Research Article
Comparative study of performing features applied in CNN architectures
@INPROCEEDINGS{10.4108/eai.24-4-2019.2284238, author={SARA LAROUI and HICHAM OMARA and Mohamed LAZAAR and Oussama MAHBOUB}, title={Comparative study of performing features applied in CNN architectures }, proceedings={Proceedings of the Third International Conference on Computing and Wireless Communication Systems, ICCWCS 2019, April 24-25, 2019, Faculty of Sciences, Ibn Tofa\~{n}l University -K\^{e}nitra- Morocco}, publisher={EAI}, proceedings_a={ICCWCS}, year={2019}, month={5}, keywords={deep networks classification convolutional neural network brain tumor medical imaging}, doi={10.4108/eai.24-4-2019.2284238} }- SARA LAROUI
HICHAM OMARA
Mohamed LAZAAR
Oussama MAHBOUB
Year: 2019
Comparative study of performing features applied in CNN architectures
ICCWCS
EAI
DOI: 10.4108/eai.24-4-2019.2284238
Abstract
Convolutional neural network (CNN), a class of artificial neural networks that has become dominant in various computer vision tasks, is attracting interest across a variety of domains, including Medical image analysis. CNN is designed to automatically and adaptively learn spatial hierarchies of features through back-propagation by using multiple building blocks, such as convolution layers, pooling layers, and fully connected layers. This paper presents an approach based on CNN for the classification of brain tumors, based on several characteristics that will be extracted automatically and some performing features that will be used in our CNN, This proposed approach provides efficient results at the level of automatic classification than the other usual methods.
