Using Segmentation Constraints in an Implicit Segmentation Scheme for Online Word Recognition
|
|
- May Hoover
- 8 years ago
- Views:
Transcription
1 1 Using Segmentation Constraints in an Implicit Segmentation Scheme for Online Word Recognition Émilie CAILLAULT LASL, ULCO/University of Littoral (Calais) Christian VIARD-GAUDIN IRCCyN, University of Nantes
2 2 Aim Problem : Training of a neuro-markovian system in the context of cursive handwritten word recognition. Difficulty : Bootstrapping of the system allowing a training from scratch. Proposed solution : Implicit segmentation procedure Definition of a segmentation control function Definition of a quality segmentation measurement
3 3 How train a neuro-markovian system? Character level training Teaching Signal: character Signal Différents hybrides MMC-MMC RN-MMC Classifier HMM MMC - RN SVM-MMC Kppv-MMC Word level training Teaching signal: word RN-MMC Parole/Hors-ligne Classifier HMM
4 Global system overview : MS-TDNN 1- MsTDNN-HMM 4 xr y dx dy cx cy P/D P O bs1 1 state / character: 66 states TD NN O bs1 O bs n O bservation w indows O t of the TD NN... TDN N inputs : tem poral sequence of features vectors for the w ord «quand» z... 3 states / c b a character: 198 states = 198 output neurons O bs1 Sam e weigths m atrices O bs n TD NN O bst Sam e convolutional w indow inside the observation window s of the TD NN O bs n O bservations vectors sequences processed by the H M M Scanning of the input word by a TDNN (temporal convolution). TDNN produces the sequence of observation probabilities. No explicit segmentation is carried out but just an overlapping window is regularly shifted. Advantages of the TDNN architecture: weight sharing reduction in computation times and in memory requirements. Reduction of the number of computation with an adapted topology of the TDNN due to the sliding observation window.
5 1- MsTDNN-HMM Dynamic Programming Likelihood computation 5 Word Lexicon un deux trois quand q s q 1 q 2 q 3 q f q s q 1 q f Words HMM = concatenation of letters HMM 1-state 3-state letter letter model model q s 1 u 1 n 1 qf q s 1 q 1 u 1 a 1 n 1 d 1 q f DP DP Likelihood Scores For each entry in the lexicon, a pseudo-hmmword model is constructed dynamically by concatenating letter HMM Hence, the likelihood for each word in the lexicon is computed by multiplying the observation probabilities over the best path through the graph using the Viterbi algorithm. The word model with the highest likelihood is the top one recognition candidate. Character models a b c d.n o p q.u.z a ij = cst transition probability O1 O2 O3.. b j (O t ), observation probability Best Viterbi path Dynamic Programming to find the best path alignment Ot, Observation sequences q q q q u a a n n d d d
6 Training Original data 1- MsTDNN-HMM Training : 6 TDNN Delta x - coord y - coord x - direction Y _ direction P ( Class 1 X ) P ( Class 2 X ) P ( Class 3 X ) P ( Class 4 X ) Global cost function Backpropagation of the gradient Normalized data 1.. Sequence of features vectors Normalisation Delta x - coord y - coord x - direction Y _ direction P ( Class 1 X ) P ( Class 2 X )... P ( Class 3 X ) P ( Class 4 X ) Obs 1 ObsT Sequence of vectors of observation probabilities, DP Features Extraction Character Likelihood Word Likelihood Computation Recognition Word Lexicon List of words ranked by their WL score N Word level training Classical backpropagation algorithm Cost function mixing MLE, MMI and character level discrimination [ICDAR 2005] «one» recognized as «over» True Hmm: (+) Best Hmm: ( ) ooonneee oovveeer Best character: ( ) aouvneel
7 Illustration of the segmentation problem 2- Implicit Segmentation Control 7 Random initialisation of the TDNN all outputs are equally probable Example: Possible paths for the English word of with 10 observations (TDNN windows) o f offfffffff ooooffffff ooooooofff ooffffffff ooooofffff ooooooooff ooofffffff ooooooffff ooooooooof
