5results about How to "Achieve super resolution" patented technology

The invention relates to a reflective non-labeled super-resolution optical microscopic system and method. The reflective non-labeled super-resolution optical microscopic system comprises a large-numerical-aperture conical super-resolution focusing module, a super-resolution focusing light field illumination and collection module, a sample and mechanical scanning module, a super-resolution imaging module and a wide-field microscopic imaging module, the characteristics of super-resolution focal spot, super-long focal depth, high radial spatial frequency, narrow frequency passband and the like of a large-numerical-aperture conical super-resolution light beam are utilized, projection of a super-resolution light field on front focal planes of two objective lenses is realized by adopting a 4f system, and a marking-free reflective far-field super-resolution optical microscopic system and method are realized by combining a confocal working principle; non-marked far-field super-resolution two-dimensional microscopic imaging is realized through two-dimensional scanning; and performing non-label far-field super-resolution two-dimensional microscopic imaging on object planes at different axial positions to obtain super-resolution two-dimensional microscopic imaging of different cross sections of the sample, thereby realizing three-dimensional chromatography. According to the invention, non-label, super-resolution and tomography of the sample can be realized.

The invention discloses a display optimization method for a low-resolution image of a double-layer ink electronic paper display, which comprises the following steps: in response to a display picture signal corresponding to a first image received by the electronic paper display, judging whether the first image is a low-resolution image; obtaining a display pixel group in response to the fact that the first image is a low-resolution image; obtaining a first upper-layer driving voltage and a second lower-layer driving voltage corresponding to the display gray-scale value according to the display gray-scale value corresponding to the display pixel group; driving the native pixel by adopting the first upper-layer driving voltage and the second lower-layer driving voltage of the display pixel group to which the native pixel belongs, and driving the interpolation pixel by adopting the first upper-layer driving voltage of the display pixel group to which the interpolation pixel belongs and the second lower-layer driving voltage of the adjacent display pixel group to which the interpolation pixel belongs. The image super-resolution is realized through the characteristics of the electronic paper display, and the display effect of the electronic paper display is improved.

The invention discloses an anti-diffraction super-resolution lensless imaging method based on a random coding mask, belongs to the technical field of computational imaging, and aims to solve the problems in the prior art. Obtaining a point spread function (PSF) of the lens-free imaging system on the image sensor; establishing a general regularization equation according to the collected aliasing image and a calibrated point spread function (PSF); splitting the regularization equation; adding an activation function into the split regularization equation to obtain an improved regularization equation; solving the regularization equation to obtain an unknown number analytic expression and a hyper-parameter analytic expression; substituting the Fourier expression into the unknown number analytic expression and the hyper-parameter analytic expression in an operator form to obtain the unknown number analytic expression and the hyper-parameter analytic expression in the Fourier form; and substituting an aliasing image directly acquired by the lensless imaging system and a point spread function (PSF) of the system into the unknown number analytic expression and the hyper-parameter analytic expression, and iteratively calculating each unknown number and hyper-parameter until convergence.

The invention provides a radar range profile super-resolution intelligent imaging method, which comprises the following steps of: firstly, converting a radar echo into a high-dimensional space to represent and capture difference characteristics of a deeper layer; then, a plurality of iteration stages composed of a measurement consistency module and a prior filtering module are provided, so that noise is suppressed and target features are enhanced in a high-dimensional space; and finally, weighting and combining the extracted high-dimensional features through a data dimension reduction module to realize HRPP super-resolution. Therefore, the HRPP super-resolution is realized in a model guiding and data driving mode, the robustness of the result can be ensured through the model, and the algorithm performance is improved through data driving; in addition, the distance high-dimensional feature extraction capability and discrimination capability can be improved through adaptive high-dimensional hyper-parameter learning, and the overall architecture learning capability is improved through a true value fuzzy technology.

The invention relates to the field of spectrum reconstruction, in particular to a spectrum reconstruction method for a broadband filtering modulation spectrum detection system, which comprises the following steps of: converting a hyperspectral data set into a training data set according to parameters of the broadband filtering modulation spectrum detection system; building a spectrum reconstruction network model based on deep learning and carrying out training; and pixel splitting point-by-point scanning reconstruction is carried out on a reconstruction target, a hyperspectral image is constructed according to original arrangement, space-spectrum joint optimization is carried out, and finally high-precision spectral image reconstruction is realized. According to the method, the demand of a spectrum reconstruction process on a data set scale is reduced through a pixel splitting point-by-point scanning reconstruction strategy, a Transform architecture is introduced into a reconstruction network, the feature information extraction capability of the network is improved, the strong nonlinear characterization capability of a KAN architecture is combined, the spectrum curve reconstruction precision is improved, and spatial spectrum combined processing is combined, so that the spectrum reconstruction efficiency is improved. The error is further reduced, and high-quality reconstruction of the spectral image is realized.