M
Maissa Hamouda
Researcher at University of Sousse
Publications - 10
Citations - 60
Maissa Hamouda is an academic researcher from University of Sousse. The author has contributed to research in topics: Convolutional neural network & Hyperspectral imaging. The author has an hindex of 4, co-authored 8 publications receiving 32 citations.
Papers
More filters
Journal ArticleDOI
Smart feature extraction and classification of hyperspectral images based on convolutional neural networks
TL;DR: A smart feature extraction (SFE) and classification by convolutional neural network (2D-CNN) method made up of two parts that consists in reducing spectral information by a probabilistic method based on the Softmax function.
Proceedings ArticleDOI
Modified Convolutional Neural Network based on Adaptive Patch Extraction for Hyperspectral Image Classification
TL;DR: A deep classification method based on the CNN networks and a clustering algorithm that provides competitive results to the other approaches in hyperspectral imaging.
Journal ArticleDOI
Hyperspectral imaging classification based on convolutional neural networks by adaptive sizes of windows and filters
TL;DR: This framework is able to improve the accuracy of the hyperspectral image classification by adaptive selection of the number of filters, using an adaptive size of the windows and an adaptivesize of the filters.
Journal ArticleDOI
Framework for Automatic Selection of Kernels based on Convolutional Neural Networks and CkMeans Clustering Algorithm
TL;DR: In this article, CNNs can learn deep feature representation for hyperspectral imagery interpretation and attain excellent accuracy of classification if we have many training samples, which can be used to train many CNNs.
Book ChapterDOI
Dual Convolutional Neural Networks for Hyperspectral Satellite Images Classification (DCNN-HSI)
Maissa Hamouda,Med Salim Bouhlel +1 more
TL;DR: A new approach to the reduction and classification of HSI is proposed consisting of a dual Convolutional Neural Networks (DCNN), which aims to improve precision and computing time.