I. Machine Learning 1. Introduction 2. Pattern Recognition 3. Machine Learning Algorithms for Pattern Recognition II. Ground Truth Data for Remote Sensing Image Classification 1. Criteria for Ground Truth Data 2. Training Data 3.

Testing Data III. Fuzzy Classifiers 1. Soft Classifiers 2. Traditional Classifiers vs Soft Classifiers 3. Linear and non-linear classifiers 4. Fuzzy c-Means (FCM) Classifier 5. Possibilistic c-Means (PCM) Classifier 6. Noise Clustering (NC) Classifier 7.

Why Noise Clustering? 8. Limitations of Possibilistic c-Means (PCM) 9. Improved Possibilistic c-Means (IPCM) 10. Advantages of IPCM over PCM 11. Modified Possibilistic c-Means (MPCM) IV. Learning Based Classifiers 1. Artificial Neural Network (ANN) 2. Convolutional Neural Network (CNN) 3.

Recurrent Neural Network (RNN) 4. Hybrid Learning Network (HLN) 5. Deep Learning Concepts 6. In-house Tool for Study of Learning Algorithms V. Hybrid Fuzzy Classifiers 1. Entropy Based Hybrid Soft Classifiers 2. Fuzzy c-Means with Entropy (FCME) 3. Noise Clustering with Entropy (NCWE) Classifier 4.

Similarity/Dissimilarity Measures in Fuzzy Classifiers 5. Kernels Concept in Fuzzy Classifiers 6. Theory behind Markov Random Field (MRF) 7. Types of MRF methods 8. Contextual Information using MRF 9. Convolution based Local Information in Fuzzy Classifiers VI. Fuzzy Classifiers for Temporal Data Processing 1. Introduction 2.

Indices Approaches 3. Fuzzy Based Algorithms for Single Class Extraction 4. Concept for Mono/Bi-sensor Remote Sensing Data Processing VII. Assessment of Accuracy for Soft Classification 1. Generation of Testing Data 2. Methods for Assessment of Accuracy 3. Fuzzy Error Matrix (FERM) and Other Operators 4. Entropy Method 5.

Mean and Variance Method for Edge Preservation 6. Correlation Coefficient 7. Root Mean Square Error 8. Receiver Operating Characteristics (ROC) Appendix A1 SMIC: Sub_Pixel Multi-spectral Image Classifier Tool Appendix A2 Case Study 1 : Study of similarity and dissimilarity measures with IPCM and MPCM classifiers Case Study 2 : Bi-sensor temporal data for paddy crop mapping Case Study 3 : Handling non-linearity between classes using kernels in fuzzy classifiers Case Study 4 : Handling noise through MRF based noise clustering classifier Case Study 5 :Local convolution based contextual information in Possibilistic c-Means Classification Case Study 6 : Optimization of local convolution based MPCM classifier and identification of paddy and burnt paddy fields Case Study 7 : Semi-supervised training approach for PCM classifier Case Study 8 : Study of hybridizing stochastic and deterministic measures with fuzzy based classifier Case Study 9 : Kernal based PCM Classification approach Case Study 10 : Effect of red edge bands in fuzzy classification: a case study of sunflower crop Case Study 11 : Discriminating sugar ratoon / plant crop using multi- sensor temporal data.