Linked e-resources
Details
Table of Contents
1 Artificial Bee Colony Algorithm for Classification of Semi-urban LU/LC Features Using High-Resolution Satellite Data; Abstract; 1 Introduction; 2 Maximum Likelihood Classifiers; 3 Artificial Bee Colony; 3.1 Advantages of ABC; 3.2 Factors Affecting the Performance of the Artificial Bee Colony; 4 Extraction of Textural Features; 5 Materials; 5.1 Data Products Used; 5.2 Study Area; 6 Results and Discussion; 6.1 Performance of ABC at Class Hierarchy Level-I and Level-II; 6.2 Texture: Selection of Optimal Window Size and Interpixel Distance
6.3 Effectiveness of Texture Feature Combinations6.4 Investigation of Texture at Class Hierarchy Level-I and Level-II; 7 Conclusion; Acknowledgements; References; 2 Saliency-Based Image Compression Using Walsh-Hadamard Transform (WHT); Abstract; 1 Introduction; 2 Backgrounds; 2.1 Saliency Detection; 2.2 Visual Saliency-Based Image Compression; 2.3 Walsh-Hadamard Transform (WHT); 3 Proposed Method; 3.1 WHT-Based Saliency Map Computation; 3.2 Saliency-Based Image Compression; 3.2.1 Preprocessing Stage; 3.2.2 Transform Domain; 3.2.3 Quantitation; 3.2.4 Encoding; 4 Experimental Results
4.1 Results of WHT-Based Saliency Detection4.2 Results of Visual Saliency-Based Image Compression; 4.3 Performance Analysis; 5 Conclusion; References; 3 Object Trajectory Prediction with Scarce Environment Information; Abstract; 1 Introduction; 2 The HOLOTECH Model and Prototype; 3 Train, Testing, and Results; 3.1 Image Acquisition and Feature Extraction; 3.2 Classifier Training and Precision Evaluation; 4 Data Flexibility; 5 Conclusions and Future Work; References; 4 A Twofold Subspace Learning-Based Feature Fusion Strategy for Classification of EMG and EMG Spectrogram Images; Abstract
1 Introduction2 Method: Multi-view Template-Based Analysis; 2.1 Database Description; 2.2 CCA Learning; 2.3 Variability Measurement (VM); 2.4 Feature Extraction and Dimension Reduction; 2.5 Feature Fusion and Classification Strategy; 2.6 Classification Performance; 3 Method: Multi-view Spectrogram Image Analysis; 3.1 Spectrogram Generation; 3.2 Classification Performance; 3.3 Comparison with State-of-the-Art Methods; 3.4 Limitations; 4 Conclusion; Acknowledgements; Appendix; Performance Evaluation; Fusion; References
5 Automatic Detection of Brain Strokes in CT Images Using Soft Computing TechniquesAbstract; 1 Introduction; 1.1 Symptoms of Stroke; 1.2 Risk Factors of Stroke; 1.3 Imaging Modalities; 1.4 Proposed Scheme; 2 Related Work; 3 Methodology; 3.1 Information Acquisition; 3.2 Image Preprocessing; 3.3 Pre-segmentation Method; 3.4 Feature Extraction; 3.4.1 Discrete Wavelet Transform; 3.4.2 Wavelet Packet Transform (WPT); 3.4.3 Gray-Level Co-occurrence Matrix (GLCM); 3.5 Feature Selection Using LDA; 4 Soft Computing; 4.1 Neural Network; 4.2 Artificial Neural Network Classifier
6.3 Effectiveness of Texture Feature Combinations6.4 Investigation of Texture at Class Hierarchy Level-I and Level-II; 7 Conclusion; Acknowledgements; References; 2 Saliency-Based Image Compression Using Walsh-Hadamard Transform (WHT); Abstract; 1 Introduction; 2 Backgrounds; 2.1 Saliency Detection; 2.2 Visual Saliency-Based Image Compression; 2.3 Walsh-Hadamard Transform (WHT); 3 Proposed Method; 3.1 WHT-Based Saliency Map Computation; 3.2 Saliency-Based Image Compression; 3.2.1 Preprocessing Stage; 3.2.2 Transform Domain; 3.2.3 Quantitation; 3.2.4 Encoding; 4 Experimental Results
4.1 Results of WHT-Based Saliency Detection4.2 Results of Visual Saliency-Based Image Compression; 4.3 Performance Analysis; 5 Conclusion; References; 3 Object Trajectory Prediction with Scarce Environment Information; Abstract; 1 Introduction; 2 The HOLOTECH Model and Prototype; 3 Train, Testing, and Results; 3.1 Image Acquisition and Feature Extraction; 3.2 Classifier Training and Precision Evaluation; 4 Data Flexibility; 5 Conclusions and Future Work; References; 4 A Twofold Subspace Learning-Based Feature Fusion Strategy for Classification of EMG and EMG Spectrogram Images; Abstract
1 Introduction2 Method: Multi-view Template-Based Analysis; 2.1 Database Description; 2.2 CCA Learning; 2.3 Variability Measurement (VM); 2.4 Feature Extraction and Dimension Reduction; 2.5 Feature Fusion and Classification Strategy; 2.6 Classification Performance; 3 Method: Multi-view Spectrogram Image Analysis; 3.1 Spectrogram Generation; 3.2 Classification Performance; 3.3 Comparison with State-of-the-Art Methods; 3.4 Limitations; 4 Conclusion; Acknowledgements; Appendix; Performance Evaluation; Fusion; References
5 Automatic Detection of Brain Strokes in CT Images Using Soft Computing TechniquesAbstract; 1 Introduction; 1.1 Symptoms of Stroke; 1.2 Risk Factors of Stroke; 1.3 Imaging Modalities; 1.4 Proposed Scheme; 2 Related Work; 3 Methodology; 3.1 Information Acquisition; 3.2 Image Preprocessing; 3.3 Pre-segmentation Method; 3.4 Feature Extraction; 3.4.1 Discrete Wavelet Transform; 3.4.2 Wavelet Packet Transform (WPT); 3.4.3 Gray-Level Co-occurrence Matrix (GLCM); 3.5 Feature Selection Using LDA; 4 Soft Computing; 4.1 Neural Network; 4.2 Artificial Neural Network Classifier