Abstract: A color conversion method for wide-gamut color spaces, in which color conversion is performed without gamut clipping so that data corresponding to a predetermined wide-gamut color space can be directly output by a display device that supports a different wide-gamut color space from the predetermined wide-gamut color space, and which maintains characteristics of the predetermined wide-gamut color space. The color conversion method includes converting data of a predetermined wide-gamut color space into data of the RGB color space, determining whether the RGB data is outside the gamut of the RGB color space, extending the RGB data and clipping the extended RGB data if the RGB data is outside the gamut of the RGB color space, and dividing the clipped RGB data into a number of regions and performing a mapping operation in units of regions.

Abstract: A system, medium, and method calibrating gray data. The system calibrating gray data includes a transformation unit to transform red, green, and blue (RGB) data of a source device into transformed color data of a different color space using a color appearance model, and a calibration unit to map a chroma value of gray data, corresponding to the transformed color data, in the different color space to a predetermined value to generate calibrated color space data.

Abstract: An apparatus and method are provided for reproducing an optimized preference color using candidate images and natural languages, in which user-oriented optimized picture quality can be provided through a printer. The apparatus includes a preference color-natural language information memory which stores characteristic information of a preference color mapped on a natural language, a candidate image provider module which provides candidate images having characteristic information applied to original images, and a candidate preference image input module which inputs one image, which satisfies a user's preference, among the candidate images.

Abstract: An apparatus, method and medium outputting a wide gamut space image in which one or more parameters that are needed to convert an existing color space into a wide gamut space are experimentally determined and then are applied to an image. The apparatus includes a feature extraction module to extract one or more feature differences between a standard gamut and a wide gamut of an image, a color range setting module to set a hue range according to the extracted feature differences and one or more experimentally determined parameters, and a conversion module to convert the image according to the extracted feature differences, the experimentally determined parameters, and the hue range.

Abstract: A method and apparatus for image reproduction using output prediction is provided. The method includes converting color information of a first color space input to an image display device into color information of a second color space in which a sampled viewing environment of an output object by a printing device has been reflected; selecting a specific color distortion region according to a difference between an actual viewing environment and the sampled viewing environment of the converted second color space, and compensating a color component of the selected specific color distortion region; and converting corrected color information of the second color space which has been created through the compensation into corrected color information of the first color space, and outputting the corrected color information of the first color space through the image display device.

Abstract: Provided is a technology which can prevent deterioration of image quality when enhancing resolution of a predetermined key frame in a video sequence. Specifically, an apparatus to enhance resolution of a video frame is provided. The apparatus includes a frame extraction unit which extracts a key frame and one or more neighboring frames of the key frame from a video sequence; an upsampling unit which upsamples the key frame and the neighboring frames; a motion-vector search unit which calculates a motion vector of the upsampled key frame using the upsampled neighboring frames as reference frames; and a key-frame estimation unit which enhances quality of the upsampled key frame using temporal information obtained from the motion vector and spatial information in the key frame.

Abstract: An apparatus and method for compensating an output image are provided. The apparatus includes an output image estimation module which estimates an output image for an original image using a lookup table (LUT) that maps one color space to another color space, an error detection module which detects an erroneous patch from the estimated output image, and an LUT compensation module which compensates the LUT based on the detected patch.

Abstract: Provided is an image-resolution-improvement apparatus and method which can increase the resolution of an input image at a high magnification to thereby obtain a high-quality final image. The apparatus includes a textured-region-detection unit to detect a texture region in an input image; and a final-image-generation unit to synthesize a first intermediate image and a second intermediate image, which are obtained by applying different interpolation techniques to the texture region and a non-texture region excluding the texture region and generating a final image.

Abstract: The present invention relates to an image processing method and apparatus. The image processing apparatus includes an image capturing unit generating a plurality of images at different visual points and a three-dimensional image processing unit extracting depth information using the plurality of images.

Abstract: A method and apparatus that outputs an optimally-converted image using predefined data and color characteristics. The method includes: receiving the color characteristics; converting the received color characteristics into a range of lightness; converting the range of lightness and the received color characteristics into a gamut of lightness and chroma to be represented by the printer; and adaptively outputting the image according to the converted range of lightness and the received color characteristics.

Abstract: A method and apparatus for dithering for multi-toning are provided. The apparatus includes a mask-pattern-generating unit that generates a mask pattern on R channel, G channel and B channel by selecting pattern values constituting the mask pattern on the channels based on randomly-determined seed values; a spatial-weight-determining unit that determines the weight for spatial dithering by using the pattern values and K-bit LSB data of the high-tone input image; and an output unit that outputs an M-bit image by applying the weight to M-bit input image data, exempting the K-bit LSB data, in a dithering apparatus for expressing an M+K bit high-tone input image in an M-bit low-tone output device.