8 How to obtain desired Likelihood distribution? 2- Implicit Segmentation Control 8 Segmentation paths for the word of offfffffff 1 ooffffffff ooofffffff ooooffffff ooooofffff ooooooffff ooooooofff ooooooooff ooooooooof 9 P(Γ) Existing solutions: Training with a character database - duration model for HMM sub-unit [Penacee] - manual segmentation constraints [Remus, Npen++] Proposed solution: - no modification of the HMM structure (transitions=1) - no training with a character database - integration of a duration model in the emission probabilities
9 Weighting function f T : 2- Implicit Segmentation Control 9 Outputstl (, ) = min( Outputs ( t, l)* f ( H );1) NN T Weighting of TDNN outputs % B H Observations range corresponding to one letter H=100 H>1000 E B = First observation position for the concerned letter E = Last observation position for the concerned letter H = Height of the function ƒ T S = E-B = letter size
10 Weighting function applied : case of the word of 2- Implicit Segmentation Control weighting coefficient 50 o f observation position H=100
11 2- Implicit Segmentation Control How to evaluate the effectiveness of this weighting function? ASR 11 ASR N N NLs( e) 1 nb _ obsi ( ) = ( ) NLci ( )* T / NLe ( ) e= 1 i= 1 ASR : Averaged homogenous Segmentation Rate e: index of the considered sample T: number of observations scanned by the TDNN N: (fixed or limited) number of training samples NL(e): number of letters in the word label NLs(e): number of sequences of different letters i: index of a sequence of letters from 1 to NLs NLc(i): number of the same consecutive letter and nb_obs(i): number of observations of the letter i in the optimal Viterbi path. Case: of NL(o) NL(f) ASR
12 Experiments : 12 Original data Normalized data Normalisation Training in 2 stages : Global cost function Backpropagation of the gradient TDNN Delta x - coord y - coord x - direction Y _ direction P ( Class 1 X ) P ( Class 2 X ) P ( Class 3 X ) P ( Class 4 X ).. Sequence of features vectors P ( Class 1 X ) P ( Class 2 X )... P ( Class 3 X ) P ( Class 4 X ) Obs 1 ObsT Sequence of vectors of observation probabilities Weighting function ƒ T ƒ T P ( Class 1 X ) P ( Class 2 X ) P ( Class 3 X ) P ( Class 4 X ) 1 True HMM Word Likelihood Computation Features Extraction Delta x - coord y - coord x - direction Y _ direction Character Likelihood Label of the true word P ( Class 1 X ) P ( Class 2 X )... P ( Class 3 X ) P ( Class 4 X ) Obs 1 ObsT Constrained Sequence wtih duration model,, N 1-f T segmentation constraint function for 20 epochs 2- training with no segmentation constraint
13 Results on online word IRONOFF database IRONOFF word database English / French Lexicon : 197 words 2/3 Training : words 1/3 TEST : words 13 System 1State- TDNN 1S-TDNN Segmentation constraint 3State-TDNN 3S-TDNN Segmentation constraint Recognition rate (%) Relative improvement (%) Average Segmentation Rate (ASR) Relative improvement (%)
14 Conclusions 14 A simple and effective process to bootstrap a hybrid system without any labeled character database Important increasing of the recognition rate by an initialisation stage with a duration model apply directly on the TDNN outputs Weighting function ƒ T Better quality of segmentation better recognition rates ASR Averaged Segmentation Rate
15 Future works : controlled segmentation stage 15 Measure of the ASR for each training iteration Adaptation of the parameter H in the weighting function to reduce the segmentation constraints according to the ASR value. H=ƒ(ASR). Initialisation with H = 100 high segmentation constraint, only balanced segmentation paths are possible Then relax constraint on H when ASR has reached a reasonable value.
16 16 Bonus
17 Introduction Problème Reconnaissance Car. Reconnaissance Mot Conclusion 17 Le moteur de reconnaissance : le TDNN MLP TDNN Global Vision Local vision to global vision Weight sharing
Numerical Field Extraction in Handwritten Incoming Mail Documents
Numerical Field Extraction in Handwritten Incoming Mail Documents Guillaume Koch, Laurent Heutte and Thierry Paquet PSI, FRE CNRS 2645, Université de Rouen, 76821 Mont-Saint-Aignan, France Laurent.Heutte@univ-rouen.fr
