An image processing apparatus applies an image to a first learning network model to optimize the edges of the image, applies the image to a second learning network model to optimize the texture of the image, and applies a first weight to the first image and a second weight to the second image based on information on the edge areas and the texture areas of the image to acquire an output image.

A video coder for predictive coding a video stream of subsequent frames according to motion compensation into an encoded video bit stream is provided. The video coder comprises a frame buffer adapted to store at least one reference frame of the video stream, the at least one reference frame being different from a current frame of the video stream, an inter predictor adapted to generate a prediction block of a current block of the current frame from a reference block of the reference frame, and a sharpening filter adapted to filter the prediction block.

A system and method for improving the detail of an input digital video signal can be implemented by computing first and second order gradients of the input digital video signal in a neighborhood size of 1,2, 4,8 and 16 increments. This gradient information can be used to construct an output digital video signal that has greater detail than the input digital video signal.

A system for improving imaging during a surgical procedure includes an image sensor coupled to a controller. The image sensor is coupled to capture a video, including a first image frame with a smoke occlusion due to surgical smoke, of the surgical procedure. The first image frame includes a plurality of pixels each having an imaged color representing a view of the tissue affected by the smoke occlusion. The controller stores instructions that when executed causes the system to perform operations. The operations include determining an estimated true color of each of the plurality of pixels. The estimated true color is closer to an unoccluded color of the tissue than the imaged color. The operations also include generating, in response to determining the estimated true color, a desmoked first image frame with a reduced amount of the smoke occlusion relative to the first image frame.

Disclosed is a display apparatus including: a signal receiver configured to receive an image signal; a display configured to display an image; a processor configured to: calculate a change degree and a change direction of pixel value differences between at least one first pixel and two or more second pixels of an image, and change a pixel value of the first pixel based on the pixel value difference which is relatively small among the pixel value differences obtained by the calculated change degree and the calculated change direction. According to this, it is possible to enhance the image details without generating or and increasing of the noises.

An apparatus includes a first circuit and a second circuit. The first circuit may be configured to (i) generate a sharpened region by sharpening an original region of an image and (ii) generate edge information by detecting an edge in the original region of the image. The second circuit may be configured to (i) evaluate a current sample of the sharpened region proximate to the edge for an artifact based on the edge information and (ii) generate a final sample by adjusting the current sample in the sharpened region where the artifact is detected. The artifact may be an overshoot or an undershoot.

A color-shift calibration method is provided to process an image including pixels, in which an arrangement of the pixels corresponds to a Bayer color filter array and the pixels include first green pixels, second green pixels, red pixels and blue pixels. The color-shift calibration method includes the steps outlined below. A regional gradient change of the first and the second green pixels within a neighboring region corresponding to a target green pixel is calculated. An intensity difference between the first and the second green pixels is calculated. When the regional gradient change is smaller than a gradient threshold and the intensity difference exceeds an intensity threshold range, a pixel calibration is performed on the target green pixel based on the first and the second green pixels.

System and method for joint refinement and perception of images are provided. A learning machine employs an image acquisition device for acquiring a set of training raw images. A processor determines a representation of a raw image, initializes a set of image representation parameters, defines a set of analysis parameters of an image analysis network configured to process the image's representation, and jointly trains the set of representation parameters and the set of analysis parameters to optimize a combined objective function. A module for transforming pixel-values of the raw image to produce a transformed image comprising pixels of variance-stabilized values, a module for successively performing processes of soft camera projection and image projection, and a module for inverse transforming the transformed pixels are disclosed. The image projection performs multi-level spatial convolution, pooling, subsampling, and interpolation.

The image processing apparatus includes: an input unit configured to receive input of a plurality of images; an alignment unit configured to select each of the plurality of images one by one as a base image, and aligns the base image and each of comparison images; a selection unit configured to select the comparison image to be combined with the base image from among the comparison images aligned with the base image for each of the base images, calculate a common region in which images included in the combination can be commonly drawn, and select the combination in which the ratio of the common region to the base image satisfies a predetermined condition; a determination unit configured to determine the combination that maximizes the number of comparison images from the selected combination; and an output unit configured to output an image group corresponding to the determined combination.

A control apparatus includes a first acquirer configured to acquire first blur information based on a motion vector calculated using an imaging signal from an image sensor, a second acquirer configured to acquire second blur information based on a blur signal from a blur detector, and a controller configured to control driving of an image stabilizing element in accordance with third blur information obtained by using the first blur information and the second blur information. A weight for the first blur information in acquiring the third blur information is determined based on a comparison between the first blur information and the second blur information.