The high dimensionality of hyperspectral images often imposes a heavy computational burden for image processing. Therefore, dimensionality reduction is often an essential step in order to remove the irrelevant, noisy and redundant bands. And consequently, increase the classification accuracy. However, identification of useful bands from hundreds or even thousands of related bands is a nontrivial task. This paper aims at identifying a small set of bands, for improving computational speed and prediction accuracy. Hence, we have proposed a hybrid algorithm through band selection for dimensionality reduction of hyperspectral images. The proposed approach combines mutual information gain (MIG), Minimum Redundancy Maximum Relevance (mRMR) and Error probability of Fano with Support Vector Machine Bands Elimination (SVM-PF). The proposed approach is compared to an effective reproduced filters approach based on mutual information. Experimental results on HSI AVIRIS 92AV3C have shown that the proposed approach outperforms the reproduced filters.
The Hyperspectral image (HSI) contains several hundred bands of the same region called the Ground Truth (GT). The bands are taken in juxtaposed frequencies, but some of them are noisily measured or contain no information. For the classification, the selection of bands, affects significantly the results of classification, in fact, using a subset of relevant bands, these results can be better than those obtained using all bands, from which the need to reduce the dimensionality of the HSI. In this paper, a categorization of dimensionality reduction methods, according to the generation process, is presented. Furthermore, we reproduce an algorithm based on mutual information (MI) to reduce dimensionality by features selection and we introduce an algorithm using mutual information and homogeneity. The two schemas are a filter strategy. Finally, to validate this, we consider the case study AVIRIS HSI 92AV3C.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.