Reduction dimensionality of hyperspectral imagery using genetic algorithm and mutual information and normalized mutual information as a fitness function

Abstract

Hyperspectral images (HSI) present a wealth of information. It is distinguished by its high dimensionality. It served humanity in many fields. The quantity of HSI information represents a double-edged sword. As a consequence, their dimensionality must be reduced. Nowadays, several methods are proposed to overcome their duress. The most useful and essential solution is selection approaches of hyperspectral bands to analyze it quickly. Our work suggests a novel method to achieve this selection: we introduce a Genetic Algorithm (GA) based on mutual information (MI) and Normalized Mutual Information (NMI) as fitness functions. It selects the relevant bands from noisiest and redundant ones that don’t contain any additional information. .The proposed method is applied to three different HSI: INDIAN PINE, PAVIA, and SALINAS. The introduced algorithm provides a remarkable efficiency on the accuracy of the classification, in front of other statistical methods: the Bhattacharyya coefficient as well as the inter-bands correlation (Pearson correlation). We conclude that the measure of information (MI, NMI) provides more efficiency as a fitness function for GA selection applied to HSI; it must be more investigated.

Self scale estimation of the tracking window merged with adaptive particle filter tracker

“…On filtering stage PF is based on weight values, we grouped the three RGB distances in one normalized vector see ( 14) and (15), that represent weight's vector for particular state.…”

“…In this work, we adopted tracker algorithm based on a probabilistic approach, as they are the frequently used ones such as genetic algorithm (GA), cuckoo search (CS) algorithm, particle swarm optimization (PSO), and particle filter (PF). In this context, Maria et al [15] introduce GA in hyperspectral images analysis, where they introduce a GA based on mutual information and normalized mutual information as fitness functions based on mutual information to achieve this bands selection. While Gao et al [16] recommend CS algorithm to solve tracking problem, the algorithm has two parameters the number of nests and the probability discovering, it initializes the nest then it replaces them by Levy Flight random model while calculating the fitness of each nest.…”