Quaternion softmax classifier

Abstract : For the feature extraction of red-blue-green (RGB) colour images, researchers usually deal with R, G and B channels separately to obtain three feature vectors, and then combine them together to obtain a long real feature vector. This approach does not exploit the relationships between the three channels of the colour images. Recently, attention has been paid to quaternion features, which take the relationships between channels into consideration and seem to be more suitable for representing colour images. However, there are only a few quaternion classifiers for dealing with quaternion features. To meet this requirement, a new quaternion classifier, namely, the quaternion softmax classifier is proposed, which is an extended version of the conventional softmax classifier generally defined in the complex (or real) domain. The proposed quaternion softmax classifier is applied to two of the most common quaternion features, that is, the quaternion principal components analysis feature and the colour image pixel feature. The experimental results show that the proposed method performs better than the quaternion back propagation neural network in terms of accuracy and convergence rate.
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

Contributeur : Lotfi Senhadji <>
Soumis le : jeudi 8 janvier 2015 - 15:04:00
Dernière modification le : mercredi 21 février 2018 - 01:58:00
Document(s) archivé(s) le : jeudi 9 avril 2015 - 10:40:24


Quaternion softmax classifier....
Fichiers produits par l'(les) auteur(s)




Rui Zeng, Jiasong Wu, Zhuhong Shao, Lotfi Senhadji, Huazhong Shu. Quaternion softmax classifier. Electronics Letters, IET, 2014, 50 (25), pp.1929-1930. 〈10.1049/el.2014.2526〉. 〈inserm-01101207〉



Consultations de la notice


Téléchargements de fichiers