To solve the problem that the extracted features are not accurate due to the use of single-size convolution kernel in convolution neural network super-resolution reconstruction algorithm, a network structure combining multi-scale features is proposed. The structure consists of a multi-scale feature extraction block and a reconstruction module. Multiple convolution kernels are adopt to extract he multi-scale feature in multi-scale feature extraction module, and sub-pixel convolution layer is used to enlarge the feature image size to high-resolution image size in the image reconstruction module. The deep network model in this paper fully considers the importance of multi-scale features and can better reconstruct the high-frequency details of the image. The experimental results show that the improved network structure model can enhance the quality of image reconstruction and can better deal with the problem of image super-resolution reconstruction.
KEYWORDS: Lawrencium, Image quality, Image restoration, Super resolution, Image resolution, Visualization, Detection and tracking algorithms, Communication engineering, Roads, Signal to noise ratio
Multi-scale structural self-similarity refer to those similar structures recurring many times within and across scales of the same image. In this paper, we present a single image super resolution (SR) method based on multi-scale structural selfsimilarity and neighborhood regression, which reconstructs a high resolution (HR) image from the image pyramid of the input image itself without depending on extrinsic set of training images. In the proposed approach, we find the nearest neighbor patches for each low resolution (LR) image patch, and then learn the neighborhood regression to map low resolution space to high resolution space. Experimental results show that our approach acquires better result in peak signal to noise ratio and visual effects against several competing methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.