More informationCursive Handwriting Recognition for Document Archiving
International Digital Archives Project Cursive Handwriting Recognition for Document Archiving Trish Keaton Rod Goodman California Institute of Technology Motivation Numerous documents have been conserved
More informationIII. SEGMENTATION. A. Origin Segmentation
2012 International Conference on Frontiers in Handwriting Recognition Handwritten English Word Recognition based on Convolutional Neural Networks Aiquan Yuan, Gang Bai, Po Yang, Yanni Guo, Xinting Zhao
More informationLecture 6. Artificial Neural Networks
Lecture 6 Artificial Neural Networks 1 1 Artificial Neural Networks In this note we provide an overview of the key concepts that have led to the emergence of Artificial Neural Networks as a major paradigm
More informationHandwritten Digit Recognition with a Back-Propagation Network
396 Le Cun, Boser, Denker, Henderson, Howard, Hubbard and Jackel Handwritten Digit Recognition with a Back-Propagation Network Y. Le Cun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard,
More informationAUTOMATIC PHONEME SEGMENTATION WITH RELAXED TEXTUAL CONSTRAINTS
AUTOMATIC PHONEME SEGMENTATION WITH RELAXED TEXTUAL CONSTRAINTS PIERRE LANCHANTIN, ANDREW C. MORRIS, XAVIER RODET, CHRISTOPHE VEAUX Very high quality text-to-speech synthesis can be achieved by unit selection
More informationNAVIGATING SCIENTIFIC LITERATURE A HOLISTIC PERSPECTIVE. Venu Govindaraju
NAVIGATING SCIENTIFIC LITERATURE A HOLISTIC PERSPECTIVE Venu Govindaraju BIOMETRICS DOCUMENT ANALYSIS PATTERN RECOGNITION 8/24/2015 ICDAR- 2015 2 Towards a Globally Optimal Approach for Learning Deep Unsupervised
More informationSELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS
UDC: 004.8 Original scientific paper SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS Tonimir Kišasondi, Alen Lovren i University of Zagreb, Faculty of Organization and Informatics,
More informationRecognition of Handwritten Digits using Structural Information
Recognition of Handwritten Digits using Structural Information Sven Behnke Martin-Luther University, Halle-Wittenberg' Institute of Computer Science 06099 Halle, Germany { behnke Irojas} @ informatik.uni-halle.de
More informationSense Making in an IOT World: Sensor Data Analysis with Deep Learning
Sense Making in an IOT World: Sensor Data Analysis with Deep Learning Natalia Vassilieva, PhD Senior Research Manager GTC 2016 Deep learning proof points as of today Vision Speech Text Other Search & information
More information1 Maximum likelihood estimation
COS 424: Interacting with Data Lecturer: David Blei Lecture #4 Scribes: Wei Ho, Michael Ye February 14, 2008 1 Maximum likelihood estimation 1.1 MLE of a Bernoulli random variable (coin flips) Given N
More informationGraph Mining and Social Network Analysis
Graph Mining and Social Network Analysis Data Mining and Text Mining (UIC 583 @ Politecnico di Milano) References Jiawei Han and Micheline Kamber, "Data Mining: Concepts and Techniques", The Morgan Kaufmann
More informationThe Backpropagation Algorithm
7 The Backpropagation Algorithm 7. Learning as gradient descent We saw in the last chapter that multilayered networks are capable of computing a wider range of Boolean functions than networks with a single
More informationHMM : Viterbi algorithm - a toy example
MM : Viterbi algorithm - a toy example.5.3.4.2 et's consider the following simple MM. This model is composed of 2 states, (high C content) and (low C content). We can for example consider that state characterizes
More informationStatistical Machine Learning
Statistical Machine Learning UoC Stats 37700, Winter quarter Lecture 4: classical linear and quadratic discriminants. 1 / 25 Linear separation For two classes in R d : simple idea: separate the classes
More informationIntroduction to Support Vector Machines. Colin Campbell, Bristol University
Introduction to Support Vector Machines Colin Campbell, Bristol University 1 Outline of talk. Part 1. An Introduction to SVMs 1.1. SVMs for binary classification. 1.2. Soft margins and multi-class classification.