Abstract: An apparatus and method for selectively outputting image frames are provided. The apparatus includes a main topic frame extractor which extracts a main topic frame, which expresses a main topic selected by a user, from continuous image frames; a composite image frame creator which extracts a key object to realize the main topic from the main topic frames, and estimates a background object with respect to the key object to create a composite image frame using the key object and the background object; a wide-angle image frame creator which creates a wide-angle image frame, which includes the composite image frame and an image frame having common information to the composite image frame, among the continuous image frames; an attractive region setting unit which sets an attractive region with respect to the wide-angle image frame; and an output unit which outputs the attractive region.

Abstract: Provided are an apparatus and method for generating an image using a multi-channel filter. More particularly, provided are an apparatus and method for generating an image using a multi-channel filter, wherein images input into a plurality of image sensors are allowed to pass through different filters, each of which includes a plurality of channels, and segmented images passed through the filters are combined to produce a desired image. The apparatus includes a filter unit including a plurality of filters having different patterns with respect to a plurality of image channels and filtering images input into the filters, an image sensing unit including a plurality of image sensors sensing images filtered through the plurality of the filters, an interpolation unit calculating image channel values of pixels of the sensed images, and an image combination unit assigning the calculated image channel values to corresponding pixel positions to generate a single desired image.

Abstract: A color image scanning system, method and medium that generates look-up tables for color data correction based on the type of printing paper and the kind of image on the printing papers, thereby improving color reproducibility upon scanning. A color image scanning system may include a storage unit to store look-up tables having correction values of first color data, obtained by scanning a first printing paper having a plurality of color patches, each of the look-up tables corresponding to a type of printing paper, and a final image generation unit to correct second color data, obtained by scanning a second printing paper, with reference to a look-up table of the look-up tables, the look-up table corresponding to the type of printing paper used by the second printing paper.

Abstract: A method and apparatus for adaptively filtering an input image are provided. The method includes dividing an input image into a plurality of color domains according to a distribution of colors in the input image, respectively calculating a plurality of filter coefficients for the color domains, and adaptively filtering the color domains using the respective filter coefficients. The apparatus includes a domain classification unit which divides an input image into a plurality of color domains according to a distribution of colors in the input image, a filter coefficient calculation unit which respectively calculates a plurality of filter coefficients for the color domains, and a filtering unit which respectively filters the color domains using the filter coefficients. Accordingly, it is possible to enhance picture quality by addressing the problem of limited texture representation capabilities of existing filtering methods and apparatuses especially for memory color domains.

Abstract: A gamut mapping apparatus includes a parameter calculating unit calculating parameters for segmenting a gamut of an output device using gamut information about first and second input color spaces; a gamut segmenting unit segmenting the gamut of the output device into a core gamut and a surround gamut using the parameters; and a gamut mapping unit performing gamut mapping on image data present into the first and second input color spaces to the core gamut and the surround gamut according to a predetermined mapping method. The gamut mapping apparatus and method enable accurate reproduction of image data having components having undergone total internal reflection falling outside the scRGB color space or high chroma components in the scRGB color space.

Abstract: A multi-focal camera apparatus and methods and mediums for generating a focus-free image and an autofocus image using the multi-focal camera apparatus are provided. The multi-focal camera apparatus includes a lens module which comprises a plurality of lenses that concentrate light incident thereupon, and an image-sensor module which comprises a plurality of sensing zones respectively corresponding to the lenses, and obtains a plurality of images by converting beams of light that transmit through the lenses into electrical signals using the sensing zones, wherein the lenses have the same optical properties and are different distances apart from the respective sensing zones.

Abstract: An apparatus and method for image-based 3D photorealistic head modeling are provided. The method for creating a 3D photorealistic head model includes: detecting frontal and profile features in input frontal and profile images; generating a 3D head model by fitting a 3D genetic model using the detected facial features; generating a realistic texture from the input frontal and profile images; and mapping the texture onto the 3D head model. In the apparatus and method, data obtained using a relatively cheap device, such as a digital camera, can be processed in an automated manner, and satisfactory results can be obtained even from imperfect input data. In other words, facial features can be extracted in an automated manner, and a robust “human-quality” face analysis algorithm is used.

Abstract: An apparatus and method for editing an optimized color preference are provided. The apparatus includes a color information controlling unit which extracts data about a preference by comparing color information of a transformed image generated by transforming color information of an original image and the original image according to a user preference; a learning unit which teaches a neural network about the preference, based on the extracted data, and predicts color information variation by the neural network; and an image correcting unit which corrects color information of an input image according to the predicted color information variation. The method includes extracting data about a preference; teaching a neural network about the preference, based on the extracted data; predicting color information variation by the neural network; and correcting color information of an input image according to the predicted color information variation.

Abstract: An apparatus and method are provided for converting a preference color, in which the color space of a preference color selected by a user is divided into a plurality of sub-regions according to color distribution characteristics, and the colors of the respective regions of an input image corresponding to the user's preference color are converted into colors of proper sub-regions among the plurality of sub-regions.