The optimally designed autoencoder network for compressed sensing
Abstract Compressed sensing (CS) is a signal processing framework, which reconstructs a signal from a small set of random measurements obtained by measurement matrices. Due to the strong randomness of measurement matrices, the reconstruction performance is unstable. Additionally, current reconstruct...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2019-04-01
|
| Series: | EURASIP Journal on Image and Video Processing |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13640-019-0460-5 |
| _version_ | 1811286683239317504 |
|---|---|
| author | Zufan Zhang Yunfeng Wu Chenquan Gan Qingyi Zhu |
| author_facet | Zufan Zhang Yunfeng Wu Chenquan Gan Qingyi Zhu |
| author_sort | Zufan Zhang |
| collection | DOAJ |
| description | Abstract Compressed sensing (CS) is a signal processing framework, which reconstructs a signal from a small set of random measurements obtained by measurement matrices. Due to the strong randomness of measurement matrices, the reconstruction performance is unstable. Additionally, current reconstruction algorithms are relatively independent of the compressed sampling process and have high time complexity. To this end, a deep learning based stacked sparse denoising autoencoder compressed sensing (SSDAE_CS) model, which mainly consists of an encoder sub-network and a decoder sub-network, is proposed and analyzed in this paper. Instead of traditional linear measurements, a multiple nonlinear measurements encoder sub-network is trained to obtain measurements. Meanwhile, a trained decoder sub-network solves the CS recovery problem by learning the structure features within the training data. Specifically, the two sub-networks are integrated into SSDAE_CS model through end-to-end training for strengthening the connection between the two processes, and their parameters are jointly trained to improve the overall performance of CS. Finally, experimental results demonstrate that the proposed method significantly outperforms state-of-the-art methods in terms of reconstruction performance, time cost, and denoising ability. Most importantly, the proposed model shows excellent reconstruction performance in the case of a few measurements. |
| first_indexed | 2024-04-13T03:04:16Z |
| format | Article |
| id | doaj.art-8a403d77e24e4e6189172e0d05faf8f3 |
| institution | Directory Open Access Journal |
| issn | 1687-5281 |
| language | English |
| last_indexed | 2024-04-13T03:04:16Z |
| publishDate | 2019-04-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Image and Video Processing |
| spelling | doaj.art-8a403d77e24e4e6189172e0d05faf8f32022-12-22T03:05:19ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-52812019-04-012019111210.1186/s13640-019-0460-5The optimally designed autoencoder network for compressed sensingZufan Zhang0Yunfeng Wu1Chenquan Gan2Qingyi Zhu3School of Communication and Information Engineering, Chongqing University of Posts and TelecommunicationsSchool of Communication and Information Engineering, Chongqing University of Posts and TelecommunicationsSchool of Communication and Information Engineering, Chongqing University of Posts and TelecommunicationsSchool of cyber security and information law, Chongqing University of Posts and TelecommunicationsAbstract Compressed sensing (CS) is a signal processing framework, which reconstructs a signal from a small set of random measurements obtained by measurement matrices. Due to the strong randomness of measurement matrices, the reconstruction performance is unstable. Additionally, current reconstruction algorithms are relatively independent of the compressed sampling process and have high time complexity. To this end, a deep learning based stacked sparse denoising autoencoder compressed sensing (SSDAE_CS) model, which mainly consists of an encoder sub-network and a decoder sub-network, is proposed and analyzed in this paper. Instead of traditional linear measurements, a multiple nonlinear measurements encoder sub-network is trained to obtain measurements. Meanwhile, a trained decoder sub-network solves the CS recovery problem by learning the structure features within the training data. Specifically, the two sub-networks are integrated into SSDAE_CS model through end-to-end training for strengthening the connection between the two processes, and their parameters are jointly trained to improve the overall performance of CS. Finally, experimental results demonstrate that the proposed method significantly outperforms state-of-the-art methods in terms of reconstruction performance, time cost, and denoising ability. Most importantly, the proposed model shows excellent reconstruction performance in the case of a few measurements.http://link.springer.com/article/10.1186/s13640-019-0460-5Compressed sensingStacked sparse denoising autoencoderDeep learningMultiple nonlinear measurementSignal reconstruction |
| spellingShingle | Zufan Zhang Yunfeng Wu Chenquan Gan Qingyi Zhu The optimally designed autoencoder network for compressed sensing EURASIP Journal on Image and Video Processing Compressed sensing Stacked sparse denoising autoencoder Deep learning Multiple nonlinear measurement Signal reconstruction |
| title | The optimally designed autoencoder network for compressed sensing |
| title_full | The optimally designed autoencoder network for compressed sensing |
| title_fullStr | The optimally designed autoencoder network for compressed sensing |
| title_full_unstemmed | The optimally designed autoencoder network for compressed sensing |
| title_short | The optimally designed autoencoder network for compressed sensing |
| title_sort | optimally designed autoencoder network for compressed sensing |
| topic | Compressed sensing Stacked sparse denoising autoencoder Deep learning Multiple nonlinear measurement Signal reconstruction |
| url | http://link.springer.com/article/10.1186/s13640-019-0460-5 |
| work_keys_str_mv | AT zufanzhang theoptimallydesignedautoencodernetworkforcompressedsensing AT yunfengwu theoptimallydesignedautoencodernetworkforcompressedsensing AT chenquangan theoptimallydesignedautoencodernetworkforcompressedsensing AT qingyizhu theoptimallydesignedautoencodernetworkforcompressedsensing AT zufanzhang optimallydesignedautoencodernetworkforcompressedsensing AT yunfengwu optimallydesignedautoencodernetworkforcompressedsensing AT chenquangan optimallydesignedautoencodernetworkforcompressedsensing AT qingyizhu optimallydesignedautoencodernetworkforcompressedsensing |