Progress in pattern recognition, image analysis, computer vision, and applications : 15th Iberoamerican Congress on Pattern Recognition, CIARP 2010, São Paulo, Brazil, November 8-11, 2010 ; proceedings

This book constitutes the refereed proceedings of the 15th iberoamerican Congress on Pattern Recognition, CIARP 2010, held in Sao Paulo, Brazil, in November 2010. The 70 revised full papers presented were carefully reviewed and selected from 145 submissions. The papers feature current research on mathematical methods and computing techniques for pattern recognition, computer vision, image analysis, and speech recognition, as well as their applications in such diverse areas as robotics, industry, health, entertainment, space exploration, telecommunications, data mining, document analysis, and natural language processing and recognition to name only few of them. Cover......Page p0001.djvu Lecture Notes in Computer Science 6419......Page p0002.djvu Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications......Page p0003.djvu Preface......Page p0005.djvu Organization......Page p0007.djvu Table of Contents......Page p0011.djvu Recent Advances in Kernel Machines......Page p0018.djvu Design of Pattern Classifiers Using Optimum-Path Forest with Applications in Image Analysis......Page p0019.djvu Vision-Based Control of Robot Motion......Page p0020.djvu Soft Computing, f-Granulation and Pattern Recognition......Page p0021.djvu Computational Illumination......Page p0022.djvu Introduction......Page p0023.djvu Walks on Color Images and Texture Signature......Page p0025.djvu Experiments and Results......Page p0026.djvu References......Page p0029.djvu Introduction......Page p0031.djvu Fractal Dimension Based Approach......Page p0032.djvu Evaluation of the Shape Descriptor......Page p0033.djvu Compared Approaches......Page p0034.djvu Results......Page p0035.djvu Conclusions......Page p0036.djvu References......Page p0037.djvu Introduction......Page p0039.djvu Preliminaries......Page p0040.djvu The Algorithm......Page p0041.djvu Experimental Results......Page p0043.djvu Concluding Remarks......Page p0045.djvu References......Page p0046.djvu Introduction......Page p0047.djvu Formal Definitions......Page p0048.djvu Edge Attributes Handling......Page p0050.djvu Databases......Page p0051.djvu Results......Page p0052.djvu Conclusions......Page p0053.djvu References......Page p0054.djvu Introduction......Page p0055.djvu Hypergraph Reduction and Properties......Page p0056.djvu Application: Joint Segmentation and Superpixels Classification......Page p0058.djvu Experimental Results......Page p0059.djvu Conclusions and Perspectives......Page p0061.djvu References......Page p0062.djvu Introduction......Page p0063.djvu Clustering by Minimum Spanning Tree Approach......Page p0064.djvu Video Summarization Using Minimum Spanning Tree......Page p0067.djvu Experiments......Page p0068.djvu References......Page p0070.djvu Introduction......Page p0072.djvu pLSA model......Page p0073.djvu Local Region Description Based on the Staining Component Analysis......Page p0074.djvu Local Region Selection......Page p0075.djvu Local Region Description......Page p0076.djvu Results and Discussion......Page p0077.djvu References......Page p0079.djvu Introduction......Page p0080.djvu Mixture Model-Based Image Segmentation......Page p0081.djvu ETM Algorithm......Page p0082.djvu Results......Page p0084.djvu Discussion......Page p0086.djvu References......Page p0087.djvu Introduction......Page p0088.djvu Generation of the Natural Multifractal Model......Page p0089.djvu Validation of the Model......Page p0090.djvu Application: MRI Classification......Page p0091.djvu The Proposed Method......Page p0092.djvu Results and Discussion......Page p0093.djvu Conclusions......Page p0094.djvu References......Page p0095.djvu Introduction......Page p0096.djvu Previous Work on Zernike Moments......Page p0097.djvu First Modification: Higher Order Weighting......Page p0098.djvu Second Modification: PCA ZMs......Page p0099.djvu Results and Final Remarks......Page p0100.djvu References......Page p0103.djvu Introduction......Page p0104.djvu MEB Problems and Support Vector Machines......Page p0105.djvu Approximate MEBs and Core Vector Machines......Page p0106.djvu The New Algorithm for MEB-SVMs......Page p0108.djvu Experiments and Conclusions......Page p0109.djvu References......Page p0111.djvu Introduction......Page p0113.djvu Non-Negative Matrix Factorization......Page p0114.djvu Multiple Back-Propagation......Page p0115.djvu Image