Fast Image Super-Resolution Using Particle Swarm Optimization-Based Convolutional Neural Networks
Image super-resolution based on convolutional neural networks (CNN) is a hot topic in image processing. However, image super-resolution faces significant challenges in practical applications. Improving its performance on lightweight architectures is important for real-time super-resolution. In this...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/4/1923 |
| _version_ | 1797618292917010432 |
|---|---|
| author | Chaowei Zhou Aimin Xiong |
| author_facet | Chaowei Zhou Aimin Xiong |
| author_sort | Chaowei Zhou |
| collection | DOAJ |
| description | Image super-resolution based on convolutional neural networks (CNN) is a hot topic in image processing. However, image super-resolution faces significant challenges in practical applications. Improving its performance on lightweight architectures is important for real-time super-resolution. In this paper, a joint algorithm consisting of modified particle swarm optimization (SMCPSO) and fast super-resolution convolutional neural networks (FSRCNN) is proposed. In addition, a mutation mechanism for particle swarm optimization (PSO) was obtained. Specifically, the SMCPSO algorithm was introduced to optimize the weights and bias of the CNNs, and the aggregation degree of the particles was adjusted adaptively by a mutation mechanism to ensure the global searching ability of the particles and the diversity of the population. The results showed that SMCPSO-FSRCNN achieved the most significant improvement, being about 4.84% better than the FSRCNN model, using the BSD100 data set at a scale factor of 2. In addition, a chest X-ray super-resolution images classification test experiment was conducted, and the experimental results demonstrated that the reconstruction ability of this model could improve the classification accuracy by 13.46%; in particular, the precision and recall rate of COVID-19 were improved by 45.3% and 6.92%, respectively. |
| first_indexed | 2024-03-11T08:11:02Z |
| format | Article |
| id | doaj.art-9f8a70cdcc214ded81a2d2cb8cc3306f |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T08:11:02Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9f8a70cdcc214ded81a2d2cb8cc3306f2023-11-16T23:07:58ZengMDPI AGSensors1424-82202023-02-01234192310.3390/s23041923Fast Image Super-Resolution Using Particle Swarm Optimization-Based Convolutional Neural NetworksChaowei Zhou0Aimin Xiong1School of Physics and Telecommunication Engineering, South China Normal University, Guangzhou 510006, ChinaSchool of Physics and Telecommunication Engineering, South China Normal University, Guangzhou 510006, ChinaImage super-resolution based on convolutional neural networks (CNN) is a hot topic in image processing. However, image super-resolution faces significant challenges in practical applications. Improving its performance on lightweight architectures is important for real-time super-resolution. In this paper, a joint algorithm consisting of modified particle swarm optimization (SMCPSO) and fast super-resolution convolutional neural networks (FSRCNN) is proposed. In addition, a mutation mechanism for particle swarm optimization (PSO) was obtained. Specifically, the SMCPSO algorithm was introduced to optimize the weights and bias of the CNNs, and the aggregation degree of the particles was adjusted adaptively by a mutation mechanism to ensure the global searching ability of the particles and the diversity of the population. The results showed that SMCPSO-FSRCNN achieved the most significant improvement, being about 4.84% better than the FSRCNN model, using the BSD100 data set at a scale factor of 2. In addition, a chest X-ray super-resolution images classification test experiment was conducted, and the experimental results demonstrated that the reconstruction ability of this model could improve the classification accuracy by 13.46%; in particular, the precision and recall rate of COVID-19 were improved by 45.3% and 6.92%, respectively.https://www.mdpi.com/1424-8220/23/4/1923convolution neural networkparticle swarm optimizationpneumonia diagnosissuper-resolution |
| spellingShingle | Chaowei Zhou Aimin Xiong Fast Image Super-Resolution Using Particle Swarm Optimization-Based Convolutional Neural Networks Sensors convolution neural network particle swarm optimization pneumonia diagnosis super-resolution |
| title | Fast Image Super-Resolution Using Particle Swarm Optimization-Based Convolutional Neural Networks |
| title_full | Fast Image Super-Resolution Using Particle Swarm Optimization-Based Convolutional Neural Networks |
| title_fullStr | Fast Image Super-Resolution Using Particle Swarm Optimization-Based Convolutional Neural Networks |
| title_full_unstemmed | Fast Image Super-Resolution Using Particle Swarm Optimization-Based Convolutional Neural Networks |
| title_short | Fast Image Super-Resolution Using Particle Swarm Optimization-Based Convolutional Neural Networks |
| title_sort | fast image super resolution using particle swarm optimization based convolutional neural networks |
| topic | convolution neural network particle swarm optimization pneumonia diagnosis super-resolution |
| url | https://www.mdpi.com/1424-8220/23/4/1923 |
| work_keys_str_mv | AT chaoweizhou fastimagesuperresolutionusingparticleswarmoptimizationbasedconvolutionalneuralnetworks AT aiminxiong fastimagesuperresolutionusingparticleswarmoptimizationbasedconvolutionalneuralnetworks |