31results about How to "Achieving Super-Resolution Reconstruction" patented technology

The embodiment of the invention provides a method and device for improving equipment electromagnetic characteristic measurement precision, and the method comprises the following steps: building a neural network model of a Maxwell equation based on a deep learning solving model of an electromagnetic equation in combination with a neural network, the method specifically comprises the following steps: receiving emission source data and a space electromagnetic characteristic distribution value solved by a deep learning solution model of an electromagnetic equation; transmitting source data and the space electromagnetic characteristic distribution value are input into a neural network; combining the emission source data and the spatial electromagnetic characteristic distribution value by using a neural network, and establishing a neural network model of a Maxwell equation; solving the electromagnetic characteristic distribution of the equipment space by using a neural network model of a Maxwell equation; and correcting the solution through a neural network model of a Maxwell equation. Compared with the current mainstream electromagnetic scattering and inverse scattering numerical method, the efficiency is improved by more than 20%, the super-resolution reconstruction of the detected target structure is realized, and the inverse scattering imaging resolution is wholly superior to that of the mainstream method.

The invention provides an image reconstruction method, a terminal and a computer readable storage medium. The method includes the following steps: extracting a plurality of local image blocks in a to-be-reconstructed image; calculating the hash key value of each local image block according to gradient feature information of each local image block in the to-be-reconstructed image, wherein there is a mapping relationship between the hash key values and the gradient feature information; calculating the pixel value of a target image block according to the hash key values, wherein the number of pixels in the target image block is N<2> times the number of pixels in each local image block, N>=2, and N is a positive integer; and reconstructing a super-resolution image according to the calculated pixel value of each local image block, wherein the resolution of the super-resolution image is N times the resolution of the to-be-reconstructed image. The method of the invention reduces the computation complexity and improves the operation speed. Moreover, the method has high processing speed, and the reconstructed high-resolution image is of high clarity and has good edge features.

The invention discloses a device for expanding an ultrasonic detection region and increasing detection precision and a method. The device consists of an ultrasonic coupling gasket and reflection grains embedded in an ultrasonic coupling gasket substrate, an outer layer material of the ultrasonic coupling gasket substrate is harder than an inner layer material of the ultrasonic coupling gasket substrate, both the outer layer and the inner layer of the ultrasonic coupling gasket are made of acoustic transmission materials, the sound velocity of ultrasonic waves transmitted in the ultrasonic coupling gasket is consistent, and the reflection grains are embedded in the outer layer material of the ultrasonic coupling gasket substrate and are arrayed. In the method, accurate position information is marked in an image detected by an ultrasonic probe by the reflection grains, an external and common coordinate system is built for local ultrasonic images obtained at different moments, prior information is provided for mosaic, fusion and registration of the local images, a registration arithmetic is simplified, fast mosaic and fusion of the detected images are realized, accordingly, the detection region is expanded, and super-resolution images are obtained.

The invention discloses a wavelet preprocessing and sparse representation-based satellite remote sensing image super-resolution reconstruction method and belongs to the technical field of satellite remote sensing image processing. The wavelet preprocessing and sparse representation-based satellite remote sensing image super-resolution reconstruction method is applicable to high resolution remote sensing images and low resolution remote sensing images with different time resolutions in the same known observation area, super-resolution reconstruction is performed on low resolution remote sensing images at other observation times and the spatial resolution of the low resolution remote sensing images is improved. The wavelet preprocessing and sparse representation-based satellite remote sensing image super-resolution reconstruction method specifically comprises steps of dictionary training and low resolution remote sensing image reconstruction. According to the wavelet preprocessing and sparse representation-based satellite remote sensing image super-resolution reconstruction method, the phonological change of the remote sensing image is taken into consideration, wavelet domain dictionaries comprising different character information are constructed, super-resolution reconstruction of the low resolution remote sensing images is effectively achieved based on training of the three pairs of wavelet section dictionaries and in combination with sparse representation, image detail features are well obtained, the reconstruction quality of the low resolution remote sensing images is effectively improved, and a basis is provided for later applications of the low resolution remote sensing images.

The invention relates to a method and device for witness verification. The method includes: acquiring a certificate face image in a certificate photo, collecting a user's natural light face image; inputting the certificate face image into a pre-trained generative adversarial network, and obtaining the A reconstructed face image corresponding to the credential face image; wherein, the generated confrontation network is used to add preset natural light attribute information to the input credential face image, and the resolution of the reconstructed face image output by it is higher than that of the The resolution of the face image of the certificate; comparing the reconstructed face image with the natural light face image, and verifying the witness according to the comparison result. The invention can effectively improve the accuracy of authentication verification.

The invention discloses an image super-resolution reconstruction method based on a multi-core gaussian process regression and mainly solves the problems that the current super-resolution reconstruction method generates edge sawtooth effect and the reconstruction texture is not rich. The image super-resolution reconstruction method based on the multi-core gaussian process regression comprises the following steps: (1), obtaining a low-resolution luminance image and an interpolation image and blocking the low-resolution luminance image and the interpolation image; (2), extracting central pixels and eight neighborhoods of low-resolution luminance image blocks to train an upper sampling model of the gaussian process regression; (3), forecasting pixel values of initial high-resolution luminance image blocks by using the upper sampling model; (4), combining all the initial high-resolution luminance image blocks to obtain an initial high-resolution luminance image; (5), obtaining an analog low-resolution image and blocking the analog low-resolution image; (6), extracting central pixels of the analog low-resolution image blocks to train a deblurring model of the gaussian process regression; (7), forecasting pixel values of the high-resolution luminance image blocks by using the deblurring model; and (8), combining all the high-resolution luminance image blocks to obtain a high-resolution luminance image. The image super-resolution reconstruction method based on the multi-core gaussian process regression is applicable to video monitoring and imaging of high-definition televisions.