5 results about "Image restoration" patented technology

The invention relates to a self-adaptive optical image high resolution restoration method combined with frame selection and blind deconvolution, comprising the following steps: firstly, a short exposure image sequence gn (x, y) is recorded when a self-adaptive optical closed loop is corrected; shannnon entropy of each frame of image in the sequence is calculated; a degraded image gm (x, y) with lower entropy is selected for blind deconvolution image restoration; secondly, an initial value hm (x, y) of a point spread function is generated by utilization of random phase; thirdly, a target f(x, y) is estimated by using the gm(x, y) and the obtained hm (x, y), and an estimated value f(x, y) is obtained after addition of positivity limitation on the target; fourthly, an estimated value hm (x, y) of the point spread function is obtained by using the gm (x, y) and the f(x, y), and an estimated value h(x, y) is obtained after addition of positivity limitation in the same way; fifthly, inspection is made whether an iterated value h(x, y) and an iterated value f(x, y) meet iteration stopping requirements or not; if the iterated values do not meet the iteration stopping requirements, the third step is returned; if the iterated values meet the iteration stopping requirements, circulation is stopped and the f(x, y) and the h(x, y) are outputted. The invention has the advantages of effective improvement of restoration quality, acceleration of convergence rate, capability of well compensating correction capability under hardware limitation of a self-adaptive optical system, and improvement of imaging quality.

The invention discloses an image super-resolution reconstruction system based on multi-stage recursive feature fusion and method thereof, and relates to the technical field of image restoration. The system is characterized in that an initial feature extraction module (10), a recursive feature extraction module (20), a multi-stage feature fusion module (30), an adder module (40) and an up-samplingreconstruction module (50) are interacted in sequence, and the initial feature extraction module (10) is interacted with the multi-stage feature fusion module (30) and the adder module (40). The method comprises the following steps: 1, extracting initial features; 2, extracting recursive feature; 3, fusing multistage feature; 4, generating depth features; 5, generating a high-resolution image. According to the method, while the high-quality super-resolution reconstructed image is obtained, the realization complexity of the system is well reduced, and the calculation time is shortened. The method is suitable for video monitoring, medical imaging and other applications.

An image processing apparatus (804) includes a function obtaining portion (804a) configured to obtain a first optical transfer function which is different depending on a shooting condition and on a position in an image, a corrected image generating portion (804b) configured to generate a corrected image from the image using the first optical transfer function, and an image restoration portion (804c) configured to perform blind deconvolution processing using the corrected image to generate a restored image.

An image restoration method includes providing image data (260) including image statistics (230) using a digital camera module. A set of digital camera module characterization parameters is selected from a common dynamic camera configuration file (210) using the image statistics (230). The selected digital camera module characterization parameters are converted to image signal processing parameters and the image data is tuned using the image signal processing parameters for providing a tuned image (270). The method may involve lens shading correction as well adjusting the processing to the characteristics of the image sensor (250).

The invention relates to an image processing method and device, a storage medium and electronic equipment, and aims to remove diffraction fringes formed by a light spot diffraction phenomenon in an image, prevent other objects near a light source from being shielded by the diffraction fringes, obtain an image more conforming to an actual scene and improve the shooting experience of a user. The generation of diffraction includes but is not limited to an under-screen camera, a common cameras and the like. The image processing method comprises the following steps: acquiring a to-be-processed initial image, a light source being displayed in the initial image; determining a diffraction region in the initial image, the diffraction region comprising diffraction fringes generated by a diffraction phenomenon of the light source; and according to pixel points in a preset range of the edge of the diffraction region, performing image restoration operation on the initial image to remove the diffraction fringes included in the diffraction region in the initial image so as to obtain a target image.