Abstract: An apparatus, a method and a non-transitory computer-readable recording medium for detecting a moving object using a depth map is provided. The apparatus includes a segment image generator unit that generates a segment image to distinguish each object using a depth image of a current input frame; a background image generator unit that generates a current background image by applying a moving average method to the depth image and a background image of a previous input frame; and a moving mask generator unit that generates a moving mask by comparing the depth image with the current background image to thereby find moving parts in the depth image.

Abstract: A color interpolation apparatus includes a threshold value determining unit that calculates a luminance value of each area set based on each pixel of a Bayer pattern image and determines edge determining threshold values, an edge information calculating unit that calculates pixel value variations in multiple directions of the set areas by using pixel values of pixels included in each area and edge information regarding each area by using the multiple directional pixel value variations, an area determining unit that determines an edge type by using the edge determining threshold values and the edge information, and a color interpolation unit that applies a color interpolation filter previously set according to the edge type to a corresponding area according to the edge type. The area determining unit uses green information or interpolated green information of a central pixel depending on whether or not a color of the central pixel is green.

Abstract: An apparatus, a method and a non-transitory computer-readable recording medium for detecting a moving object using a depth map is provided. The apparatus includes a segment image generator unit that generates a segment image to distinguish each object using a depth image of a current input frame; a background image generator unit that generates a current background image by applying a moving average method to the depth image and a background image of a previous input frame; and a moving mask generator unit that generates a moving mask by comparing the depth image with the current background image to thereby find moving parts in the depth image.

Abstract: There are provided an apparatus and a method for estimating edge areas of pixels in a digital image to thereby prevent an edge sharpening algorithm from being applied to non-edge area of the digital image. Therefore, the apparatus can accurately determine whether each pixel is in an edge area or in a non-edge area, by generating a binary mask obtained by using a luminance difference average between each pixel and each of neighboring pixels in the digital image. Moreover, the determination of an edge-area or a non-edge area may be applied to various digital images, by adjusting a level of edge-area determination.

Abstract: An apparatus for enhancing the visibility of color images includes: a luminance value cumulative distribution calculator that calculates a cumulative distribution function of the number of pixels from a minimum value of luminance values; a baseband signal determining unit that determines baseband signal pixels having luminance values smaller than a threshold level; a luminance compensation value generator that generates luminance compensation values to apply the lower-level luminance compensation values as the pixels have higher-level luminance values, for the pixels having the luminance values larger than the threshold level; a luminance gain generator that determines a luminance gain applied to the luminance compensation values according to a mean luminance values of the input images and the level of the luminance values of the pixels to which the luminance compensation values are applied; and a luminance value enhancing unit that summing the luminance compensation values including the gain with the luminan

Abstract: An apparatus for auto white balance includes a histogram generation unit writing respective histograms of Cb values and Cr values with regard to pixels included in an input image frame, a single-tone determination unit comparing respective maximum values of the histograms of Cb values and Cr values with a first threshold value, and determining the input image frame as a single-tone image if at least one of the maximum values is higher than the first threshold value, and an auto white balance gain computation unit computing and an auto white balance gain by using color information of an input image frame and outputting the computed auto white balance gain, wherein if the input image frame is determined to be a single-tone image, the auto white balance gain computation unit outputs an auto white balance gain computed with respect to a previous input image frame.

Abstract: There is provided an apparatus for improving the sharpness of an image, which may prevent occurrence of distortion of an image in an edge enhancement process of the image by applying an active weight in accordance with a two-dimensional (2D) high pass filtering value of the image. The apparatus may include: a 2D high pass filter outputting a high frequency element value for the luminance values of pixels of an input image; a weight generating unit generating a weight changed depending on a magnitude of the high frequency element value; a weight applying unit applying the weight to the high frequency element value; and an edge enhancement image generating unit adding, to the luminance values of the pixels of the input image, the high frequency element value to which the weight is applied to thereby output an image of which an edge is enhanced.

Abstract: An apparatus and method for removing red-eye in a 2D image, which can remove red-eye more naturally and apply a gain for a real-time correction on input pixels by differently performing a correction degree according to positions of pixels included in red-eye.

Abstract: An apparatus and method for removing red-eye in a 2D image, which can remove red-eye more naturally and apply a gain for a real-time correction on input pixels by differently performing a correction degree according to positions of pixels included in red-eye.

Abstract: A Two-Dimensional (2D) image segmentation apparatus for segmenting pixels of a progressive input 2D image includes a group information storing unit storing information of pixel groups including a plurality of adjacent pixels; a pixel determining unit determining coordinates of an input pixel, and determining whether the input pixel is an effective pixel for segmentation; a group scanning unit scanning a adjacent pixel group disposed in a scan range preset from the effective pixel in the group storing unit when the input pixel is determined as the effective pixel by the pixel determining unit; and a group information updating unit updating information of a pixel group stored in the group information storing unit according to whether there is the scanned adjacent pixel group and a pixel group including an input pixel preceding the effective pixel. Moreover, a method is provided that removes red-eye using area information of a pixel group determined by the segmentation apparatus.

Abstract: There is provided a method of grouping pixels in a 2D digital image that assigns labels to regions of objects to differentiate between objects separated in the input image and groups a region of an object having the same label into one group when pattern recognition and image process are performed on the 2D digital image. A method of grouping pixels in a 2d digital image according to an aspect of the invention may include: determining whether a target pixel in an input image is included in a labeling section; determining whether the target pixel is connected to a previous pixel of the target pixel and an upper pixel located adjacent to and above the target pixel to perform a labeling process, and renewing a label table while saving a labeling result in a line memory when the target pixel is included in the labeling section and is a valid pixel including object information; and grouping pixels of the input image using the labeling result and the renewed label table, and renewing a group.

