ADVANCES IN OBJECT RECOGNITION SYSTEMS potx

ADVANCESINOBJECT RECOGNITIONSYSTEMS  EditedbyIoannisKypraios            Advances in Object Recognition Systems Edited by Ioannis Kypraios Published by InTech Janeza Trdine 9, 51000 Rijeka, Croatia Copyright © 2012 InTech All chapters are Open Access distributed under the Creative Commons Attribution 3.0 license, which allows users to download, copy and build upon published articles even for commercial purposes, as long as the author and publisher are properly credited, which ensures maximum dissemination and a wider impact of our publications. After this work has been published by InTech, authors have the right to republish it, in whole or part, in any publication of which they are the author, and to make other personal use of the work. Any republication, referencing or personal use of the work must explicitly identify the original source. As for readers, this license allows users to download, copy and build upon published chapters even for commercial purposes, as long as the author and publisher are properly credited, which ensures maximum dissemination and a wider impact of our publications. Notice Statements and opinions expressed in the chapters are these of the individual contributors and not necessarily those of the editors or publisher. No responsibility is accepted for the accuracy of information contained in the published chapters. The publisher assumes no responsibility for any damage or injury to persons or property arising out of the use of any materials, instructions, methods or ideas contained in the book. Publishing Process Manager Sasa Leporic Technical Editor Teodora Smiljanic Cover Designer InTech Design Team First published May, 2012 Printed in Croatia A free online edition of this book is available at www.intechopen.com Additional hard copies can be obtained from orders@intechopen.com Advances in Object Recognition Systems, Edited by Ioannis Kypraios p. cm. ISBN 978-953-51-0598-5    Contents  Preface IX Section 1 Cognition, and Biologically-Inspired Systems 1 Chapter 1 Neural Basis of Object Recognition 3 R. Marra, D. Rotiroti and V. Rispoli Chapter 2 Spontaneous Object Recognition in Animals: A Test of Episodic Memory 25 Amy-Lee Kouwenberg, Gerard M. Martin, Darlene M. Skinner, Christina M. Thorpe and Carolyn J. Walsh Chapter 3 Performance Analysis of the Modified-Hybrid Optical Neural Network Object Recognition System Within Cluttered Scenes 39 Ioannis Kypraios Section 2 Colour Processing 71 Chapter 4 The Contribution of Color to Object Recognition 73 Inês Bramão, Luís Faísca, Karl Magnus Petersson and Alexandra Reis Section 3 Optical Correlators, and Artificial Neural Networks 89 Chapter 5 Advances in Adaptive Composite Filters for Object Recognition 91 Victor H. Diaz-Ramirez, Leonardo Trujillo and Sergio Pinto-Fernandez Chapter 6 The Use of Contour, Shape and Form in an Integrated Neural Approach for Object Recognition 111 I. Lopez-Juarez VI Contents Section 4 Applications 125 Chapter 7 Automatic Coin Classification and Identification 127 Reinhold Huber-Mörk, Michael Nölle, Michael Rubik, Michael Hödlmoser, Martin Kampel and Sebastian Zambanini Chapter 8 Non-Rigid Objects Recognition: Automatic Human Action Recognition in Video Sequences 155 Mehrez Abdellaoui, Ali Douik and Kamel Besbes    Preface  Aninvariant object recognition system needs to be ableto recognise the object under anyusuala prioridefineddistortionssuchastranslation,scalingandin‐planeandout‐ of‐planerotation.Ideally,thesystemshouldbe able to recognise (detect and classify) anycomplexsceneof objectsevenwithinbackgroundclu tternoise.  Thisproblemisa very complex and difficult one. In this book, we present recent advances towards achieving fully‐robust object recognition. In the book’s chapters’ cutting edge recent  researchisdiscussedindetailsfor allthereaderswitha core orwiderinterestin this area. In section 1, the relation and im portance of object recognition in the cognitive processesofhumansandanimalsisdescribedaswellashowhuman‐andanimal‐like cognitive processes can be used for the design of biologically‐inspired object recognitionsystems.Chapter1discussesabouttheneurophysiopathologyofattention, learning and memory. The n, it discusses about object recognition, and a novel object recognitiontestanditsroleinbuildinganexperimentalmodelofAlzheimer’sdisease. Chapter2discussesaboutepisodichumanmemoryandepisodic‐likeanimalmemory. Then, it discusses about object