Pre-processing......Page p0116.djvu Parts-Based Representation of the Images Yale Data Base......Page p0117.djvu Results and Discussion......Page p0118.djvu Conclusions and Future Work......Page p0119.djvu References......Page p0120.djvu Introduction......Page p0121.djvu The HWR System......Page p0123.djvu Overview......Page p0124.djvu Recognition Confidence......Page p0125.djvu Experimental Evaluation......Page p0126.djvu References......Page p0128.djvu Introduction ......Page p0130.djvu Feature Selection in Dynamic Hierarchical Compact Algorithm ......Page p0131.djvu F1-Travel Quality Measure......Page p0133.djvu Experimental Results......Page p0135.djvu References......Page p0137.djvu Introduction......Page p0138.djvu Fresnel Reflection......Page p0139.djvu Background Division......Page p0140.djvu Results......Page p0142.djvu Conclusions......Page p0143.djvu References......Page p0144.djvu Introduction......Page p0145.djvu The Incremental Gaussian Mixture Model......Page p0146.djvu Experimental Results......Page p0150.djvu Conclusion......Page p0151.djvu References......Page p0152.djvu Introduction......Page p0153.djvu Speech Recognizer Architecture......Page p0154.djvu Database Description......Page p0156.djvu Comparing Phonological and Acoustic Representation Spaces......Page p0157.djvu Concluding Remarks......Page p0159.djvu References......Page p0160.djvu Introduction......Page p0161.djvu Feature Selection......Page p0162.djvu Yeast Cell-Cycle Stochastic Restricted Boolean Model......Page p0163.djvu Experimental Results......Page p0164.djvu Conclusion......Page p0167.djvu References......Page p0168.djvu Introduction......Page p0170.djvu General Framework......Page p0171.djvu Convergence of the Cost Function......Page p0172.djvu Simulations......Page p0174.djvu References......Page p0177.djvu Introduction......Page p0178.djvu The Images......Page p0179.djvu The Segmentation Algorithms and Distance Measures......Page p0180.djvu Quantitative Measures......Page p0181.djvu Results......Page p0182.djvu References......Page p0184.djvu Introduction......Page p0186.djvu Description of $(2,n)$-Threshold Image Secret Sharing Scheme Proposed by Rey.M.D ......Page p0187.djvu Recovering the Original Image from a Single Share......Page p0189.djvu Experimental Results......Page p0190.djvu References......Page p0192.djvu Introduction......Page p0193.djvu Matching Pursuits......Page p0194.djvu K-SVD......Page p0195.djvu Experimental Results......Page p0196.djvu References......Page p0199.djvu Introduction......Page p0201.djvu A Dissimilarity Measure......Page p0202.djvu Our Method for Transition Detection ......Page p0204.djvu Experiments......Page p0206.djvu References......Page p0208.djvu Dis)Similarity Measures for Trajectories......Page p0210.djvu Proposed Approach......Page p0213.djvu Experimental Results in Anomaly Detection......Page p0214.djvu Conclusions......Page p0217.djvu References......Page p0218.djvu Introduction......Page p0219.djvu System Overview......Page p0220.djvu Selected Key-Frames......Page p0221.djvu Building Models......Page p0222.djvu Construction of Database of Models......Page p0224.djvu Shape Matching......Page p0225.djvu Tests and Results......Page p0226.djvu References......Page p0227.djvu Introduction......Page p0229.djvu Technical Setup......Page p0230.djvu Data Base Description......Page p0231.djvu Global Threshold Detection (GDT)......Page p0232.djvu Local Threshold Detection with Tracking (LTD-T)......Page p0233.djvu Experiments and Results......Page p0234.djvu Conclusions and Future Work......Page p0235.djvu References......Page p0236.djvu Introduction......Page p0237.djvu Cluster-Based Reconstruction......Page p0238.djvu The Algorithm......Page p0239.djvu Detection and Compensation of Unreliable Components......Page p0240.djvu Results......Page p0241.djvu Conclusions and Future Work......Page p0243.djvu References......Page p0244.djvu Introduction......Page p0245.djvu Proposed Classifier......Page p0246.djvu Preprocessing Phase......Page p0247.djvu Experimental Results......Page p0248.djvu Conclusions......Page p0251.djvu References......Page p0252.djvu Introduction......Page p0253.djvu Signal Pre-processing......Page p0254.djvu Wavelet Packet Transform......Page p0255.djvu SVM Classifier......Page p0256.djvu Experiments and Results......Page p0258.djvu References......Page p0259.djvu Introduction......Page p0261.djvu LPC Feature Analysis......Page p0263.djvu Hidden Markov Model......Page p0265.djvu Performance Based on Punjabi Numerals......Page p0266.djvu