Embodiments described herein provide an integrated holographic reconstruction platform that enables a user to perform three-dimensional visualization of a phenomenon by reconstructing holograms using a combination of normalization and propagation algorithms, which yields better results with significantly less demanding processing time and computing resources. Specifically, the integrated holographic reconstruction platform may be implemented as an all-in-one computer software that includes software components of digital holographic reconstruction, de-twinning and optical distortion removal via a user-friendly graphical interface.

Systems for image evaluation and dynamic cropping are provided. In some examples, a system, may receive an instrument or image of an instrument. Identifying information may be extracted from the instrument or image of the instrument. Based on the extracted identifying information, a check/check image profile may be retrieved. In some examples, expected size and/or shape data may be extracted from the check/check image profile. The extracted expected size and/or shape data may be compared to size and/or shape data from the received instrument or image of the instrument to identify any anomalies (e.g., to determine whether the expected size and/or shape data matches the size and/or shape data of the received instrument or image of the instrument. If the expected size and/or shape data does not match size and/or shape data from the received instrument or image of the instrument, the instrument or image of the instrument may be programmatically modified and a modified image of the instrument may be generated.

The present disclosure relates to an image processing method. The image processing method may include upscaling a feature image of an input image by an upscaling convolutional network to obtain a upscaled feature image; downscaling the upscaled feature image by a downscaling convolutional network to obtain a downscaled feature image; determining a residual image between the downscaled feature image and the feature image of the input image; upscaling the residual image between the downscaled feature image and the feature image of the input image to obtain an upscaled residual image; correcting the upscaled feature image using the upscaled residual image to obtain a corrected upscaled feature image; and generating a first super-resolution image based on the input image using the corrected upscaled feature image.

A method includes exciting, at a first time period, a first set of pixels in an excitation array, wherein the first set of pixels comprises more than one pixel, and no pixel in the first set of pixels is adjacent to another pixel in the first set of pixels. The method also includes exciting, at a second time period, a second set of pixels in the excitation array wherein the second set of pixels comprises more than one pixel, and no pixel in the second set of pixels is adjacent to another pixel in the second set of pixels. The method retrieves excitation data, wherein the excitation data is comprised of data from the first set of pixels and data from the second set of pixels, and the excitation data is capable of being combined to reconstruct an image of a target object for rendering on a display.

A method of filtering a fingerprint image is provided. The method includes: receiving an input fingerprint image; preliminarily filtering the input fingerprint image to obtain a preprocessed image; normalizing and then filtering the preprocessed image to obtain a denoised image; filtering and then segmenting the preprocessed image to obtain a background mask; postprocessing the background mask to obtain a final mask; and applying the final mask to the denoised image to obtain an output fingerprint image.

The present disclosure provides an image processing method applied to a displaying terminal. The method includes: receiving a to-be-processed layer image delivered by the displaying terminal; querying a high resolution layer image matched with the to-be-processed layer image in a preset database based on the to-be-processed layer image; and delivering the high resolution layer image to the displaying terminal, thereby the displaying terminal processes the to-be-processed layer image based on the high resolution layer image. The present disclosure further discloses an image processing device, system and computer readable storage medium. According to the disclosure, an image resolution is improved.

An image signal processor is provided. The image signal processor includes a white balancing block which performs white balancing on a raw RGB image of a Bayer pattern received from an image sensor on a kernel basis or in a kernel unit, a green generation block which performs cross-binning on white-balanced G pixel to generate a first green pixel, and adds a high-frequency component to which a preset weight is applied to generate a binned green pixel, a red-blue generation block which generates a U pixel and a V pixel indicating directionality, on the basis of the binned green pixel, a white-balanced R pixel, and a white-balanced B pixel, and merges the binned green pixel to each of the U pixel and the V pixel to generate a binned red pixel and a binned blue pixel and an inverse white balancing block which performs an inverse white balancing on the binned red pixel, the binned green pixel, and the binned blue pixel to output a final binning image.

Disclosed herein includes a system, a method, and a device for improving computational efficiency of deconvolution by reducing a number of dot products. In one aspect, an input image having a set of pixels is received. A first dot product may be performed on a subset of the set of pixels of the input image and a portion of a kernel, to generate a first pixel of an output image. A number of multiplications performed for the first dot product performed may be less than a number of elements of the kernel. A second dot product on a remaining portion of the kernel to generate the first pixel of the output image may be bypassed.

Disclosed in the present invention is a point cloud attribution compression method based on deleting 0 elements in a quantisation matrix, including optimizing a traversal sequence for a quantisation matrix and deleting the 0 elements at the end of the data stream. The present invention may use seven types of traversal sequences at the encoding end of the point cloud attribute compression, such that the distribution of the 0 elements in the data stream may be more concentrated at the end thereof. The 0 elements at the end of the data stream may be deleted, removing redundant information and reducing the quantity of data to be entropy encoded. At the decoding end, the point cloud geometric information may be incorporated to supplement the deleted 0 elements and the quantisation matrix may be restored according to the traversal sequence, thereby improving compression performance without introducing new errors.

Techniques are described for content-adaptive downsampling of digital images and videos for computer vision operations, such as semantic segmentation. A computer vision system comprises a memory, one or more processors operably coupled to the memory and a downsampling module configured for execution by the one or more processors to perform, based on a non-uniform sampling model trained to predict content-aware sampling parameters, downsampling input image data to generate downsampled image data. A segmentation module is configured for execution by the one or more processors to perform segmentation on the downsampled image to produce a segmentation result, such as a feature map that assigns pixels of the downsampled image data to object classes. An upsampling module is configured for execution by the one or more processors to perform upsampling according to the segmentation result to produce upsampled image data.