recognition and a novel object recognition task which canbeus edasanexperimentaltoolforinvestigatingfullepisodicmemoryindifferent animal species. Chapter 3 presents the performance analysis of the biologically‐ inspired modified‐hybrid optical neural network object recognition system within cluttered scenes. The system’s biologically‐inspired hybrid design is analysed and is showntocombineaknowledgerepresentationuni tbeingthe optical correlatorblock with a knowledge learning unit being the NNET block. Several experiments were conductedfortestingthesystem’sproblemsolvingabilitiesaswellasitsperformance inrecognisingmultipleobjectsofthesameordifferentclasseswithinclutteredscenes. In section 2, we discuss about colour processing and how it can be used to improve object recognition. Chapter 4 reviews the current state‐of‐the‐art research about the specificroleofcolourinformationinobjectrecognition.Then,itinvestigatestheroleof colourintherecognitionofcolourandnon‐colourdiagnosticobjectsatdiff erentlevels ofthebrain’svisualprocessing. In literature, we can identify two main categories of object recognition systems. The firstcategoryconsistsoflinearcombinatorialtypefilters.Thesecondcategoryconsists X Preface of pure neural modelling approaches. In section 3, we discuss about those two categoriesofopticalcorrelatorsandofartificialneuralnetworks,respectively.Chapter 5presentsaniterativeapproachforsynthesizingadaptivecompositecorrelationfilters forobjectrecognition.Theapproachcanbeusedforimprovingthequalityofasimple composite f ilter in terms of quality metrics using all available information about the true‐class object to be recognised and false‐class objects to be rejected such as the background. Two different filters employing this iterative approach are described. First, an adaptive constrained filter is described which optimises its class discrimination properties, an d, second, an adaptive unconstrained composite filter is describedwhichoptimisesitspropertieswithrespecttotheaveragecorrelationheight (ACH), average correlation energy (ACE) and average similarity measure (ASM). Chapter 6 presents a method of integrating image features from the object’s contour, itstypeofcurvature ortopographicalsurfaceinform ationanddepthinformationfrom astereocamera,andthenafterbeingconcatenatedformaninvariantvectordescriptor which is input to a Fuzzy ARTMAP artificial neural network for learning and recognitionpurposes.Experimentalresultsarediscussedwhenusingasinglecontour vectordescription(BOF),acombinationofsurfaceinformationvector(SFS)withBOF, andthefullconcatenatedvectorofBOF+SFS+Depth. In section 4, we present two different applications of object recognition with still images and with video sequences. Chapter 7 presents an application of object recognitionfor the discrimination of modern coins into several hundreds of different classes,andtheidentif icationof hand‐madeancientcoins.Modern coinsareacquired byamachinevisionsystemforcoinsortingbutforancientcoinsascannerandcamera devices are considered. In particularly, the use of a 3D acquisition device and 3D models of ancient coins are discussed. Different methods of segmentation are dis cussed for modern and ancient coins. Two main methods for classification are compared, one based on matching edge features in log‐polar space and a second methodbasedonaneigenspacerepresentation.Fortheidentificationofcoinsfeatures extracted from the edge of a coin and from the Fourier domain representation of the coincontou rareused,andaBayesianfusionofcoinsidesisstudied.Improvementby 3D analysis and modelling is also presented. Results are discussed for all considered datasets and methods. Chapter 8 presents an application of non‐rigid objects recognition in video sequences. An approach for recognising human act ion using spatiotemporal interest points (STIPs) is described. The STIPs are detected by employingdifferent  detectors.Severalmotionanalysistechniquesarepresented,such as activity function, human body interest regions, and spatiotemporal boxes. Those techniques can be applied on a set of detected STIPs as an effective way of act ion representation.Severalmotionclassificationalgorithmsarediscussed,suchassupport vectormachines(SVM),probabilisticlatentsemanticanalysis(pLSA)andothers,anda proposed by the authors algorithm based on unsupervised k‐means clustering algorithm. The proposed algorithm is compared with existing algorithms by being testedwiththeKTHhumanactiondataba se.