ADVANCESINOBJECT RECOGNITIONSYSTEMS EditedbyIoannisKypraios 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 Aninvariant object recognition system needs to be ableto recognise the object under anyusuala prioridefineddistortionssuchastranslation,scalingandin‐planeandout‐ of‐planerotation.Ideally,thesystemshouldbe able to recognise (detect and classify) anycomplexsceneof objectsevenwithinbackgroundclu tternoise. Thisproblemisa 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 researchisdiscussedindetailsfor allthereaderswitha core orwiderinterestin this area. In section 1, the relation and im portance of object recognition in the cognitive processesofhumansandanimalsisdescribedaswellashowhuman‐andanimal‐like cognitive processes can be used for the design of biologically‐inspired object recognitionsystems.Chapter1discussesabouttheneurophysiopathologyofattention, learning and memory. The n, it discusses about object recognition, and a novel object recognitiontestanditsroleinbuildinganexperimentalmodelofAlzheimer’sdisease. Chapter2discussesaboutepisodichumanmemoryandepisodic‐likeanimalmemory. Then, it discusses about object recognition and a novel object recognition task which canbeus edasanexperimentaltoolforinvestigatingfullepisodicmemoryindifferent 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 showntocombineaknowledgerepresentationuni tbeingthe optical correlatorblock with a knowledge learning unit being the NNET block. Several experiments were conductedfortestingthesystem’sproblemsolvingabilitiesaswellasitsperformance inrecognisingmultipleobjectsofthesameordifferentclasseswithinclutteredscenes. 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 specificroleofcolourinformationinobjectrecognition.Then,itinvestigatestheroleof colourintherecognitionofcolourandnon‐colourdiagnosticobjectsatdiff erentlevels ofthebrain’svisualprocessing. In literature, we can identify two main categories of object recognition systems. The firstcategoryconsistsoflinearcombinatorialtypefilters.Thesecondcategoryconsists X Preface of pure neural modelling approaches. In section 3, we discuss about those two categoriesofopticalcorrelatorsandofartificialneuralnetworks,respectively.Chapter 5presentsaniterativeapproachforsynthesizingadaptivecompositecorrelationfilters forobjectrecognition.Theapproachcanbeusedforimprovingthequalityofasimple 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 describedwhichoptimisesitspropertieswithrespecttotheaveragecorrelationheight (ACH), average correlation energy (ACE) and average similarity measure (ASM). Chapter 6 presents a method of integrating image features from the object’s contour, itstypeofcurvature ortopographicalsurfaceinform ationanddepthinformationfrom astereocamera,andthenafterbeingconcatenatedformaninvariantvectordescriptor which is input to a Fuzzy ARTMAP artificial neural network for learning and recognitionpurposes.Experimentalresultsarediscussedwhenusingasinglecontour vectordescription(BOF),acombinationofsurfaceinformationvector(SFS)withBOF, andthefullconcatenatedvectorofBOF+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 recognitionfor the discrimination of modern coins into several hundreds of different classes,andtheidentif icationof hand‐madeancientcoins.Modern coinsareacquired byamachinevisionsystemforcoinsortingbutforancientcoinsascannerandcamera 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 methodbasedonaneigenspacerepresentation.Fortheidentificationofcoinsfeatures extracted from the edge of a coin and from the Fourier domain representation of the coincontou rareused,andaBayesianfusionofcoinsidesisstudied.Improvementby 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 employingdifferent detectors.Severalmotionanalysistechniquesarepresented,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.Severalmotionclassificationalgorithmsarediscussed,suchassupport vectormachines(SVM),probabilisticlatentsemanticanalysis(pLSA)andothers,anda proposed by the authors algorithm based on unsupervised k‐means clustering algorithm. The proposed algorithm is compared with existing algorithms by being testedwiththeKTHhumanactiondataba se.