More informationBayesian Network Modeling of Hangul Characters for On-line Handwriting Recognition
Bayesian Network Modeling of Hangul haracters for On-line Handwriting Recognition Sung-ung ho and in H. Kim S Div., EES Dept., KAIS, 373- Kusong-dong, Yousong-ku, Daejon, 305-70, KOREA {sjcho, jkim}@ai.kaist.ac.kr
More informationFinal Year Project Progress Report. Frequency-Domain Adaptive Filtering. Myles Friel. Supervisor: Dr.Edward Jones
Final Year Project Progress Report Frequency-Domain Adaptive Filtering Myles Friel 01510401 Supervisor: Dr.Edward Jones Abstract The Final Year Project is an important part of the final year of the Electronic
More informationMulti-Class and Structured Classification
Multi-Class and Structured Classification [slides prises du cours cs294-10 UC Berkeley (2006 / 2009)] [ p y( )] http://www.cs.berkeley.edu/~jordan/courses/294-fall09 Basic Classification in ML Input Output
More informationOff-line Handwriting Recognition by Recurrent Error Propagation Networks
Off-line Handwriting Recognition by Recurrent Error Propagation Networks A.W.Senior* F.Fallside Cambridge University Engineering Department Trumpington Street, Cambridge, CB2 1PZ. Abstract Recent years
More informationThe Role of Size Normalization on the Recognition Rate of Handwritten Numerals
The Role of Size Normalization on the Recognition Rate of Handwritten Numerals Chun Lei He, Ping Zhang, Jianxiong Dong, Ching Y. Suen, Tien D. Bui Centre for Pattern Recognition and Machine Intelligence,
More informationFeed-Forward mapping networks KAIST 바이오및뇌공학과 정재승
Feed-Forward mapping networks KAIST 바이오및뇌공학과 정재승 How much energy do we need for brain functions? Information processing: Trade-off between energy consumption and wiring cost Trade-off between energy consumption
More informationAnalecta Vol. 8, No. 2 ISSN 2064-7964
EXPERIMENTAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN ENGINEERING PROCESSING SYSTEM S. Dadvandipour Institute of Information Engineering, University of Miskolc, Egyetemváros, 3515, Miskolc, Hungary,
More information6.2.8 Neural networks for data mining
6.2.8 Neural networks for data mining Walter Kosters 1 In many application areas neural networks are known to be valuable tools. This also holds for data mining. In this chapter we discuss the use of neural
More informationGeneralization Capacity of Handwritten Outlier Symbols Rejection with Neural Network
Generalization Capacity of Handwritten Outlier Symbols Rejection with Neural Network Harold Mouchère, Eric Anquetil To cite this version: Harold Mouchère, Eric Anquetil. Generalization Capacity of Handwritten
More informationCoding and decoding with convolutional codes. The Viterbi Algor
Coding and decoding with convolutional codes. The Viterbi Algorithm. 8 Block codes: main ideas Principles st point of view: infinite length block code nd point of view: convolutions Some examples Repetition
More informationHardware Implementation of Probabilistic State Machine for Word Recognition
IJECT Vo l. 4, Is s u e Sp l - 5, Ju l y - Se p t 2013 ISSN : 2230-7109 (Online) ISSN : 2230-9543 (Print) Hardware Implementation of Probabilistic State Machine for Word Recognition 1 Soorya Asokan, 2
More informationData Mining using Artificial Neural Network Rules
Data Mining using Artificial Neural Network Rules Pushkar Shinde MCOERC, Nasik Abstract - Diabetes patients are increasing in number so it is necessary to predict, treat and diagnose the disease. Data
More informationPATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 4: LINEAR MODELS FOR CLASSIFICATION Introduction In the previous chapter, we explored a class of regression models having particularly simple analytical
More informationHow To Understand The Network Of A Network
Roles in Networks Roles in Networks Motivation for work: Let topology define network roles. Work by Kleinberg on directed graphs, used topology to define two types of roles: authorities and hubs. (Each
More informationData Mining: An Overview. David Madigan http://www.stat.columbia.edu/~madigan
Data Mining: An Overview David Madigan http://www.stat.columbia.edu/~madigan Overview Brief Introduction to Data Mining Data Mining Algorithms Specific Eamples Algorithms: Disease Clusters Algorithms:
More informationIBM SPSS Neural Networks 22
IBM SPSS Neural Networks 22 Note Before using this information and the product it supports, read the information in Notices on page 21. Product Information This edition applies to version 22, release 0,
More informationAutomatic parameter regulation for a tracking system with an auto-critical function
Automatic parameter regulation for a tracking system with an auto-critical function Daniela Hall INRIA Rhône-Alpes, St. Ismier, France Email: Daniela.Hall@inrialpes.fr Abstract In this article we propose
More informationHidden Markov Models
