Quaternion softmax classifier. Issue 25 (1st December 2014)

• Record Type: Journal Article
• Authors: Zeng, Rui; Wu, Jiasong; Shao, Zhuhong; Senhadji, Lotfi; Shu, Huazhong
• Is Part Of: Electronics letters. Volume 50:Issue 25(2014)
• Page Start: 1929
• Page End: 1931
• Publication Date: 2014-12-01
• Subjects: image classification -- feature extraction -- image colour analysis -- image representation -- principal component analysis; colour image pixel feature -- QPCA feature -- quaternion principal component analysis feature -- colour image representation -- quaternion features -- feature vectors -- R channels -- G channels -- B channels -- RGB colour images -- red‐bluegreen colour images -- feature extraction -- quaternion softmax classifier; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2014.2526
• Languages: English
• ISSNs: 0013-5194

Abstract

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.