References......Page p0268.djvu Introduction......Page p0270.djvu Determination of Feature Vectors......Page p0271.djvu Generation of Training Instances......Page p0272.djvu Learning Algorithms......Page p0273.djvu Combination of Classifiers......Page p0274.djvu Results Obtained......Page p0275.djvu References......Page p0276.djvu Introduction......Page p0278.djvu Related Work......Page p0279.djvu Searching for Topic Cohesion......Page p0280.djvu Detecting the Topic Segment Boundaries......Page p0281.djvu Evaluation......Page p0282.djvu References......Page p0284.djvu Introduction......Page p0286.djvu License Plate Detection......Page p0287.djvu Classification......Page p0290.djvu Experimental Results......Page p0291.djvu References......Page p0293.djvu Introduction......Page p0294.djvu Neighborhood Selection for Synthetic Images......Page p0295.djvu PCA and NLM......Page p0296.djvu NLM Using PCA Neighborhoods......Page p0298.djvu Discussion, Conclusions and Future Work......Page p0300.djvu References......Page p0301.djvu Introduction......Page p0302.djvu Striping Noise and Its Reduction......Page p0305.djvu Quality Indexes......Page p0306.djvu Results......Page p0308.djvu Conclusions......Page p0310.djvu References......Page p0311.djvu Introduction......Page p0312.djvu Initialization and Preprocessing......Page p0313.djvu Vessel Tangent Estimation......Page p0314.djvu Synthetic Images......Page p0315.djvu Real Images......Page p0316.djvu Discussion and Conclusions......Page p0318.djvu References......Page p0319.djvu Introduction......Page p0320.djvu Bilateral Filtering......Page p0321.djvu Segmentation Process with Self-calibration Framework......Page p0322.djvu Segmentation Process with Definiens Developper Software......Page p0324.djvu Results......Page p0325.djvu Conclusions......Page p0326.djvu References......Page p0327.djvu Introduction......Page p0328.djvu Bilateral Filter......Page p0329.djvu Image Fusion with Bilateral Filter......Page p0330.djvu Quality Determination - Comparison with Other Techniques......Page p0331.djvu Results......Page p0332.djvu Conclusion......Page p0334.djvu References......Page p0335.djvu Introduction......Page p0336.djvu Previous Works......Page p0337.djvu Description of the Method......Page p0338.djvu Calculation of Average Hue......Page p0340.djvu Results and Discussion......Page p0342.djvu Conclusions......Page p0344.djvu References......Page p0345.djvu Introduction......Page p0346.djvu Related Works......Page p0347.djvu Pixel Affinity Graph......Page p0348.djvu Quadtree-Based Similarity Graph......Page p0349.djvu Algorithm Overview......Page p0350.djvu Experiments......Page p0351.djvu References......Page p0353.djvu Introduction......Page p0355.djvu The Studied Fusion System......Page p0356.djvu Importance of the Extraction Step......Page p0358.djvu Principle of Genetic Algorithm......Page p0359.djvu Illustration on 3D Tomography Image Interpretation......Page p0360.djvu Conclusions......Page p0361.djvu References......Page p0362.djvu Introduction......Page p0363.djvu Atomic Functions......Page p0364.djvu Quaternion Atomic Function......Page p0365.djvu Quaternion Atomic Wavelet Function......Page p0366.djvu Results......Page p0367.djvu References......Page p0369.djvu Introduction......Page p0371.djvu Texture as a Pixel Network......Page p0372.djvu Evaluation......Page p0374.djvu Experiments......Page p0375.djvu Results and Discussion......Page p0376.djvu Conclusion......Page p0377.djvu References......Page p0378.djvu Introduction......Page p0379.djvu Gabor Wavelets......Page p0380.djvu Volumetric Fractal Dimension......Page p0381.djvu Experimentation and Evaluation......Page p0382.djvu Conclusions......Page p0384.djvu References......Page p0385.djvu Introduction......Page p0387.djvu Fourier Descriptors......Page p0388.djvu Zernike Moments......Page p0389.djvu Experimental Results......Page p0390.djvu Comparison of Methods......Page p0391.djvu References......Page p0394.djvu Introduction......Page p0395.djvu Adaptive Directional Mask......Page p0396.djvu Ridge Direction and Geodesic Distance......Page p0397.djvu Experiments......Page p0400.djvu Conclusions......Page p0401.djvu References......Page p0402.djvu Introduction......Page p0403.djvu Proposed Detectors......Page p0404.djvu The Frangi Filter......Page p0405.djvu Parameter Estimation......Page p0406.djvu Experimental Results......Page p0407.djvu Conclusions......Page p0409.djvu References......Page p0410.djvu Introduction......Page p0411.djvu Orthogonal Moments......Page