Abstract: There is provided an apparatus for removing color noise including: a color interpolation unit performing color interpolation on a bayer pattern image output from an image sensor; a high-pass filter unit performing high-pass filtering on each of the pixels of the bayer pattern image to generate high-pass filtered values of each of the pixels; a high frequency region determining unit comparing pixel values of a target pixel, from which color noise is removed, and pixels adjacent to the target pixel with the high-pass filtered values to determine whether the target pixel is included in a high frequency region; and a color noise region determining unit using differences between color values of the target pixel interpolated by the color interpolation unit and determining whether the target pixel is included in a color noise region when it is determined that the target pixel is included in the high frequency region.

Abstract: Provided are an apparatus for removing ringing noise and an apparatus for removing noise. The apparatuses includes a representative value setting block dividing pixel data in one block including a plurality of pixel data into two groups through a K-means algorithm and setting a representative value in each of the groups; a parameter generator block calculating intervals and approaches between all the pixel data in the block and a pair of the representative values; and a correction block correcting an inputted pixel data value using the intervals and the approaches.

Abstract: Provided is an apparatus for improving the sharpness of an image. The apparatus includes an edge detector, an effective edge judging unit, an effective edge classifying unit, an isolated edge judging unit, and a 2-D HPF applying unit. The edge detector calculates an edge value using brightness relation with neighboring pixels with respect to each of pixels of an input image. The effective edge judging unit determines effective edge pixels. The effective edge classifying unit determines weak edge pixels and strong edge pixels. The isolated edge judging unit judges an isolated edge pixel included in an isolated edge. The 2-D HPF applying unit applies a first 2-D HPF to the weak edge pixels, and applies a second 2-D HPF to the strong edge pixels to generate edge strengthening values. The edge strengthening value applying unit adds the edge strengthening values to brightness values of the respective pixels of the input image.

Abstract: An apparatus and method for controlling auto exposure (AE) that is used in digital imaging devices. The apparatus controlling the luminance of an image being outputted from an image sensor by controlling exposure time and analog gain of the image sensor includes: a luminance operation unit operating and outputting a mean luminance of the image outputted from the image sensor; a shutter index determination unit comparing a predetermined target luminance with the mean luminance of the outputted image and determining a shutter index in different manners according to the magnitude of the difference between the target luminance and the mean luminance of the outputted image; and an exposure time/analog gain determination unit generating exposure time and analog gain corresponding to the shutter index determined in the shutter index determination unit and applying the generated exposure time and analog gain to the image sensor.

Abstract: There are provided an apparatus and a method for estimating edge areas of pixels in a digital image to thereby prevent an edge sharpening algorithm from being applied to non-edge area of the digital image. Therefore, the apparatus can accurately determine whether each pixel is in an edge area or in a non-edge area, by generating a binary mask obtained by using a luminance difference average between each pixel and each of neighboring pixels in the digital image. Moreover, the determination of an edge-area or a non-edge area may be applied to various digital images, by adjusting a level of edge-area determination.

Abstract: There is provided an apparatus for improving the sharpness of an image, which may prevent occurrence of distortion of an image in an edge enhancement process of the image by applying an active weight in accordance with a two-dimensional (2D) high pass filtering value of the image. The apparatus may include: a 2D high pass filter outputting a high frequency element value for the luminance values of pixels of an input image; a weight generating unit generating a weight changed depending on a magnitude of the high frequency element value; a weight applying unit applying the weight to the high frequency element value; and an edge enhancement image generating unit adding, to the luminance values of the pixels of the input image, the high frequency element value to which the weight is applied to thereby output an image of which an edge is enhanced.

Abstract: There is provided a method of performing auto white balance including: setting a plurality of sections of a whole range of a value of each of Y, Cb, and Cr in the YCbCr color space, according to a size of each value; calculating an accumulated Y, Cb, and Cr value of pixels included in each of the plurality of sections; determining effective sections according to the number of the pixels included in each of the plurality of sections; calculating a mean Y, Cb, and Cr value of pixels included in all of the effective sections by using the accumulated Y, Cb, and Cr value of each of the effective sections; calculating a mean RGB value by converting the mean Y, Cb, and Cr value into an RGB color space; and determining an RGB color gain of a Bayer image outputted from an image sensor by using the mean RGB value.

Abstract: An apparatus for enhancing the visibility of color images includes: a luminance value cumulative distribution calculator that calculates a cumulative distribution function of the number of pixels from a minimum value of luminance values; a baseband signal determining unit that determines baseband signal pixels having luminance values smaller than a threshold level; a luminance compensation value generator that generates luminance compensation values to apply the lower-level luminance compensation values as the pixels have higher-level luminance values, for the pixels having the luminance values larger than the threshold level; a luminance gain generator that determines a luminance gain applied to the luminance compensation values according to a mean luminance values of the input images and the level of the luminance values of the pixels to which the luminance compensation values are applied; and a luminance value enhancing unit that summing the luminance compensation values including the gain with the luminan

Abstract: An apparatus for auto white balance includes a histogram generation unit writing respective histograms of Cb values and Cr values with regard to pixels included in an input image frame, a single-tone determination unit comparing respective maximum values of the histograms of Cb values and Cr values with a first threshold value, and determining the input image frame as a single-tone image if at least one of the maximum values is higher than the first threshold value, and an auto white balance gain computation unit computing and an auto white balance gain by using color information of an input image frame and outputting the computed auto white balance gain, wherein if the input image frame is determined to be a single-tone image, the auto white balance gain computation unit outputs an auto white balance gain computed with respect to a previous input image frame.