Abstract: A user adaptive image compensator includes a feature extractor, a compensated image generator, an image selector, and a preference parameter updater. The feature extractor extracts features from an input image. The compensated image generator generates compensated preference parameters based on a preference parameter. The compensated image generator generates a plurality of compensated images by compensating the input image based on the compensated preference parameters. The image selector displays the compensated images to a user. The image selector outputs a selected compensated image, which is selected from the compensated images by the user, as an output image. The image selector outputs a selected compensated preference parameter from the compensated preference parameters and which corresponds to the selected compensated image. The preference parameter updater updates the preference parameter based on the selected compensated preference parameter and the extracted features.

Abstract: A user adaptive image compensator includes a feature extractor, a compensated image generator, an image selector, and a preference parameter updater. The feature extractor extracts features from an input image. The compensated image generator generates compensated preference parameters based on a preference parameter. The compensated image generator generates a plurality of compensated images by compensating the input image based on the compensated preference parameters. The image selector displays the compensated images to a user. The image selector outputs a selected compensated image, which is selected from the compensated images by the user, as an output image. The image selector outputs a selected compensated preference parameter from the compensated preference parameters and which corresponds to the selected compensated image. The preference parameter updater updates the preference parameter based on the selected compensated preference parameter and the extracted features.

Abstract: Image restoration by restoring a high-frequency component of a deteriorated image. A high-frequency image information predicting and stabilizing method includes: determining a shooting area, which is a high-frequency area that includes an overly-restored high-frequency component, in an input image; predicting a high-frequency component of the input image by applying different deterioration models to the shooting area and a remaining area in the input image; and stabilizing a high-frequency component of an edge area by using an edge blur kernel determined to be parallel to an edge direction of the input image.

Abstract: An image scaling apparatus and method, with enhancement of image quality. The method includes generating a plurality of intermediate pixels positioned near a plurality of resultant pixels to be generated to scale an input image using pixels of the input image; determining the image characteristics of the plurality of resultant pixels using a predetermined region of the input image or the plurality of intermediate pixels within the predetermined region; determining a filter for generating the plurality of resultant pixels based on the image characteristics with respect to the resultant pixels, and generating the plurality of resultant pixels through filtering of the plurality of intermediate pixels using the determined filter. The apparatus includes an intermediate pixel generation unit which generates a plurality of intermediate pixels. A filter determination unit determines a filter for generating the plurality of resultant pixels.

Abstract: An apparatus and method for suppressing color rolling are provided. The apparatus includes a digital signal processor which detects first motion information on a current frame and second motion information on at least one of a plurality of neighboring frames, calculates a gain based on the first and second motion information, and applies the gain to at least one channel of the current frame.

Abstract: Image restoration by restoring a high-frequency component of a deteriorated image. A high-frequency image information predicting and stabilizing method includes: determining a shooting area, which is a high-frequency area that includes an overly-restored high-frequency component, in an input image; predicting a high-frequency component of the input image by applying different deterioration models to the shooting area and a remaining area in the input image; and stabilizing a high-frequency component of an edge area by using an edge blur kernel determined to be parallel to an edge direction of the input image.

Abstract: An image scaling apparatus and method, with enhancement of image quality. The method includes generating a plurality of intermediate pixels positioned near a plurality of resultant pixels to be generated to scale an input image using pixels of the input image; determining the image characteristics of the plurality of resultant pixels using a predetermined region of the input image or the plurality of intermediate pixels within the predetermined region; determining a filter for generating the plurality of resultant pixels based on the image characteristics with respect to the resultant pixels, and generating the plurality of resultant pixels through filtering of the plurality of intermediate pixels using the determined filter. The apparatus includes an intermediate pixel generation unit which generates a plurality of intermediate pixels. A filter determination unit determines a filter for generating the plurality of resultant pixels.

Abstract: An apparatus and method for suppressing color rolling are provided. The apparatus includes a digital signal processor which detects first motion information on a current frame and second motion information on at least one of a plurality of neighboring frames, calculates a gain based on the first and second motion information, and applies the gain to at least one channel of the current frame.