Patent
Single-image super-resolution reconstruction method based on deep residual network
Reads0
Chats0
TLDR
Zhang et al. as mentioned in this paper proposed a single-image super-resolution reconstruction method based on a deep residual network, which mainly comprises a first step of performing block extraction and pixel averaging processing on an image in a sample image database to obtain a corresponding high-resolution and low-resolution training image sets; a second step of constructing a deep convolutional neutral network with a residual structure for iterative training, and then inputting the training set obtained in the first step to the neural network constructed in the second step, according to a data model obtained by training, realizing theAbstract:
The invention discloses a single-image super-resolution reconstruction method based on a deep residual network. The method of the invention mainly comprises a first step of performing block extraction and pixel averaging processing on an image in a sample image database to obtain a corresponding high resolution and low resolution training image sets; a second step of constructing a deep convolutional neutral network with a residual structure for iterative training, and then inputting the training set obtained in the first step to the neural network constructed in the second step for iterative training; and a third step of according to a data model obtained by training, realizing the continuous up-scaling of the input low resolution image through the combination of iterative operation and an interpolation algorithm. By introducing a deep residual network and introducing an upsampling layer at the end of the network, the method of the invention accelerates the processing speed of the image up-scaling, enhances the display effect of the image details, obtains a better image super-resolution reconstruction effect, and has a wide range of applications in the image high definition display, image compression, security checks and other fields.read more
Citations
More filters
Patent
Image Processing Method and Device
Abstract: In a rectangular region detection mechanism, a to-be-processed image information is received, where the to-be-processed image information comprises at least two images, and where the at least two images comprise a same plurality of first feature points A plurality of first edge line segments in one of the at least two images are detected Four first edge line segments from the plurality of first edge line segments are determined Locations of photographed points corresponding to the plurality of first feature points in a region formed by the four first edge line segments are determined based on location information of the plurality of first feature points The region is determined as a rectangular region when the photographed points corresponding to the plurality of first feature points in the region are coplanar
Patent
Intelligent identification method for electrocardiogram data based on residual network
TL;DR: In this article, an intelligent identification method for electrocardiogram data based on a residual network was proposed, which comprises the steps of S1, according to the Rwave position, intercepting a map in front and behind the heartbeat signal R wave position, and dividing the map into a training set and a test set proportionally; S2, constructing a deep convolutional neural network structure with a residual structure, and adding dense connection based on the original residual network; S3, inputting the training set into the network structure for iterative training, and conducting iteration
Patent
Face super-resolution reconstruction method based on extremely deep convolutional neural network
TL;DR: In this paper, a face super-resolution reconstruction method based on an extremely deep convolutional neural network, which comprises the following steps of 1, performing down sampling and processing on a high resolution face image by different multiples to obtain a low-resolution face image training set.
Patent
Image super-resolution method and device
TL;DR: In this paper, an image super resolution method and device is proposed to improve the quality of a high resolution image obtained by means of super resolution, which can be applied to the field of computer vision technology for artificial intelligence.
Patent
Hyperspectral image super-resolution reconstruction method and device based on depth residual network
TL;DR: In this article, a super-resolution reconstruction method of a hyperspectral image based on a depth residual network was proposed. But the method of the method is limited to a single image.
References
More filters
Patent
Device for reconstructing based on super-resolution of multi-block single-frame image, system and method thereof
TL;DR: In this paper, a multi-block super-resolution method based on scale-invariant self-similarity (SiSS) was proposed for reconstructing from a single video frame.
Patent
Super-resolution amplification method of ultra-high definition video image converted from high definition video image
TL;DR: In this article, a super-resolution amplification method of an ultra-high definition video image converted from high-definition video image is proposed. But the method is not suitable for the real-time frame rate of 25 fps.
Patent
Single image super-resolution reconstruction method base on block rotation and sharpness
TL;DR: In this article, a single image super-resolution reconstruction method based on block rotation and sharpness is proposed, where the sample blocks are rotated by a certain angle, and then the block definition is introduced to classify training samples.