Method for producing super-resolution images and nonlinear digital filter for implementing same

Abstract

The invention relates to the field of photo and video images and can be used for producing high-quality images of visually close objects using a camera or video camera equipped with sensors with an electronic shutter. The technical result consists in increasing the resolution of an image when a plurality of frames of low resolution are used for producing one frame of high resolution (i.e. super-resolution), as well as the possibility of high-speed capture of a plurality of frames of an image while scanning only part of the sensor. The result is achieved in that a plurality of frames is exposed, initial images are produced by means of a reading from the sensor in the form of a continuous sequence of frames with high-speed capture, during which the frequency of the frames is inversely proportional to the magnitude of that part of the light-sensitive region of the sensor which is being scanned, said initial images are aligned, an enhanced image is produced and this image is filtered using a nonlinear filter, which comprises a neural network which is pretrained using a test image comprising radial and sinusoidal test charts, as well as reference points. Furthermore, the filtration comprises supplying premodified digitized data to the neural network, wherein the modification of said data comprises: isolating the low-frequency component, arranging the pixels element-by-element, reading the low-frequency component from the arranged pixels, and subsequently standardizing said pixels. Then, the data at the output of the neural network are subjected to inverse standardization, and the low-frequency component is added to the value at the output of the neural network.

Description

technical field [0001] The invention relates to the field of photographic and video images and can be used to produce high quality images of visually magnified objects by means of photo and video cameras equipped with sensors with electronic shutters. Background of the invention [0002] Modern mobile devices are often equipped with photo and video cameras capable of capturing very high-quality images. However, the mobility requirements of such devices do not allow the use of optical systems (lenses) with variable focal lengths (variable magnification zoom lenses) in order to capture visually magnified images due to their large size. Therefore, such mobile devices rely on the use of digital zoom. [0003] The following solutions are known in the art: [0004] A digital zoom method is used to obtain an enlarged image with low resolution. When using this method of visual magnification, only the central portion of the sensor is active. Then, to obtain an image with a number...

AI Technical Summary

Problems solved by technology

[0031] - It is necessary to split the images into two groups during processing; this requires additional computational resources

Images