Principles of digital image processing for agricultural applications / Suryaprabha Deenan, Satheeshkumar Janakiraman, Seenivasan Nagachandrabose.

Format:

Book

Author/Creator:

Deenan, Suryaprabha, author.

Nagachandrabose, Seenivasan, author.

Janakiraman, Satheeshkumar, author.

Series:

Agriculture Issues and Policies

Language:

English

Subjects (All):

Agricultural innovations.

Image processing--Digital techniques.

Image processing.

Agricultural informatics.

Physical Description:

1 online resource (184 pages)

Edition:

1st ed.

Place of Publication:

New York, New York : Nova Science Publishers, [2023]

Summary:

"This book is designed for undergraduate and post-graduate agricultural science students and agricultural engineering researchers to provide a comprehensive insight into the role of digital image processing in agriculture, and its basic principles to solve agriculture issues. This book is constructed with 11 different chapters comprising an introduction to digital image processing, various applications of digital image processing, the role of image processing in the agriculture sector, an overview of fundamental digital image processing procedures, image acquisition methods appropriate for various agricultural situations, image enhancement tools for images acquired in different conditions, image segmentation methods concerned with plant and agriculture images, feature extraction techniques applicable for agricultural images, image classification or pattern recognition to solve agricultural problems, quality assessment metrics of reference and non-reference agriculturally important images and a case study on successful digital image processing application on the banana"-- Provided by publisher.

Contents:

