Content-based microscopic image analysis / vorgelegt von M. Sc. Chen Li.

Format:

Book

Author/Creator:

Li, Chen, 1985 April 22- author.

Series:

Studien zur Mustererkennung ; Band 39.

Studien zur Mustererkennung ; Band 39

Language:

English

German

Subjects (All):

Image processing.

Image analysis--Data processing.

Image analysis.

Microscopy--Data processing.

Microscopy.

Physical Description:

1 online resource (xxiv, 171 pages) : illustrations.

Edition:

1st ed.

Place of Publication:

Berlin : Logos Verlag Berlin, [2016]

Language Note:

In English and German.

Summary:

Long description: In this dissertation, novel Content-based Microscopic Image Analysis (CBMIA) methods, including Weakly Supervised Learning (WSL), are proposed to aid biological studies. In a CBMIA task, noisy image, image rotation, and object recognition problems need to be addressed. To this end, the first approach is a general supervised learning method, which consists of image segmentation, shape feature extraction, classification, and feature fusion, leading to a semi-automatic approach. In contrast, the second approach is a WSL method, which contains Sparse Coding (SC) feature extraction, classification, and feature fusion, leading to a full-automatic approach. In this WSL approach, the problems of noisy image and object recognition are jointly resolved by a region-based classifier, and the image rotation problem is figured out through SC features. To demonstrate the usefulness and potential of the proposed methods, experiments are implemented on different practical biological tasks, including environmental microorganism classification, stem cell analysis, and insect tracking.

Contents:

Intro

1 Introduction

1.1 Fundamental Concept of Content-based Microscopic Image Analysis

1.2 Motivation of the Present Work

1.3 Contribution of the Present Work

1.4 Overview of this Dissertation

2 RelatedWork

2.1 Related Algorithms in CBMIA

2.1.1 Image Segmentation

2.1.2 Shape Features

2.1.3 Sparse Coding Features

2.1.4 Supervised Learning

2.1.5 Unsupervised Learning

2.1.6 Object Detection and Tracking

2.2 Biological Applications Using CBMIA

2.2.1 Microorganism Classification

2.2.2 Cell Clustering

2.2.3 Insect Tracking

2.3 Summary

3 Semi-automatic Microscopic Image Classification Using Strongly Supervised Learning

3.1 Overview of the System

3.2 Image Segmentation

3.2.1 Sobel Edge Detection and Morphological Operations

3.2.2 Semi-automatic Image Segmentation

3.3 Global Shape Features

3.3.1 Isomerous Edge Histogram Descriptor

3.3.2 Basic Geometrical Features

3.3.3 Fourier Descriptor

3.3.4 Internal Structure Histogram

3.4 Local Shape Features

3.5 Strongly Supervised Learning

3.5.1 Fundamentals of SVM

3.5.2 Radial Basis Function Kernel SVM

3.5.3 Late Fusion of SVM

3.6 Summary

4 Full-automatic Microscopic Image Classification Using Weakly Supervised Learning

4.1 Overview of the System

4.2 Sparse Coding Features

4.2.1 Sparse Coding

4.2.2 Non-negative Sparse Coding

4.3 Weakly Supervised Learning

4.3.1 Basic RBSVM

4.3.2 Improved RBSVM

4.4 Summary

5 Microscopic Image Clustering Using Unsupervised Learning

5.1 Overview of the System

5.2 Full-automatic Image Segmentation

5.2.1 Motivation

5.2.2 Techniques

5.3 Global Shape Features

5.3.1 Edge Histogram Descriptor

5.3.2 Higher-level Geometrical Feature

5.3.3 Shape Signature Histogram

5.3.4 Shape Context Feature

5.4 Unsupervised Learning.

5.4.1 k-means Clustering

5.4.2 Clustering Evaluation

5.5 Summary

6 Object Tracking Using Interactive Learning

6.1 Fundamental Conception

6.2 Preliminaries

6.2.1 Object Detection and Preprocessing

6.2.2 Anatomical Model of Insect Body Parts

6.3 Interactive Object Tracking Framework

6.3.1 Object Classification

6.3.2 Constrained Frame-to-Frame Linking

6.3.3 Interactive KF Estimation and Annotation Query

6.3.4 Track Linking Through Merge Conditions

6.4 Summary

7 Applications and Experiments

7.1 Environmental Microorganism Classification

7.1.1 EM Dataset

7.1.2 Classification Using SSL

7.1.3 Classification Using WSL

7.2 Stem Cell Analysis and Clustering

7.2.1 Evaluation of Segmentation

7.2.2 Evaluation of Clustering

7.3 Insect Body Parts Tracking

7.3.1 Dataset and Experimental Setting

7.3.2 Experimental Results

7.4 Extended Experiments

7.4.1 CBMIR on EMDS Images

7.4.2 Late Fusion of Global Shape Features on MPEG-7 Dataset

7.4.3 EM Classification Using Pair-wise Local Features

7.5 Summary

8 Conclusion and Future Work

8.1 Conclusion

8.2 Future Work

List of Publications.

Notes:

PublicationDate: 20160515

Includes bibliographical references (pages 147-167).

Description based on print version record.

ISBN:

3-8325-8810-8

9783832588106