Hong Tat Ewe

TL;DR: This paper presents a combined Entropy Decomposition and Support Vector Machine (EDSVM) technique for Synthetic Aperture Radar (SAR) image classification with the application on rice monitoring and offers the ability to analyze single-polarized, multi-temporal data with the advantage of the unique features from the combined method.

TL;DR: Theoretical analysis of the simulation results shows in particular that second-order effects are important for cross-polarized backscatter data and that coherent effects need to be considered at lower frequencies.

TL;DR: An iris recognition system that implements the combination of proposed black hole search method and integro-differential operators for iris localization, one-dimensional fractal analysis for feature extraction and dissimilarity operator for matching and achieves 100% accuracy of pupil detection.

TL;DR: A novel approach to solve the low-frequency high-order polynomial and high- frequency sinusoidal phase errors by using the power-to-spreading noise ratio (PSR) and image entropy (IE) to search for optimum solution.

TL;DR: The hybrid EDSVM is developed to provide an alternative solution to improve the classification accuracy and is proved to be robust and to yield a superior result compared with neural network (NN), SVM and EDNN classifiers.