Filters








113 Hits in 8.0 sec

Preselection of support vector candidates by relative neighborhood graph for large-scale character recognition

Masanori Goto, Ryosuke Ishida, Seiichi Uchida
2015 2015 13th International Conference on Document Analysis and Recognition (ICDAR)  
We propose a pre-selection method for training support vector machines (SVM) with a large-scale dataset.  ...  For the selection, that is, searching for boundary patterns, we utilize a relative neighborhood graph (RNG).  ...  • We developed an efficient method for constructing RNGs. The computation time of the method scales with O(n 2 ) and the algorithm is memory-efficient.  ... 
doi:10.1109/icdar.2015.7333773 dblp:conf/icdar/GotoIU15 fatcat:d6wgrpnrjzb4hegqirexyju3zy

Vision-Based Hand Gesture Recognition for Human-Computer Interaction [chapter]

Xenophon Zabulis, Haris Baltzakis, Antonis Argyros
2009 Human Factors and Ergonomics  
Acknowledgements This work has been partially supported by EU-IST NoE MUSCLE (FP6-507752), the Greek national GSRT project XENIOS and the EU-IST project INDIGO (FP6-045388).  ...  • K l (P ) is a local maximum in its (scale-dependent) neighborhood of the contour.  ...  The similarity of the candidate to the prototype is proportional to the total score on a preselected similarity measure.  ... 
doi:10.1201/9781420064995-c34 fatcat:ethpj6kys5dpdjihszbkjgqewa

Pattern recognition: Historical perspective and future directions

Azriel Rosenfeld, Harry Wechsler
2000 International journal of imaging systems and technology (Print)  
Pattern recognition is one of the most important functionalities for intelligent behavior and is displayed by both biological and artificial systems.  ...  Pattern recognition also involves categorization: making sense of patterns not previously seen.  ...  The weights are the relative contributions of the support vectors to the decision surface.  ... 
doi:10.1002/1098-1098(2000)11:2<101::aid-ima1>3.0.co;2-j fatcat:7avx2v64l5h6leyn5pdgg6s4ey

Open Stylometric System WebSty: Integrated Language Processing, Analysis and Visualisation

Maciej Piasecki, Tomasz Walkowiak, Maciej Eder
2018 Computational Methods in Science and Technology  
We discuss the underlying ideas of the system, its architecture, a pipeline of language tools for processing Polish, and its integration with systems for clustering, visualizing the results of clustering  ...  The paper presents an open, web-based system for stylometric analysis named WebSty, which is a part of the CLARIN-PL research infrastructure.  ...  Acknowledgements Works funded by the Polish Ministry of Science and Higher Education within CLARIN-PL Research Infrastructure.  ... 
doi:10.12921/cmst.2018.0000007 fatcat:pditv66ns5emzj6xbs4fi46ssu

From surfaces to objects: computer vision and three dimensional scene analysis

1990 ChoiceReviews  
I feel awkward about ranking people by the amount or the quality of the help given, so I will not do that.  ...  The work presented here takes an integrated view of the problems and demonstrates that recognition can actually be done.  ...  A position consists of a 3-vector representing relative translation and a unit 4-vector quaternion representing relative orientation (of the form (cos(θ/2), sin(θ/2) w) for a rotation of θ about the axis  ... 
doi:10.5860/choice.27-2755 fatcat:cpli4dhclfblfgummz5ohq72ce

Building semantic trees from XML documents

Joe Tekli, Nathalie Charbel, Richard Chbeir
2016 Journal of Web Semantics  
nodes as special sphere neighborhood vectors including all XML structural relationships within a (user-chosen) range, and iv) running context vectors through a hybrid disambiguation process, combining  ...  XSDF consists of four main modules for: i) linguistic pre-processing of simple/compound XML node labels and values, ii) selecting ambiguous XML nodes as targets for disambiguation, iii) representing target  ...  This study is partly funded by the National Council for Scientific Research (CNRS), Lebanon, project: NCSR_00695_01/09/15, and by LAU grant: SOERC1415T004.  ... 
doi:10.1016/j.websem.2016.03.002 fatcat:uqehvo445bgwpeyawpqxoon4ye

Performance Evaluation of Different Data Mining Classification Algorithm and Predictive Analysis

Syeda Farha Shazmeen Syeda Farha Shazmeen
2013 IOSR Journal of Computer Engineering  
Data mining is the knowledge discovery process by analyzing the large volumes of data from various perspectives and summarizing it into useful information; data mining has become an essential component  ...  and improve the performance by applying data preprocessing techniques and feature selection and also prediction of new class labels.  ...  We thank our parents for their support and thank all our friends and well-wishers who were a constant source of inspiration This is a relatively new field and there is a tremendous potential for future  ... 
doi:10.9790/0661-1060106 fatcat:ffw6zxhlajaljmhstlrz6tbqhe

Beyond Traditional Kernels: Classification in Two Dissimilarity-Based Representation Spaces

Elzbieta Pekalska, Robert P. W. Duin
2008 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
Proximity captures the degree of similarity between examples and is thereby fundamental in learning.  ...  Learning from pairwise proximity data usually relies on either kernel methods for specifically designed kernels or the nearest neighbor (NN) rule.  ...  Paclík for providing dissimilarity data. The authors also thank anonymous reviewers for their good suggestions.  ... 
doi:10.1109/tsmcc.2008.2001687 fatcat:olsjte6j7zan3gtvqhpwyl7dhm

