Convolutional autoencoder-based color image classification using chroma subsampling in YCbCr space

Zuhe Li, Yangyu Fan, Fengqin Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

We propose a convolutional autoencoder neural network for image classification in YCbCr color space to reduce computational complexity. We first learned local image features from image patches in YCbCr space with a sparse autoencoder and then convolved them with large images to obtain global features. Chrominance components were subsampled before convolution as it is permitted to reduce bandwidth for chrominance components in YCbCr space. We then adopted an algorithm to resize the convolved features in chrominance components by shifting the elements after convolution. Global features were finally fed into a softmax classifier to test the classification accuracy. Experimental results reveal that the convolutional neural network in YCbCr space is able to obtain a reduction of at least 21.6% in time consumption compared to the RGB representation with a slight loss in accuracy.

Original languageEnglish
Title of host publicationProceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015
EditorsLipo Wang, Sen Lin, Zhiyong Tao, Bing Zeng, Xiaowei Hui, Liangshan Shao, Jie Liang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages351-355
Number of pages5
ISBN (Electronic)9781467390989
DOIs
StatePublished - 16 Feb 2016
Event8th International Congress on Image and Signal Processing, CISP 2015 - Shenyang, China
Duration: 14 Oct 201516 Oct 2015

Publication series

NameProceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015

Conference

Conference8th International Congress on Image and Signal Processing, CISP 2015
Country/TerritoryChina
CityShenyang
Period14/10/1516/10/15

Keywords

  • Computer vision
  • Convolutional neural network
  • Image classification
  • Sparse autoencoder
  • Unsupervised feature learning

Fingerprint

Dive into the research topics of 'Convolutional autoencoder-based color image classification using chroma subsampling in YCbCr space'. Together they form a unique fingerprint.

Cite this