p0412.djvu Experimental Results......Page p0413.djvu Comparison of Feature Extraction Methods......Page p0414.djvu Discriminating Capability of Orthogonal Moments......Page p0415.djvu Effect of Moment Order in Classification Results......Page p0416.djvu References......Page p0417.djvu Introduction......Page p0419.djvu Overview of Face Segmentation in Thermal Infrared ImagES......Page p0420.djvu Proposed Method......Page p0421.djvu Experimental Results......Page p0422.djvu Experimental Results and Discussion......Page p0423.djvu Conclusion......Page p0425.djvu References......Page p0426.djvu Introduction......Page p0427.djvu Illumination Compensation Using DCT in Log Domain......Page p0428.djvu The New Photometric Normalisation Method......Page p0429.djvu Experimental Evaluation......Page p0430.djvu Classifier Fusion......Page p0432.djvu References......Page p0433.djvu Introduction......Page p0435.djvu Related Work......Page p0437.djvu Experimental Results......Page p0439.djvu Conclusions......Page p0441.djvu References......Page p0442.djvu Introduction......Page p0443.djvu Measures......Page p0444.djvu Face Recognition Using Complex Networks......Page p0445.djvu Feature Vector Extraction......Page p0446.djvu Analysis of the Method Parameters......Page p0447.djvu Comparing with Other Methods......Page p0448.djvu Conclusion......Page p0449.djvu References......Page p0450.djvu Introduction......Page p0451.djvu Quaternion Theory......Page p0452.djvu Image Quaternion Representation in the Frequency Domain......Page p0453.djvu Experimental Evaluation......Page p0454.djvu Verification Experiment......Page p0455.djvu Identification Experiment......Page p0456.djvu References......Page p0457.djvu Introduction......Page p0459.djvu The A Contrario Framework......Page p0460.djvu Iris Template Matching......Page p0461.djvu Partitioning the Iris Template......Page p0462.djvu Performance Evaluation......Page p0463.djvu Results......Page p0464.djvu Conclusions......Page p0465.djvu References......Page p0466.djvu Introduction......Page p0467.djvu Definition of DBNR in a General Setting......Page p0468.djvu Specification in the Gaussian Case......Page p0469.djvu Simulation Results......Page p0470.djvu Conclusions......Page p0473.djvu References......Page p0474.djvu Introduction......Page p0475.djvu Volcano Monitoring......Page p0477.djvu The Analytic Signal......Page p0478.djvu Circular Statistics......Page p0479.djvu Wavelet Transform......Page p0480.djvu Results......Page p0481.djvu References......Page p0482.djvu Introduction......Page p0484.djvu Optimum-Path Forest Classifier......Page p0485.djvu Optimum-Path Forest Classifier with Outliers Detection: OPF-OD......Page p0487.djvu Results......Page p0489.djvu References......Page p0491.djvu Introduction......Page p0493.djvu M-Step......Page p0495.djvu Initialization......Page p0496.djvu Results......Page p0497.djvu Conclusion......Page p0499.djvu References......Page p0500.djvu Introduction......Page p0501.djvu Background......Page p0502.djvu SMO Algorithm for the AD-SVM......Page p0503.djvu Selection Strategy......Page p0504.djvu Algorithm Structure......Page p0505.djvu Experiments and Conclusions......Page p0506.djvu References......Page p0508.djvu Introduction......Page p0509.djvu Data Sets......Page p0511.djvu Support Vector Regression......Page p0512.djvu Experimental Results......Page p0513.djvu References......Page p0515.djvu Introduction......Page p0517.djvu Model-Free Approach to Fault Diagnosis......Page p0518.djvu Feature Selection......Page p0519.djvu Best Selected Feature Subsets Ensemble Creation......Page p0520.djvu Studied Classification Approaches......Page p0521.djvu Misalignment Predictor Overproduced SVMs......Page p0522.djvu $5\times2$ Cross-Validation Estimation Results......Page p0523.djvu References......Page p0524.djvu Introduction......Page p0526.djvu Semi-Supervised Learning......Page p0527.djvu Multi-Objective Learning......Page p0528.djvu Multi-Objective Semi-Supervised Feature Selection (MOBJ-SSFS)......Page p0529.djvu Results and Discussions......Page p0530.djvu References......Page p0532.djvu Introduction......Page p0534.djvu ANNs Trained with Simulated Annealing......Page p0535.djvu ROC Az Error with Simulated Annealing......Page p0536.djvu Experimental Setup......Page p0537.djvu Results and Discussion......Page p0538.djvu Conclusions......Page p0540.djvu References......Page p0541.djvu Introduction......Page p0542.djvu Partition Selection Based on Cluster Ensemble......Page p0543.djvu Computational Complexity