Reduced Biquaternion Stacked Denoising Convolutional AutoEncoder for RGB-D Image Classification

RGB-D image classification based on convolutional neural networks have been extensively explored recently. However, they suffer from problems of effective representation of RGB-D image, intra-class variances and inter-class similarities. To address these problems, this letter proposes a novel RGB-D...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE signal processing letters Ročník 28; s. 1205 - 1209
Hlavní autori: Huang, Xiang, Gai, Shan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Artificial neural networks
autoencoder
Classification
Convolution
Feature extraction
hypercomplex network
Image classification
Image color analysis
Matrix converters
Noise reduction
Reduced biquaternion
RGB-D
Tensors
Training
ISSN:1070-9908, 1558-2361
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:RGB-D image classification based on convolutional neural networks have been extensively explored recently. However, they suffer from problems of effective representation of RGB-D image, intra-class variances and inter-class similarities. To address these problems, this letter proposes a novel RGB-D image classification framework based on reduced biquaternion stacked denoising convolutional autoencoder (RQ-SDCAE). The proposed framework can encode and extract the depth feature effectively by using the reduced biquaternion. The stacked training method is utilized to train the proposed reduced biquaternion convolutional autoencoder. Extensive evaluations for RGB-D image classification demonstrate that RQ-SDCAE outperforms the state-of-the-art methods.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2021.3088049