Automatic Diatom Identification.
Başlık:
Automatic Diatom Identification.
Yazar:
du Buf, Hans.
ISBN:
9789812777867
Yazar Ek Girişi:
Fiziksel Tanımlama:
1 online resource (329 pages)
Seri:
Series in Machine Perception and Artificial Intelligence ; v.51
Series in Machine Perception and Artificial Intelligence
İçerik:
Contents -- Preface -- Acknowledgments -- Authors' Affiliations -- Chapter 1 Introduction to ADIAC and This Book -- 1 History and structure of the project -- 2 Research in biology and diatoms -- 3 The chapters -- References -- Chapter 2 Diatoms: Organism and Image -- 1 General introduction -- 2 Introduction to the diatom cell -- 3 Classifying and identifying diatoms -- 4 Complications -- 5 Final comments -- References -- Chapter 3 Diatom Applications -- 1 Introduction -- 2 Forensic science: the diagnosis of drowning -- 3 Environmental monitoring -- 4 Palaeoecological applications -- References -- Chapter 4 ADIAC Imaging Techniques and Databases -- 1 Microscopy and image acquisition -- 2 Image Databases -- 3 Pandora taxonomic database -- 4 WWW database -- References -- Chapter 5 Human Error and Quality Assurance in Diatom Analysis -- 1 Introduction -- 2 Material and methods -- 3 Results -- 4 Discussion -- References -- Chapter 6 Contour Extraction -- 1 Introduction -- 2 Pre-segmentation -- 3 Contour extraction -- 4 Results -- 5 Conclusion -- References -- Chapter 7 Identification Using Classical and New Features in Combination with Decision Tree Ensembles -- 1 Introduction -- 2 Feature extraction -- 3 Classification by decision trees -- 4 Data sets used -- 5 Identification results -- 6 Conclusions -- References -- Chapter 8 Identification by Curvature of Convex and Concave Segments -- 1 Introduction -- 2 Feature extraction -- 3 Classifier and test sets -- 4 Implementation, CPU times and parameter selection -- 5 Identification results -- 6 Discussion and conclusions -- References -- Chapter 9 Identification by Contour Profiling and Legendre Polynomials -- 1 Introduction -- 2 Dynamic ellipse fitting and contour profiling -- 3 Legendre polynomials -- 4 Experimental results -- 5 Conclusions -- References.
Chapter 10 Identification by Gabor Features -- 1 Introduction -- 2 Contour processing and feature extraction -- 3 Ornamentation processing by grating and bar cell models -- 4 Identification tests -- 5 Discussion -- References -- Chapter 11 Identification by Mathematical Morphology -- 1 Introduction -- 2 Diatom contour analysis -- 3 Analysis of diatom ornamentation -- 4 Identification results -- 5 Conclusions -- References -- Chapter 12 Mixed-Method Identifications -- 1 Introduction -- 2 Integration module framework -- 3 Identification results -- ADIACweb -- an online identification system -- References -- Chapter 13 Automatic Slide Scanning -- 1 Introduction -- 2 Material and methods -- 3 Automatic slide scanning -- 4 Autofocusing -- 5 Multi-focus visualization techniques -- 6 Conclusions -- References -- Chapter 14 ADIAC Achievements and Future Work -- 1 Databases -- 2 Summary of identification results -- 3 Slide scanning and autofocusing -- 4 Problems and future research -- 5 Potential tools for routine diatom work -- Appendix: The Mixed Genera Data Set.
Özet:
This is the first book to deal with automatic diatom identification. It provides the necessary background information concerning diatom research, useful for both diatomists and non-diatomists. It deals with the development of electronic databases, image preprocessing, automatic contour extraction, the application of existing contour and ornamentation features and the development of new ones, as well as the application of different classifiers (neural networks, decision trees, etc.). These are tested using two image sets: (i) a very difficult set of Sellaphora pupula with 6 demes and 120 images; (ii) a mixed genera set with 37 taxa and approximately 800 images. The results are excellent, and recognition rates well above 90% have been achieved on both sets. The results are compared with identification rates obtained by human experts. One chapter of the book deals with automatic image capture, i.e. microscope slide scanning at different resolutions using a motorized microscope stage, autofocusing, multifocus fusion, and particle screening to select only diatoms and to reject debris. This book is the final scientific report of the European ADIAC project (Automatic Diatom Identification and Classification), and it lists the web-sites with the created public databases and an identification demo. Contents: Introduction to ADIAC and This Book (H Du Buf & M M Bayer); Diatoms: Organism and Image (D G Mann); Diatom Applications (R J Telford et al.); ADIAC Imaging Techniques and Databases (M M Bayer & S Juggins); Human Error and Quality Assurance in Diatom Analysis (M G Kelly et al.); Contour Extraction (S Fischer et al.); Identification Using Classical and New Features in Combination with Decision Tree Ensembles (S Fischer & H Bunke); Identification by Curvature of Convex and Concave Segments (R E Loke & H du Buf); Identification by Contour Profiling and
Legendre Polynomials (A Ciobanu & H du Buf); Identification by Gabor Features (L M Santos & H du Buf); Identification by Mathematical Morphology (M H F Wilkinson et al.); Mixed-Method Identifications (M A Westenberg & J B T M Roerdink); Automatic Slide Scanning (J L Pech-Pacheco & G Cristóbal); ADIAC Achievements and Future Work (H du Buf & M M Bayer). Readership: Researchers in pattern recognition and computer vision, researchers working with diatoms, and psychologists.
Notlar:
Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2017. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.
Tür:
Yazar Ek Girişi:
Elektronik Erişim:
Click to View