8.47 Introduction to omputational Molecular Biology Lecture 7: November 4, 2004 Scribe: Han-Pang hiu Lecturer: Ross Lippert Editor: Russ ox Hidden Markov Models The G island phenomenon The nucleotide frequencies
More informationVideo Affective Content Recognition Based on Genetic Algorithm Combined HMM
Video Affective Content Recognition Based on Genetic Algorithm Combined HMM Kai Sun and Junqing Yu Computer College of Science & Technology, Huazhong University of Science & Technology, Wuhan 430074, China
More informationIntroduction to General and Generalized Linear Models
Introduction to General and Generalized Linear Models General Linear Models - part I Henrik Madsen Poul Thyregod Informatics and Mathematical Modelling Technical University of Denmark DK-2800 Kgs. Lyngby
More informationTowards Online Recognition of Handwritten Mathematics
Towards Online Recognition of Handwritten Mathematics Vadim Mazalov, joint work with Oleg Golubitsky and Stephen M. Watt Ontario Research Centre for Computer Algebra Department of Computer Science Western
More informationMachine Learning and Data Mining -
Machine Learning and Data Mining - Perceptron Neural Networks Nuno Cavalheiro Marques (nmm@di.fct.unl.pt) Spring Semester 2010/2011 MSc in Computer Science Multi Layer Perceptron Neurons and the Perceptron
More informationPerformance Evaluation of Artificial Neural. Networks for Spatial Data Analysis
Contemporary Engineering Sciences, Vol. 4, 2011, no. 4, 149-163 Performance Evaluation of Artificial Neural Networks for Spatial Data Analysis Akram A. Moustafa Department of Computer Science Al al-bayt
More informationCar Insurance. Havránek, Pokorný, Tomášek
Car Insurance Havránek, Pokorný, Tomášek Outline Data overview Horizontal approach + Decision tree/forests Vertical (column) approach + Neural networks SVM Data overview Customers Viewed policies Bought
More informationBatch Production Scheduling in the Process Industries. By Prashanthi Ravi
Batch Production Scheduling in the Process Industries By Prashanthi Ravi INTRODUCTION Batch production - where a batch means a task together with the quantity produced. The processing of a batch is called
More informationJava Modules for Time Series Analysis
Java Modules for Time Series Analysis Agenda Clustering Non-normal distributions Multifactor modeling Implied ratings Time series prediction 1. Clustering + Cluster 1 Synthetic Clustering + Time series
More informationOptimization Modeling for Mining Engineers
Optimization Modeling for Mining Engineers Alexandra M. Newman Division of Economics and Business Slide 1 Colorado School of Mines Seminar Outline Linear Programming Integer Linear Programming Slide 2
More informationCSCI567 Machine Learning (Fall 2014)
CSCI567 Machine Learning (Fall 2014) Drs. Sha & Liu {feisha,yanliu.cs}@usc.edu September 22, 2014 Drs. Sha & Liu ({feisha,yanliu.cs}@usc.edu) CSCI567 Machine Learning (Fall 2014) September 22, 2014 1 /
More informationDLP Driven, Learning, Optical Neural Networks
01001000100000110000001000001100 010010001000 DLP Driven, Learning, Optical Neural Networks Emmett Redd & A. Steven Younger Associate Professor SPRP506 Missouri State University EmmettRedd@MissouriState.edu
More informationLecture 13: Validation
Lecture 3: Validation g Motivation g The Holdout g Re-sampling techniques g Three-way data splits Motivation g Validation techniques are motivated by two fundamental problems in pattern recognition: model
More informationResearch on the UHF RFID Channel Coding Technology based on Simulink
Vol. 6, No. 7, 015 Research on the UHF RFID Channel Coding Technology based on Simulink Changzhi Wang Shanghai 0160, China Zhicai Shi* Shanghai 0160, China Dai Jian Shanghai 0160, China Li Meng Shanghai
More informationPOS Tagging 1. POS Tagging. Rule-based taggers Statistical taggers Hybrid approaches
POS Tagging 1 POS Tagging Rule-based taggers Statistical taggers Hybrid approaches POS Tagging 1 POS Tagging 2 Words taken isolatedly are ambiguous regarding its POS Yo bajo con el hombre bajo a PP AQ
More information4.2 Description of the Event operation Network (EON)
Integrated support system for planning and scheduling... 2003/4/24 page 39 #65 Chapter 4 The EON model 4. Overview The present thesis is focused in the development of a generic scheduling framework applicable
More informationDESIGN OF DIGITAL SIGNATURE VERIFICATION ALGORITHM USING RELATIVE SLOPE METHOD
DESIGN OF DIGITAL SIGNATURE VERIFICATION ALGORITHM USING RELATIVE SLOPE METHOD P.N.Ganorkar 1, Kalyani Pendke 2 1 Mtech, 4 th Sem, Rajiv Gandhi College of Engineering and Research, R.T.M.N.U Nagpur (Maharashtra),
More informationThe Impact of Big Data on Classic Machine Learning Algorithms. Thomas Jensen, Senior Business Analyst @ Expedia