Action synopsis

Jackie Assa, Yaron Caspi, Daniel Cohen-Or
2005 ACM Transactions on Graphics  
(Images used courtesy Abstract Illustrating motion in still imagery for the purpose of summary, abstraction and motion description is important for a diverse spectrum of fields, ranging from arts to sciences  ...  We present methods for illustrating the selected poses in an image as a means to convey the action.  ...  This work was supported in part by grants from the Israel Science Foundation (founded by the Israel Academy of Sciences and Humanities), by the Israeli Ministry of Science.  ... 
doi:10.1145/1073204.1073246 fatcat:z4pqytthqrbqdn6tnaazfv3qbe

Action synopsis

Jackie Assa, Yaron Caspi, Daniel Cohen-Or
2005 ACM SIGGRAPH 2005 Papers on - SIGGRAPH '05  
(Images used courtesy Abstract Illustrating motion in still imagery for the purpose of summary, abstraction and motion description is important for a diverse spectrum of fields, ranging from arts to sciences  ...  We present methods for illustrating the selected poses in an image as a means to convey the action.  ...  This work was supported in part by grants from the Israel Science Foundation (founded by the Israel Academy of Sciences and Humanities), by the Israeli Ministry of Science.  ... 
doi:10.1145/1186822.1073246 fatcat:e3qwtworcfdczp7h7ocaaltebe

Topic models for image retrieval on large-scale databases

Eva Hörster, Rainer Lienhart, Wolfgang Effelsberg, Bernhard Möller
2009 ACM SIGMultimedia Records  
Throughout this thesis, the suitability of all proposed models and approaches is demonstrated by user studies on a real-world, large-scale database in the context of image retrieval tasks.  ...  In this thesis we present a complete image retrieval system based on topic models and evaluate the suitability of different types of topic models for the task of large-scale retrieval on real-world databases  ...  Given a predefined interest point at a specified scale (i.e., size of local neighborhood), they describe the local image region surrounding the interest point compactly by a feature vector.  ... 
doi:10.1145/1738921.1738925 fatcat:ia42ztkmznfdvmsowo2uo6ufda

A hierarchical model of goal directed navigation selects trajectories in a visual environment

Uğur M. Erdem, Michael J. Milford, Michael E. Hasselmo
2015 Neurobiology of Learning and Memory  
The reviewer is correct in his/her understanding about the visual place recognition method we used for loop closure.  ...  We rectify the loss of fidelity by exploiting the loop-closure detection ability of a biologically inspired, robot navigation model termed RatSLAM.  ...  Acknowledgements This work was supported by the ONR MURI grant N00014-10-1-0936, the ONR grant N00014-09-1-0641 and an Australian Research Council Discovery Project DP1212775.  ... 
doi:10.1016/j.nlm.2014.07.003 pmid:25079451 fatcat:nkfiuntx2fhkli4tif7sndt46u

Ordinal Hyperplane Loss

Bob Vanderheyden, Ying Xie
2018 2018 IEEE International Conference on Big Data (Big Data)  
Ratings scales, medical classification scales, socio-economic scales, meaningful groupings of continuous data, facial emotional intensity and facial age estimation are examples of ordinal data for which  ...  Our conversations outside of course work were special for me. You will always be a dear friend. I also want to thank Yiyun Zhou and Dr. Linh Le for all of the help that you provided.  ...  Based on examination of the image data, the cropped images are relatively large images for the purposes of this type of classification.  ... 
doi:10.1109/bigdata.2018.8622079 dblp:conf/bigdataconf/VanderheydenX18 fatcat:yj4ttuibt5ayvefjv6wsmfhb54

A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems

Jörg H. Kappes, Bjoern Andres, Fred A. Hamprecht, Christoph Schnörr, Sebastian Nowozin, Dhruv Batra, Sungwoong Kim, Bernhard X. Kausler, Thorben Kröger, Jan Lellmann, Nikos Komodakis, Bogdan Savchynskyy (+1 others)
2015 International Journal of Computer Vision  
large range of model types.  ...  Key insights from our study agree with the results of Szeliski et al. for the types of models they studied.  ...  This work has been supported by the German Research Foundation (DFG) within the program "Spatio-/ Temporal Graphical Models and Applications in Image Analysis", grant GRK 1653.  ... 
doi:10.1007/s11263-015-0809-x fatcat:62xje37yzffsfgw76hhflwiyt4

A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problems [article]

Jörg H. Kappes, Bjoern Andres, Fred A. Hamprecht, Christoph Schnörr, Sebastian Nowozin, Dhruv Batra, Sungwoong Kim, Bernhard X. Kausler, Thorben Kröger, Jan Lellmann, Nikos Komodakis, Bogdan Savchynskyy, Carsten Rother
2014 arXiv   pre-print
large range of model types.  ...  Key insights from our study agree with the results of Szeliski et al. for the types of models they studied.  ...  This work has been supported by the German Research Foundation (DFG) within the program "Spatio-/ Temporal Graphical Models and Applications in Image Analysis", grant GRK 1653.  ... 
arXiv:1404.0533v1 fatcat:eh2mhtz2dngnjh4uhzscw2w7c4
« Previous Showing results 1 — 15 out of 113 results