Super-Resolution Reconstruction Algorithm for Infrared Image with Double Regular Items Based on Sub-Pixel Convolution

Yu, Lei; Zhang, Xuewei; Chu, Yan

doi:10.3390/app10031109

Cited by 11 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the process of improving the authenticity of the digital image of cultural heritage, based on the digital image of cultural heritage after illumination compensation obtained in Section 3.3, the multilateral filtering technology is introduced into the process of extracting the luminance digital image, and the optimum neighborhood range of the pixel of the digital image of cultural heritage is calculated by tilting the filtering window of the multilateral filter [12,13]. In this range, a binary constraint function is introduced to smooth the edges of the digital image of cultural heritage, and the extracted luminance digital image is enhanced by the multiscale Retinex digital image.…”

Section: Multilateral Filtering Of Cultural Heritage Digital Imagesmentioning

confidence: 99%

Digital Protection of Cultural Heritage Based on Web Technology

Zhao

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the rapid development of digital technology, it has now been widely used for the digital protection of cultural heritage. The traditional cultural heritage digital protection method of information retrieval recall rate is low, and the processing time is long. Therefore, a new digital protection method of cultural heritage based on web technology is proposed. An improved four-layer architecture design pattern is adopted to plan a web-based digital protection platform for cultural heritage. The application service provider (ASP) combines SQL server and B/S architecture to develop a database platform and functional modules for direct dynamic management of the website model. Based on this, combined with web technology, the digital image of cultural heritage is reconstructed followed by computing the uncertainty probability of web visualization, completing the modeling metalanguage, and classification of network cultural heritage. The digital image enhancement of cultural heritage is based on HSV color space. In order to realize the digital protection of traditional cultural heritage, multifiltering technology is introduced into the process of brightness digital image extraction. It is evident from the experimental results that the proposed method has higher recall and lower error and can enhance the digital image of cultural heritage in a shorter time, which shows that the proposed method can effectively achieve digital protection of cultural heritage.

show abstract

Section: Multilateral Filtering Of Cultural Heritage Digital Imagesmentioning

confidence: 99%

Digital Protection of Cultural Heritage Based on Web Technology

Zhao

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Previous studies have shown that for the problem of image super-resolution reconstruction based on deep learning, an upsampling process based on sub-pixel convolution is effective in improving image quality (Zhao et al, 2019(Zhao et al, , 2020Yu et al, 2020). Therefore, in the root pixel segmentation task, the introduction of sub-pixel convolution can improve the problem of pixel loss after bilinear upsampling in the standard DeepLabv3+, thereby improving the segmentation accuracy of the network for small root loci and further enhancing the robustness of the model.…”

Section: Model Improvementmentioning

confidence: 99%

High-Throughput in situ Root Image Segmentation Based on the Improved DeepLabv3+ Method

et al. 2020

View full text Add to dashboard Cite

The Rhizotrons method is an important means of detecting dynamic growth and development phenotypes of plant roots. However, the segmentation of root images is a critical obstacle restricting further development of this method. At present, researchers mostly use direct manual drawings or software-assisted manual drawings to segment root systems for analysis. Root systems can be segmented from root images obtained by the Rhizotrons method, and then, root system lengths and diameters can be obtained with software. This type of image segmentation method is extremely inefficient and very prone to human error. Here, we investigate the effectiveness of an automated image segmentation method based on the DeepLabv3+ convolutional neural network (CNN) architecture to streamline such measurements. We have improved the upsampling portion of the DeepLabv3+ network and validated it using in situ images of cotton roots obtained with a micro root window root system monitoring system. Segmentation performance of the proposed method utilizing WinRHIZO Tron MF analysis was assessed using these images. After 80 epochs of training, the final verification set F1-score, recall, and precision were 0.9773, 0.9847, and 0.9702, respectively. The Spearman rank correlation between the manually obtained Rhizotrons manual segmentation root length and automated root length was 0.9667 (p < 10 −8), with r 2 = 0.9449. Based on the comparison of our segmentation results with those of traditional manual and U-net segmentation methods, this novel method can more accurately segment root systems in complex soil environments. Thus, using the improved DeepLabv3+ to segment root systems based on micro-root images is an effective method for accurately and quickly segmenting root systems in a homogeneous soil environment and has clear advantages over traditional manual segmentation.

show abstract

“…The clinical validation of the deep learning model will provide useful information and further research directions for other researchers. We evaluated the full width at half maximum (FWHM), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) [27,28]. In the following sections, we briefly describe the implementation of the simulation and experiment and discuss the results in detail.…”

Section: Introductionmentioning

confidence: 99%

A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image Quality

Kim,

Lee

2023

Applied Sciences

View full text Add to dashboard Cite

Ultrasound imaging is widely used as a noninvasive lesion detection method in diagnostic medicine. Improving the quality of these ultrasound images is very important for accurate diagnosis, and deep learning-based algorithms have gained significant attention. This study proposes a multiscale deep encoder–decoder with phase congruency (MSDEPC) algorithm based on deep learning to improve the quality of diagnostic ultrasound images. The MSDEPC algorithm included low-resolution (LR) images and edges as inputs and constructed a multiscale convolution and deconvolution network. Simulations were conducted using the Field 2 program, and data from real experimental research were obtained using five clinical datasets containing images of the carotid artery, liver hemangiomas, breast malignancy, thyroid carcinomas, and obstetric nuchal translucency. LR images, bicubic interpolation, and super-resolution convolutional neural networks (SRCNNs) were modeled as comparison groups. Through visual assessment, the image processed using the MSDEPC was the clearest, and the lesions were clearly distinguished. The structural similarity index metric (SSIM) value of the simulated ultrasound image using the MSDEPC algorithm improved by approximately 38.84% compared to LR. In addition, the peak signal-to-noise ratio (PSNR) and SSIM values of clinical ultrasound images using the MSDEPC algorithm improved by approximately 2.33 times and 88.58%, respectively, compared to LR. In conclusion, the MSDEPC algorithm is expected to significantly improve the spatial resolution of ultrasound images.

show abstract

Super-Resolution Reconstruction Algorithm for Infrared Image with Double Regular Items Based on Sub-Pixel Convolution

Cited by 11 publications

References 15 publications

Digital Protection of Cultural Heritage Based on Web Technology

Digital Protection of Cultural Heritage Based on Web Technology

High-Throughput in situ Root Image Segmentation Based on the Improved DeepLabv3+ Method

A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image Quality

Contact Info

Product

Resources

About