The Impact of Big Data on Classic Machine Learning Algorithms Thomas Jensen, Senior Business Analyst @ Expedia Who am I? Senior Business Analyst @ Expedia Working within the competitive intelligence unit
More informationGoals of the Unit. spm - 2014 adolfo villafiorita - introduction to software project management
Project Scheduling Goals of the Unit Making the WBS into a schedule Understanding dependencies between activities Learning the Critical Path technique Learning how to level resources!2 Initiate Plan Execute
More informationAn Introduction to Neural Networks
An Introduction to Vincent Cheung Kevin Cannons Signal & Data Compression Laboratory Electrical & Computer Engineering University of Manitoba Winnipeg, Manitoba, Canada Advisor: Dr. W. Kinsner May 27,
More informationTracking Groups of Pedestrians in Video Sequences
Tracking Groups of Pedestrians in Video Sequences Jorge S. Marques Pedro M. Jorge Arnaldo J. Abrantes J. M. Lemos IST / ISR ISEL / IST ISEL INESC-ID / IST Lisbon, Portugal Lisbon, Portugal Lisbon, Portugal
More informationSpeech Recognition on Cell Broadband Engine UCRL-PRES-223890
Speech Recognition on Cell Broadband Engine UCRL-PRES-223890 Yang Liu, Holger Jones, John Johnson, Sheila Vaidya (Lawrence Livermore National Laboratory) Michael Perrone, Borivoj Tydlitat, Ashwini Nanda
More informationTracking Moving Objects In Video Sequences Yiwei Wang, Robert E. Van Dyck, and John F. Doherty Department of Electrical Engineering The Pennsylvania State University University Park, PA16802 Abstract{Object
More informationAn Approach for Utility Pole Recognition in Real Conditions
6th Pacific-Rim Symposium on Image and Video Technology 1st PSIVT Workshop on Quality Assessment and Control by Image and Video Analysis An Approach for Utility Pole Recognition in Real Conditions Barranco
More informationCOMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS
COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS B.K. Mohan and S. N. Ladha Centre for Studies in Resources Engineering IIT
More informationLogistic Regression for Spam Filtering
Logistic Regression for Spam Filtering Nikhila Arkalgud February 14, 28 Abstract The goal of the spam filtering problem is to identify an email as a spam or not spam. One of the classic techniques used
More informationCOMPUTING CLOUD MOTION USING A CORRELATION RELAXATION ALGORITHM Improving Estimation by Exploiting Problem Knowledge Q. X. WU
COMPUTING CLOUD MOTION USING A CORRELATION RELAXATION ALGORITHM Improving Estimation by Exploiting Problem Knowledge Q. X. WU Image Processing Group, Landcare Research New Zealand P.O. Box 38491, Wellington
More informationSignature Segmentation from Machine Printed Documents using Conditional Random Field
2011 International Conference on Document Analysis and Recognition Signature Segmentation from Machine Printed Documents using Conditional Random Field Ranju Mandal Computer Vision and Pattern Recognition
More informationNLP Programming Tutorial 5 - Part of Speech Tagging with Hidden Markov Models
NLP Programming Tutorial 5 - Part of Speech Tagging with Hidden Markov Models Graham Neubig Nara Institute of Science and Technology (NAIST) 1 Part of Speech (POS) Tagging Given a sentence X, predict its
More informationL13: cross-validation
Resampling methods Cross validation Bootstrap L13: cross-validation Bias and variance estimation with the Bootstrap Three-way data partitioning CSCE 666 Pattern Analysis Ricardo Gutierrez-Osuna CSE@TAMU
More informationOffline sorting buffers on Line
Offline sorting buffers on Line Rohit Khandekar 1 and Vinayaka Pandit 2 1 University of Waterloo, ON, Canada. email: rkhandekar@gmail.com 2 IBM India Research Lab, New Delhi. email: pvinayak@in.ibm.com
More informationUniversità degli Studi di Bologna
Università degli Studi di Bologna DEIS Biometric System Laboratory Incremental Learning by Message Passing in Hierarchical Temporal Memory Davide Maltoni Biometric System Laboratory DEIS - University of
More informationComp 14112 Fundamentals of Artificial Intelligence Lecture notes, 2015-16 Speech recognition
Comp 14112 Fundamentals of Artificial Intelligence Lecture notes, 2015-16 Speech recognition Tim Morris School of Computer Science, University of Manchester 1 Introduction to speech recognition 1.1 The
More informationLow-resolution Character Recognition by Video-based Super-resolution
2009 10th International Conference on Document Analysis and Recognition Low-resolution Character Recognition by Video-based Super-resolution Ataru Ohkura 1, Daisuke Deguchi 1, Tomokazu Takahashi 2, Ichiro
More informationLoad balancing in a heterogeneous computer system by self-organizing Kohonen network
Bull. Nov. Comp. Center, Comp. Science, 25 (2006), 69 74 c 2006 NCC Publisher Load balancing in a heterogeneous computer system by self-organizing Kohonen network Mikhail S. Tarkov, Yakov S. Bezrukov Abstract.