Intro

Contents

Preface

Chapter 1

Introduction to Digital Image Processing

1.1. Basic Modules in Image Processing

1.1.1. Formation

1.1.2. Enhancement

1.1.3. Visualization

1.1.4. Analysis

1.1.5. Management

Chapter 2

Various Applications of Digital Image Processing

2.1. Medical Sector

2.2. Law Enforcement Sector

2.3. Satellite Remote Sensing Sector

2.4. Civil Engineering Sector

2.5. Mechanical Engineering Sector

2.6. Underwater Imaging Sector

2.7. Textile Industries

Chapter 3

Role of Image Processing in the Agriculture Sector

3.1. Techniques Used in Plant Disease Identification

3.1.1. Pomegranate Plant Disease

3.1.2. Citrus Plant Disease

3.1.3. Tomato Plant Disease

3.2. Precision Farming

3.2.1. Technological Tools Used in Precision Farming

3.3. Crop and Land Assessment Using Remote Sensing

3.4. Plant Species Identification

3.5. Fruit Sorting and Classification

3.5.1. Methods Used for Fruit Classification

3.5.1.1. Color Image Processing

3.5.1.2. Image Segmentation

3.5.1.3. Regional Descriptors

3.5.1.4. Boundary Descriptors

3.5.2. Role of Features and Classifiers in Fruit Classification

3.5.2.1. Pattern Classification and Nearest Neighbor Classifier

3.5.2.2. Neural Network Classifier

3.6. Tea Quality Assessment

3.7. Sugar Cane Leaf Area Measurement

3.8. Paddy Crop Growth Analysis

Chaptaer 4

An Overview of Fundamental Digital Image Processing Procedures

4.1. Acquisition

4.2. Enhancement

4.3. Segmentation

4.4. Morphological Operations

4.4.1. Image Representation and Description

4.4.2. Object Recognition

Chapter 5

Image Acquisition Methods Appropriate for Various Agricultural Situations

5.1. Mono-RGB Vision Systems

5.2. Stereo Vision System

5.3. Multispectral and Hyperspectral Camera.

5.4. ToF Camera

5.5. LIDAR

5.6. Thermography and Fluorescence Imaging

5.7. Tomography Imaging

Chapter 6

Image Enhancement Tools for Images Acquired in Different Agro Conditions

6.1. Point Processing Methods

6.1.1. Gray Level Transformation

6.1.2. Histogram Processing

6.1.3. Fuzzy-Based Enhancement Using Fuzzy If-Then Rules

6.2. Neighborhood Processing Methods

6.2.1. Image Smoothing

6.2.2. Image Sharpening Filters

Chapter 7

Image Segmentation Methods Concerned with Plant and Agriculture Images

7.1. Edge-Based Segmentation Methods

7.1.1. Steps in Edge Detection

7.1.1.1. Filtering

7.1.1.2. Enhancement

7.1.1.3. Detection

7.1.2. First Order Derivative Based Methods

7.1.2.1. Roberts Edge Method

7.1.2.2. Sobel Edge Method

7.1.2.3. Prewitt Edge Method

7.1.3. Second Order Derivative Based Methods

7.1.3.1. LoG Based Edge Method

7.1.3.2. Zero Crossing Edge Method

7.1.3.3. Canny Edge Detection Method

7.2. Region-Based Segmentation Methods

7.2.1. Region Growing Method

7.2.2. Split and Merge Method

7.3. Thresholding-Based Segmentation Methods

7.4. Clustering Based Segmentation

7.4.1. Partitional Clustering Algorithms

7.4.2. Hierarchical Clustering Algorithms

7.4.2.1. K-Means Algorithm

7.4.2.2. Fuzzy C-Means Algorithm

7.5. Color Image Segmentation

7.6. PDE-Based Image Segmentation Methods

7.6.1. Active Contour Model

7.6.2. Geodesic Active Contour Model

7.7. Hybrid Segmentation Method

7.7.1. Edge Detection Using Vector Based Color Gradient

7.7.2. Region Growing Method

7.8. Optimization-Based Edge Detection

7.8.1. Improved Edge Detection Method Using Non-Linear Constrained Optimization

7.8.1.1. Penalty Method

7.8.2. Lagrange Multiplier Method.

7.8.3. Unconstrained Non-Linear Optimization Technique Based Enhanced Edge Detection Method

7.8.3.1. Newton-Raphson Based Segmentation Method

7.8.3.2. Vector Based Color Gradient Calculation

7.8.3.3. Finding Edge Points Using Newton-Raphson Method

7.9. Soft Computing Edge Detection Techniques

7.9.1. Fuzzy Logic and Genetic Algorithm-Based Edge Detection

7.10. Metaheuristic Algorithms in Edge Detection

7.10.1. Genetic Algorithms (GA)

7.10.2. Ant Colony Optimization (ACO)

7.10.3. Particle Swarm Optimization (PSO)

7.10.4. Flower Pollination Algorithm

Chapter 8

Feature Extraction Techniques Applicable for Agricultural Images

8.1. Color Value Extraction

8.2. Size Value Extraction

8.3. FAST Algorithm

8.4. Histogram of Gradients

8.5. Gray-Level Co-Occurrence Matrix (GLCM)

Chapter 9

Image Classification or Pattern Recognition to Solve Agricultural Problems

9.1. Support Vector Machine

9.2. Principal Component Analysis

Chapter 10

Quality Assessment Metrics of Reference and Non-Reference Agriculturally Important Images

10.1. Subjective Evaluation Method

10.2. Objective Evaluation Method

10.2.1. Analytical

10.2.2. Empirical

10.2.2.1. Discrepancy Measures

Receiver Operating Characteristics (ROC) Curve

Area under ROC Curve (AUC)

Precision-Recall (PR) Curve

F-Measure

Accuracy

Figure of Merit

Rand Index

Variation of Information (VI)

Dice-Coefficient

Jaccard-Coefficient

10.2.2.2. Goodness Measures

Cohens' Kappa

Entropy

Shape Measure

Intra Region Uniformity

10.2.3. Other

Peak Signal to Noise Ratio (PSNR)

Structural Similarity Index Measure (SSIM)

Feature Similarity Index Measure (FSIM)

Chapter 11

Case Study on Successful Digital Image Processing Application on Banana

11.1. Acquisition.

11.2. Pre-Processing

11.3. Segmentation

11.4. Feature Extraction

11.5. Classification

References

Index

About the Authors

Blank Page.

Notes:

Includes bibliographical references and index.

Description based on print version record.

Other Format:

Print version: Deenan, Suryaprabha Principles of Digital Image Processing for Agricultural Applications

ISBN:

9798886974805