Demonstrates how automated identification can be applied to various organismal groups and in a range of contextsPresents current trends in quantitative approaches to the group-recognition problem in biologyProvides an introduction to neural nets written in an easily accessible, non-mathematical mannerIllustrates the capabilities of various software systems currently available for identifying systematic objects/groupsIncludes descriptions of highly developed applications for achieving image-based automated group identificationContains accessible descriptions of ABIS, DAISY, and SPIDA
The automated identification of biological objects or groups has been a dream among taxonomists and systematists for centuries. However, progress in designing and implementing practical systems for fully automated taxon identification has been frustratingly slow. Regardless, the dream has never died. Recent developments in computer architectures and innovations in software design have placed the tools needed to realize this vision in the hands of the systematics community, not several years hence, but now. And not just for DNA barcodes or other molecular data, but for digital images of organisms, digital sounds, digitized chemical data - essentially any type of digital data.
Based on evidence accumulated over the last decade and written by applied researchers, Automated Taxon Identification in Systematics explores contemporary applications of quantitative approaches to the problem of taxon recognition. The book begins by reviewing the current state of systematics and placing automated taxon identification in the context of contemporary trends, needs, and opportunities. The chapters present and evaluate different aspects of current automated system designs. They then provide descriptions of case studies in which different theoretical and practical aspects of the overall group-identification problem are identified, analyzed, and discussed.
A recurring theme through the chapters is the relationship between taxonomic identification, automated group identification, and morphometrics. This collection provides a bridge between these communities and between them and the wider world of applied taxonomy. The only book-length treatment that explores automated group identification in systematic context, this text also includes introductions to basic aspects of the fields of contemporary artificial intelligence and mathematical group recognition for the entire biological community.
Table of Contents
Introduction, N. MacLeod
Digital Innovation and Taxonomy's Finest Hour, Q.D. Wheeler
Natural Object Categorization: Man versus Machine, P.F. Culverhouse
Neural Networks in Brief, R. Lang
69Morphometrics and Computer Homology: An Old Theme Revisited, F.L. Bookstein
The Automated Identification of Taxa: Concepts and Applications, D. Chesmore
DAISY: A Practical Computer-Based Tool for Semi-Automated Species Identification, M.A. O'Neill
Automated Extraction and Analysis of Morphological Features for Species Identification, V. Steinhage, S. Schröder, K.-H. Lampe and A.B. Cremers
Introducing SPIDA-Web: Wavelets, Neural Networks and Internet Accessibility in an Image-Based Automated Identification System, K.N. Russell, M.T. Do, J.C. Huff and N.I. Platnick
Automated Tools for the Identification of Taxa from Morphological Data: Face Recognition in Wasps, N. MacLeod, M. O'Neill and S. Walsh
Pattern Recognition for Ecological Science and Environmental Monitoring: An Initial Report, E.N. Mortensen, E.L. Delgado, H. Deng, D. Lytle, A. Moldenke, R. Paasch, L. Shapiro, P. Wu, W. Zhang and T.G. Dietterich
Plant Identification from Characters and Measurements Using Artificial Neural Networks, J.Y. Clark
Spot the Penguin: Can Reliable Taxonomic Identifications Be Made Using Isolated Foot Bones? S.A. Walsh, N. MacLeod and M. O'Neill
A New Semi-Automatic Morphometric Protocol for Conodonts and a Preliminary Taxonomic Application, D. Jones and M. Purnell
Decision Trees: A Machine-Learning Method for Characterizing Morphological Patterns Resulting from Ecological Adaptation, M. Mendoza
Data Integration and Multifactorial Analyses: The Yeasts and the BioloMICS Software as a Case Study, R. Vincent
Automatic Measurement of Honeybee Wings, A. Tofilski
Good Performers Know Their Audience! Identification and Characterization of Pitch Contours in Infant- and Foreigner-Directed Speech, M.A. Knoll, S.A. Walsh, N. MacLeod, M. O'Neill and M. Uther