Analysis......Page p0546.djvu Experimental Results......Page p0547.djvu Conclusions......Page p0548.djvu References......Page p0549.djvu Introduction......Page p0550.djvu Automated Galaxy Classification......Page p0551.djvu Radial Basis Function Networks......Page p0552.djvu Experimental Results......Page p0553.djvu References......Page p0556.djvu Introduction......Page p0558.djvu Contextual Information Representation......Page p0559.djvu Exploiting Contextual Information for Image Re-ranking......Page p0560.djvu Impact of Parameters......Page p0562.djvu Experimental Results......Page p0563.djvu Conclusions......Page p0564.djvu References......Page p0565.djvu Introduction......Page p0566.djvu Visual Description of Images......Page p0567.djvu Our Proposed Spatial Descriptor......Page p0568.djvu The Spatial Relationship Similarity......Page p0569.djvu Matching Strategy......Page p0570.djvu Experiment Description and Results......Page p0571.djvu Conclusions......Page p0572.djvu References......Page p0573.djvu Introduction......Page p0574.djvu Ontologies......Page p0575.djvu Data-Representation Ontology (DRO)......Page p0576.djvu Structure of the DRO......Page p0577.djvu Principals Steps for Automatic Generation of DRO......Page p0578.djvu Semantic Abstraction of Geographical Data......Page p0579.djvu Classification of Data Representation Nodes (DRN)......Page p0580.djvu Experimental Results......Page p0581.djvu References......Page p0584.djvu Author Index......Page p0586.djvu Pattern recognition is a central topic in contemporary computer sciences, with continuously evolving topics, challenges, and methods, including machine learning, content-based image retrieval, and model- and knowledge-based - proaches, just to name a few. The Iberoamerican Congress on Pattern Recog- tion (CIARP) has become established as a high-quality conference, highlighting the recent evolution of the domain. These proceedings include all papers presented during the 15th edition of this conference, held in Sao Paulo, Brazil, in November 2010. As was the case for previous conferences, CIARP 2010 attracted parti- pants from around the world with the aim of promoting and disseminating - going research on mathematical methods and computing techniques for pattern recognition, computer vision, image analysis, and speech recognition, as well as their applications in such diverse areas as robotics, health, entertainment, space exploration, telecommunications, data mining, document analysis,and natural language processing and recognition, to name only a few of them. Moreover, it provided a forum for scienti?c research, experience exchange, sharing new kno- edge and increasing cooperation between research groups in pattern recognition and related areas. It is important to underline that these conferences have contributed sign- icantly to the growth of national associations for pattern recognition in the Iberoamerican region, all of them as members of the International Association for Pattern Recognition (IAPR). Pattern recognition is a central topic in contemporary computer sciences, with continuously evolving topics, challenges, and methods, including machine learning, content-based image retrieval, and model- and knowledge-based - proaches, just to name a few. The Iberoamerican Congress on Pattern Recog- tion (CIARP) has become established as a high-quality conference, highlighting the recent evolution of the domain. These proceedings include all papers presented during the 15th edition of this conference, held in Sao Paulo, Brazil, in November 2010. As was the case for previous conferences, CIARP 2010 attracted parti- pants from around the world with the aim of promoting and disseminating - going research on mathematical methods and computing techniques for pattern recognition, computer vision, image analysis, and speech recognition, as well as their applications in such diverse areas as robotics, health, entertainment, space exploration, telecommunications, data mining, document analysis, and natural language processing and recognition, to name only a few of them. Moreover, it provided a forum for scienti?c research, experience exchange, sharing new kno- edge and increasing cooperation between research groups in pattern recognition and related areas. It is important to underline that these conferences have contributed sign- icantly to the growth of national associations for pattern recognition in the Iberoamerican region, all of them as members of the International Association for Pattern Recognition (IAPR)