image classification based on convolutional denoising sparse autoencoder
Clicks: 214
ID: 163702
2017
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This
article has not been analysed, so there is no overall score —
reader engagement is measured and shown alongside.
Reader Engagement
Emerging Content
30.0
/100
214 views
41 readers
AI Quality Assessment
Not analyzed
Readership in this journal
EmergingRanked #69 of 1,093 articles by views in journal of power sources
Most read
Least read
Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 1,093 in total.
Mint this article as an NFT
Not yet mintedCreate a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.
5
SUSD
one-off · no wallet required
Abstract
Image classification aims to group images into corresponding semantic categories. Due to the difficulties of interclass similarity and intraclass variability, it is a challenging issue in computer vision. In this paper, an unsupervised feature learning approach called convolutional denoising sparse autoencoder (CDSAE) is proposed based on the theory of visual attention mechanism and deep learning methods. Firstly, saliency detection method is utilized to get training samples for unsupervised feature learning. Next, these samples are sent to the denoising sparse autoencoder (DSAE), followed by convolutional layer and local contrast normalization layer. Generally, prior in a specific task is helpful for the task solution. Therefore, a new pooling strategy—spatial pyramid pooling (SPP) fused with center-bias prior—is introduced into our approach. Experimental results on the common two image datasets (STL-10 and CIFAR-10) demonstrate that our approach is effective in image classification. They also demonstrate that none of these three components: local contrast normalization, SPP fused with center-prior, and l2 vector normalization can be excluded from our proposed approach. They jointly improve image representation and classification performance.
| Reference Key |
chen2017mathematicalimage
Use this key to autocite in the manuscript while using
SciMatic Manuscript Manager or Thesis Manager
|
|---|---|
| Authors | ;Shuangshuang Chen;Huiyi Liu;Xiaoqin Zeng;Subin Qian;Jianjiang Yu;Wei Guo |
| Journal | journal of power sources |
| Year | 2017 |
| DOI |
10.1155/2017/5218247
|
| URL | |
| Keywords |
Citations
No citations found. To add a citation, contact the admin at info@scimatic.org
Comments
No comments yet. Be the first to comment on this article.