More informationA Learning Based Method for Super-Resolution of Low Resolution Images
A Learning Based Method for Super-Resolution of Low Resolution Images Emre Ugur June 1, 2004 emre.ugur@ceng.metu.edu.tr Abstract The main objective of this project is the study of a learning based method
More informationSimplified Machine Learning for CUDA. Umar Arshad @arshad_umar Arrayfire @arrayfire
Simplified Machine Learning for CUDA Umar Arshad @arshad_umar Arrayfire @arrayfire ArrayFire CUDA and OpenCL experts since 2007 Headquartered in Atlanta, GA In search for the best and the brightest Expert
More informationChapter 4: Artificial Neural Networks
Chapter 4: Artificial Neural Networks CS 536: Machine Learning Littman (Wu, TA) Administration icml-03: instructional Conference on Machine Learning http://www.cs.rutgers.edu/~mlittman/courses/ml03/icml03/
More informationEnvironmental Remote Sensing GEOG 2021
Environmental Remote Sensing GEOG 2021 Lecture 4 Image classification 2 Purpose categorising data data abstraction / simplification data interpretation mapping for land cover mapping use land cover class
More informationData Mining and Neural Networks in Stata
Data Mining and Neural Networks in Stata 2 nd Italian Stata Users Group Meeting Milano, 10 October 2005 Mario Lucchini e Maurizo Pisati Università di Milano-Bicocca mario.lucchini@unimib.it maurizio.pisati@unimib.it
More informationVEHICLE ROUTING PROBLEM
VEHICLE ROUTING PROBLEM Readings: E&M 0 Topics: versus TSP Solution methods Decision support systems for Relationship between TSP and Vehicle routing problem () is similar to the Traveling salesman problem
More informationHybrid Evolution of Heterogeneous Neural Networks
Hybrid Evolution of Heterogeneous Neural Networks 01001110 01100101 01110101 01110010 01101111 01101110 01101111 01110110 01100001 00100000 01110011 01101011 01110101 01110000 01101001 01101110 01100001
More information9. Text & Documents. Visualizing and Searching Documents. Dr. Thorsten Büring, 20. Dezember 2007, Vorlesung Wintersemester 2007/08
9. Text & Documents Visualizing and Searching Documents Dr. Thorsten Büring, 20. Dezember 2007, Vorlesung Wintersemester 2007/08 Slide 1 / 37 Outline Characteristics of text data Detecting patterns SeeSoft
More information1. Classification problems
Neural and Evolutionary Computing. Lab 1: Classification problems Machine Learning test data repository Weka data mining platform Introduction Scilab 1. Classification problems The main aim of a classification
More informationSUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK
SUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK N M Allinson and D Merritt 1 Introduction This contribution has two main sections. The first discusses some aspects of multilayer perceptrons,
More informationApplication of Neural Network in User Authentication for Smart Home System
Application of Neural Network in User Authentication for Smart Home System A. Joseph, D.B.L. Bong, D.A.A. Mat Abstract Security has been an important issue and concern in the smart home systems. Smart
More informationPredictive Dynamix Inc
Predictive Modeling Technology Predictive modeling is concerned with analyzing patterns and trends in historical and operational data in order to transform data into actionable decisions. This is accomplished
More informationSegmentation & Clustering
EECS 442 Computer vision Segmentation & Clustering Segmentation in human vision K-mean clustering Mean-shift Graph-cut Reading: Chapters 14 [FP] Some slides of this lectures are courtesy of prof F. Li,
More informationIntroduction to Machine Learning and Data Mining. Prof. Dr. Igor Trajkovski trajkovski@nyus.edu.mk
Introduction to Machine Learning and Data Mining Prof. Dr. Igor Trakovski trakovski@nyus.edu.mk Neural Networks 2 Neural Networks Analogy to biological neural systems, the most robust learning systems
More informationSemi-Supervised Support Vector Machines and Application to Spam Filtering
Semi-Supervised Support Vector Machines and Application to Spam Filtering Alexander Zien Empirical Inference Department, Bernhard Schölkopf Max Planck Institute for Biological Cybernetics ECML 2006 Discovery
More informationCONATION: English Command Input/Output System for Computers
CONATION: English Command Input/Output System for Computers Kamlesh Sharma* and Dr. T. V. Prasad** * Research Scholar, ** Professor & Head Dept. of Comp. Sc. & Engg., Lingaya s University, Faridabad, India
More informationLecture 2: The SVM classifier
