectively. Performance comparison with other previously developed tools such as SIFT, SNAP and Polyphen2 indicates that our method provides a favorable performance with higher Sensitivity scores and Matthew's correlation coefficients (MCC). These results indicate that the prediction performance of SAPs classifiers can be effectively improved by feature selection. Moreover, division of SAPs into three respective categories and construction of accurate SVM-based classifiers for each class provides a practically useful way for investigating the difference between Mendelian disease-related variants and cancer somatic mutations.

关键词： Support vector machines Accuracy Proteins Feature extraction Humans Amino acids Databases

Robust occupancy detection from stereo images

学校读者我要写书评

暂无评论

Robust occupancy detection from stereo images

International Conference on Intelligent Transportation

作者： B. Alefs M. Clabian H. Bischof W. Kropatsch F. Khairallah Advanced Computer Vision GmbH-ACV Vienna Austria Advanced Computer Vision GmbH-ACV Austria Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Pattern Recognition and Image Processing Group Institute of Computer Aided Automation Computer Science Department University of Technology Vienna Vienna Austria TRW Automotive GmbH Farmington Hills MI USA

Vehicle occupants that are out-of-position can be deadly injured by the deployment of the air bag in a crash situation. In recent years many different sensors and systems have been proposed to detect the type of occupant and the position of the occupant's head. This work presents a method for classification and occupant's head detection based on passive stereo vision. The proposed system uses depth surface analysis and scene statistics together with support vector machines for classification and selection of head candidates. Evaluation of the method shows 99% correct for classification and 98% correct for head detection, using large sets of image data, and image sequences recorded in a driving vehicle.

关键词： Robustness Magnetic heads Vehicle crash testing Sensor systems Stereo vision Layout Statistical analysis Support vector machines Support vector machine classification Vehicle detection

Efficient spatialtemporal context modeling for action recognition?

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Congqi Lu, Yue Zhang, Yifan Jiang, Dongmei Zhang, Yanning Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Lab on Speech and Image Information Processing School of Computer Science Northwestern Poly-technical University Xi'an710129 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing100190 China

Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextual information between any two points brings huge cost in computation and memory, especially for action recognition, where there is an additional temporal dimension. Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition. The global context is factorized into sparse relation maps. We model the relationship between points in the same line along the direction of horizon, vertical and depth at each time, which forms a 3D criss-cross structure, and duplicate the same operation with recurrent mechanism to transmit the relation between points in a line to a plane finally to the whole spatiotemporal space. Compared with the non-local method, the proposed RCCA-3D module reduces the number of parameters and FLOPs by 25% and 30% for video context modeling. We evaluate the performance of RCCA-3D with two latest action recognition networks on three datasets and make a thorough analysis of the architecture, obtaining the optimal way to factorize and fuse the relation maps. Comparisons with other state-of-the-art methods demonstrate the effectiveness and efficiency of our model. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Learning data-adaptive non-parametric kernels

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

COVID-MTL: Multitask learning with shift3D and random-weighted loss for automated diagnosis and severity assessment of COVID-19

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bao, Guoqing Chen, Huai Liu, Tongliang Gong, Guanzhong Yin, Yong Wang, Lisheng Wang, Xiuying School of Computer Science The University of Sydney J12/1 Cleveland St Darlington SydneyNSW2008 Australia Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Department of Radiation Oncology Shandong Cancer Hospital and Institute Shandong First Medical University Shandong Academy of Medical Sciences Jinan250117 China

There is an urgent need for automated methods to assist accurate and effective assessment of COVID-19. Radiology and nucleic acid test (NAT) are complementary COVID-19 diagnosis methods. In this paper, we present an end-to-end multitask learning (MTL) framework (COVID-MTL) that is capable of automated and simultaneous detection (against both radiology and NAT) and severity assessment of COVID-19. COVID-MTL learns different COVID-19 tasks in parallel through our novel random-weighted loss function, which assigns learning weights under Dirichlet distribution to prevent task dominance;our new 3D real-time augmentation algorithm (Shift3D) introduces space variances for 3D CNN components by shifting low-level feature representations of volumetric inputs in three dimensions;thereby, the MTL framework is able to accelerate convergence and improve joint learning performance compared to single-task models. By only using chest CT scans, COVID-MTL was trained on 930 CT scans and tested on separate 399 cases. COVID-MTL achieved AUCs of 0.939 and 0.846, and accuracies of 90.23% and 79.20% for detection of COVID-19 against radiology and NAT, respectively, which outperformed the state-of-the-art models. Meanwhile, COVID-MTL yielded AUC of 0.800 ± 0.020 and 0.813 ± 0.021 (with transfer learning) for classifying control/suspected, mild/regular, and severe/critically-ill cases. To decipher the recognition mechanism, we also identified high-throughput lung features that were significantly related (P © 2020, CC BY.

关键词： Radiology

Sparse generalized canonical correlation analysis: Distributed alternating iteration based approach

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cai, Jia Lv, Kexin Huo, Junyi Huang, Xiaolin Yang, Jie School of Statistics and Mathematics Guangdong University of Finance & Economics Big Data and Educational Statistics Application Laboratory 21 Chisha Road Guangzhou Guangdong510320 China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing 800 Dongchuan Road Shanghai200240 China School of Electronics and Computer Science University of Southampton University Road SouthamptonSO17 1BJ United Kingdom

Sparse canonical correlation analysis (CCA) is a useful statistical tool to detect latent information with sparse structures. However, sparse CCA works only for two datasets, i.e., there are only two views or two distinct objects. To overcome this limitation, in this paper, we propose a sparse generalized canonical correlation analysis (GCCA), which could detect the latent relations of multiview data with sparse structures. Moreover, the introduced sparsity could be considered as Laplace prior on the canonical variates. Specifically, we convert the GCCA into a linear system of equations and impose 1 minimization penalty for sparsity pursuit. This results in a nonconvex problem on Stiefel manifold, which is difficult to solve. Motivated by Boyd’s consensus problem, an algorithm based on distributed alternating iteration approach is developed and theoretical consistency analysis is investigated elaborately under mild conditions. Experiments on several synthetic and real world datasets demonstrate the effectiveness of the proposed algorithm. Copyright © 2020, The Authors. All rights reserved.

关键词： Statistical mechanics