Super Resolution Image Reconstruction Based on Image Similarity and Feature Combination

Zhan, Yuli; Chi, Jing; Ye, Yanan; Zhang, Caiming; Huo, Wenyuan

doi:10.3724/sp.j.1089.2019.17395

“…This method uses the non-local similarity of the depth map and restricts the non-local mean to obtain the final depth map reconstruction. On this basis, an end-to-end depth map super-resolution reconstruction network is established to improve the effect of the reconstructed image [11] .…”

Section: Introductionmentioning

confidence: 99%

An improved non-local means algorithm for CT image denoising

Kong,

Gao,

Du

et al. 2024

Multimedia Systems

2

0

View full text Add to dashboard Cite

The non-local means (NLM) is a classical image denoising algorithm. However, the denoising effect of the NLM algorithm is easily affected by the noise level of neighboring pixel and image edge information, which leads to poor denoising effect for high noise level image. In this paper, an improved NLM (I-NLM) denoising algorithm is proposed, which can extract the gradient information of the image more accurately by fusing the Laplacian of Gaussian operator. At the same time, the algorithm combines the real domain information and the gradient information of the image to calculate the weight of the similarity between the image blocks. Experimental results show that compared with the traditional NLM algorithm, the proposed I-NLM algorithm can effectively preserve the edge of the image while suppressing the noise, and recover the CT images with high Peak signal-to-noise ratio (PSNR) and SSIM values.

show abstract

“…They were able to automatically learn the training data without the need for human intervention. Zhang et al (2014) enhanced the diversified structure network and created a dual-branch network module structure by combining it with the concept of the Inception module structure in the GoogLeNet network. By incorporating the Fourier transform and discrete wavelet transform, Michel et al (2015) enhanced the CNN model and algorithm and used it for image-recognition research.…”

mentioning

confidence: 99%

Practical Research on the Application of Multimedia and Visual Image Technology in the Cultivation of College Counselors in the Network Environment

Du

2024

International Journal of Information and Communication Technology Education

0

View full text Add to dashboard Cite

In the context of the multimedia era, college counselors and college students should make progress together. This article aims to explore the practical issues of applying multimedia and visual-image technology to the training of college counselors. We propose a three-dimensional multimedia visual image recognition technology based on convolutional neural networks (CNNs) and apply the algorithm to image-recognition tasks to provide support and assistance for college-counselor training in network and multimedia environments. By combining a CNN with image recognition, our research results show that this method can effectively adapt to different types of image-recognition tasks. This means that our algorithm can be fully applied to these tasks and provide strong support for the training of college counselors.

show abstract

An improved non-local means algorithm for CT image denoising

Huihua,

Wenbo,

Yunxia

2023

Preprint

0

View full text Add to dashboard Cite

The non-local means (NLM) is a classical image denoising algorithm. However, the denoising effect of the NLM algorithm is easily affected by the noise level of neighboring pixel and image edge information, which leads to poor denoising effect for high noise level image. In this paper, an improved NLM (I-NLM) denoising algorithm is proposed, which can extract the gradient information of the image more accurately by fusing the Laplacian of Gaussian operator. At the same time, the algorithm combines the real domain information and the gradient information of the image to calculate the weight of the similarity between the image blocks. Experimental results show that compared with the traditional NLM algorithm, the proposed I-NLM algorithm can effectively preserve the edge of the image while suppressing the noise, and recover the CT images with high Peak signal-to-noise ratio (PSNR) and SSIM values.

show abstract

Super Resolution Image Reconstruction Based on Image Similarity and Feature Combination

Cited by 3 publications

References 0 publications

An improved non-local means algorithm for CT image denoising

An improved non-local means algorithm for CT image denoising

Practical Research on the Application of Multimedia and Visual Image Technology in the Cultivation of College Counselors in the Network Environment

An improved non-local means algorithm for CT image denoising

Contact Info

Product

Resources

About