Lecture 2: The SVM classifier C19 Machine Learning Hilary 2015 A. Zisserman Review of linear classifiers Linear separability Perceptron Support Vector Machine (SVM) classifier Wide margin Cost function
More informationDocument Image Retrieval using Signatures as Queries
Document Image Retrieval using Signatures as Queries Sargur N. Srihari, Shravya Shetty, Siyuan Chen, Harish Srinivasan, Chen Huang CEDAR, University at Buffalo(SUNY) Amherst, New York 14228 Gady Agam and
More informationComparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification
Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification R. Sathya Professor, Dept. of MCA, Jyoti Nivas College (Autonomous), Professor and Head, Dept. of Mathematics, Bangalore,
More informationEfficient on-line Signature Verification System
International Journal of Engineering & Technology IJET-IJENS Vol:10 No:04 42 Efficient on-line Signature Verification System Dr. S.A Daramola 1 and Prof. T.S Ibiyemi 2 1 Department of Electrical and Information
More informationHidden Markov Models in Bioinformatics. By Máthé Zoltán Kőrösi Zoltán 2006
Hidden Markov Models in Bioinformatics By Máthé Zoltán Kőrösi Zoltán 2006 Outline Markov Chain HMM (Hidden Markov Model) Hidden Markov Models in Bioinformatics Gene Finding Gene Finding Model Viterbi algorithm
More informationIEEE TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING, VOL.?, NO.?, MONTH 2009 1
IEEE TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING, VOL.?, NO.?, MONTH 2009 1 Data balancing for efficient training of Hybrid ANN/HMM Automatic Speech Recognition systems Ana Isabel García-Moral,
More informationPredict Influencers in the Social Network
Predict Influencers in the Social Network Ruishan Liu, Yang Zhao and Liuyu Zhou Email: rliu2, yzhao2, lyzhou@stanford.edu Department of Electrical Engineering, Stanford University Abstract Given two persons
More informationNeural network software tool development: exploring programming language options
INEB- PSI Technical Report 2006-1 Neural network software tool development: exploring programming language options Alexandra Oliveira aao@fe.up.pt Supervisor: Professor Joaquim Marques de Sá June 2006
More information2. Distributed Handwriting Recognition. Abstract. 1. Introduction
XPEN: An XML Based Format for Distributed Online Handwriting Recognition A.P.Lenaghan, R.R.Malyan, School of Computing and Information Systems, Kingston University, UK {a.lenaghan,r.malyan}@kingston.ac.uk
More informationData a systematic approach
Pattern Discovery on Australian Medical Claims Data a systematic approach Ah Chung Tsoi Senior Member, IEEE, Shu Zhang, Markus Hagenbuchner Member, IEEE Abstract The national health insurance system in
More informationDynamic programming. Doctoral course Optimization on graphs - Lecture 4.1. Giovanni Righini. January 17 th, 2013
Dynamic programming Doctoral course Optimization on graphs - Lecture.1 Giovanni Righini January 1 th, 201 Implicit enumeration Combinatorial optimization problems are in general NP-hard and we usually
More informationPerformance Evaluation On Human Resource Management Of China S Commercial Banks Based On Improved Bp Neural Networks
Performance Evaluation On Human Resource Management Of China S *1 Honglei Zhang, 2 Wenshan Yuan, 1 Hua Jiang 1 School of Economics and Management, Hebei University of Engineering, Handan 056038, P. R.
More informationNeural Networks algorithms and applications
Neural Networks algorithms and applications By Fiona Nielsen 4i 12/12-2001 Supervisor: Geert Rasmussen Niels Brock Business College 1 Introduction Neural Networks is a field of Artificial Intelligence
More informationReinforcement Learning
Reinforcement Learning LU 2 - Markov Decision Problems and Dynamic Programming Dr. Joschka Bödecker AG Maschinelles Lernen und Natürlichsprachliche Systeme Albert-Ludwigs-Universität Freiburg jboedeck@informatik.uni-freiburg.de
More informationBLIND SOURCE SEPARATION OF SPEECH AND BACKGROUND MUSIC FOR IMPROVED SPEECH RECOGNITION
BLIND SOURCE SEPARATION OF SPEECH AND BACKGROUND MUSIC FOR IMPROVED SPEECH RECOGNITION P. Vanroose Katholieke Universiteit Leuven, div. ESAT/PSI Kasteelpark Arenberg 10, B 3001 Heverlee, Belgium Peter.Vanroose@esat.kuleuven.ac.be
More informationSignature verification using Kolmogorov-Smirnov. statistic
Signature verification using Kolmogorov-Smirnov statistic Harish Srinivasan, Sargur N.Srihari and Matthew J Beal University at Buffalo, the State University of New York, Buffalo USA {srihari,hs32}@cedar.buffalo.edu,mbeal@cse.buffalo.edu
More information