Abstract: Provided is an apparatus, method and computer-readable medium removing noise of an image. The apparatus may include a channel image correction unit to correct remaining channel images excluding a currently processed channel image, from among a plurality of channel images, using the currently processed channel image, a noise removal unit to remove noise of the currently processed channel image, using the corrected remaining channel images and the currently processed channel image, and a color image reconstruction unit to reconstruct a color image in which noise is removed, by combining the plurality of channel images in which noise is removed when the noise of the plurality of channel images is removed.

Abstract: An image processing apparatus is provided. The image processing apparatus for image signal processor (ISP) realization may include a Static Random Access Memory (SRAM) for each function module. A unified SRAM to store at least one line data of an input image for each of a plurality of functions modules within the image processing apparatus is further provided.

Abstract: Provided are an image processing method and apparatus capable of improving the result of segmenting an image and discriminatively determining the extent of processing the image. In the method, the extent of segmentation of the image is calculated; the result of segmentation is compensated for and the extent of processing the image is determined, based on the calculated extent of segmentation; and each region of the image is discriminatively processed according to the determined extent of processing. Accordingly, it is possible to improve the precision of the result of segmentation and continuously control the extent of discriminative processing around a complex image object.

Abstract: A method of controlling an application using a motion of an image pickup unit, the method includes storing gestures corresponding to a command to control an application, tracing a motion parameter corresponding to an image that is continuously input, detecting a gesture corresponding to the traced motion parameter from the stored gestures, and outputting a control signal of a command corresponding to the detected gesture.

Abstract: Provided is an image interpolation method and apparatus using a reference block depending on a direction. The image interpolation method may generate a horizontal reference block and a vertical reference block each with respect to an inputted image, and determine interpolation directivity with respect to the inputted image using the generated horizontal reference block and vertical reference block, thereby performing an interpolation on an image based on accurate interpolation directivity. In particular, the image interpolation method may determine whether to verify interpolation directivity depending on an edge intensity of an inputted image, thereby performing a color filter array (CFA) interpolation on an image based on an edge direction without determining the interpolation directivity, when the edge intensity is strong.

Abstract: Provided is an apparatus and method of determining a dynamic range extended mode for a digital camera using a fuzzy rule. The method may determine a feature value with respect to a preview image in accordance with a predetermined measurement criterion, and may determine a dynamic range extended mode using a fuzzy rule where the determined feature value is matched in the fuzzy rule, thereby intelligently controlling a photographing mode of the digital camera. In particular, the method may determine the feature value with respect to the preview image in accordance with various measurement criterions, thereby obtaining an optimum photographing mode for subsequent images.

Abstract: Provided is a multi-exposure controlling method and apparatus. An exposure control unit may set an initial exposure time based on a comparison result between a predetermined brightness confidence interval and an average high brightness that is calculated based on at least one current histogram. A comparison unit may compare the brightness confidence interval and an average low brightness that is calculated based on a subsequent histogram obtained by photographing a subject using the set initial exposure time. The exposure control unit may change the initial exposure time based on a comparison result of the comparison unit.

Abstract: An image processing method and apparatus is provided, with which a size of a filter window may be decreased by determining an edge direction of each of the pixels constituting an image and by vertically applying an anisotropic filter window to the determined edge direction.

Abstract: An automatic white balance adjusting apparatus and method based on detection of an effective area. The automatic white balance adjusting apparatus may detect the effective area by using a color temperature, a luminance, and a correlation, and may adjust a white balance with respect to the detected effective area.

Abstract: Provided are an image signal processing apparatus and method. According to the image signal processing method, by simultaneously performing in an integrated manner image denoising and interpolation using 4-directional image gradient information which defines differences in color brightness between adjacent pixels on the basis of edge direction information obtained from a bayer image output from an image sensor, it is possible to improve picture quality and processing speed.

Abstract: An apparatus and method for auto white balance adjusting using an effective area. The auto white balance adjusting apparatus may extract a grey area from an input image, and select an effective area from the grey area according to color temperature and luminance, thereby performing white balance using the effective area. The auto white balance adjusting apparatus may perform white balance of the input image using image information of the effective area which is a more precise grey area, thereby improving the white balance.

Abstract: A color reproduction apparatus may include a white balance performing unit to perform white balance with respect to an image obtained from a sensor using a white balance gain, an image restoring unit to restore an RGB image from the white-balanced image by interpolating a color filter array image, a first color corrector to correct a color distortion caused by a light source by applying first correction data, and a second color corrector to correct a color distortion caused by a characteristic of a sensor by applying second correction data.

Abstract: An image enhancement apparatus and method based on luminance information of a pixel. The image enhancement apparatus may determine luminance data of each of a plurality of pixels, and may adaptively determine a conversion ratio according to the luminance data to apply the conversion ratio to an input image, thereby performing image-enhancing. The image enhancement apparatus may adaptively converse the input image according to luminance data, thereby precisely and effectively performing image-enhancing.

Abstract: Disclosed are an auto exposure system and a method thereof. The auto exposure system may check whether an exposure target value is correct using brightness information of an input image. When the exposure target value is not proper, the auto exposure system may readjust the exposure target value through analyzing the brightness information of the input image. Also, the auto exposure system may correct exposure of the input image based on an exposure correction value according to the adjusted exposure target value, thereby adjusting the exposure of the input image to be proper. Also, exposure information of the input image may be easily obtained from a final exposure target value.

Abstract: An image signal processing method. A first coefficient indicating a probability that a first pixel of an input image is an edge may be calculated. A first edge enhanced signal where an edge of the input image is enhanced may be multiplied with the first coefficient, and a first low-pass filtered signal where the input image is low-pass filtered may be multiplied with a second coefficient indicating a probability that the first pixel is not an edge. The two calculated values may be added, and thus an edge enhanced signal may be generated.

Abstract: Provided are an image signal processing apparatus and method. According to the image signal processing method, by simultaneously performing in an integrated manner image denoising and interpolation using 4-directional image gradient information which defines differences in color brightness between adjacent pixels on the basis of edge direction information obtained from a bayer image output from an image sensor, it is possible to improve picture quality and processing speed.

Abstract: Provided are a method and apparatus for simultaneously reducing various kinds of noises in an image output from an image sensor equipped to a camera. The image noise reducing method includes: determining a color reference value, which corresponds to a corrected value of the color value of a current pixel, based on the difference values between the color value of the current pixel among pixels of an image and the color values of neighboring pixels around the current pixel; determining unified filter kernel coefficients, which represent the weights of the current pixel and the neighboring pixels, based on the similarities between the determined color reference value and the color values of the neighboring pixels; and reducing a noise in the color value of the current pixel by weighted-averaging the color value of the current pixel and the color values of the neighboring pixels using the unified filter kernel coefficients.

Abstract: An object pose normalization method and apparatus and an object recognition method are provided. The object pose normalization method includes: determining a pose of a non-frontal image of an object; performing smoothing transformation on the non-frontal image of the object, thereby generating a smoothed object image; and synthesizing a frontal image of the object by using the pose determination result and the smoothed object image. According to the method and apparatus, a front object image can be synthesized by using a non-frontal object image without causing an image distortion problem due to self-occlusion and non-rigid deformation.

Abstract: Provided are a method and apparatus for extracting facial features from an image containing a face. The method and apparatus filter an input image using a filter set for face recognition at each of predetermined locations in the input image, merge values obtained by filtering the input image at locations, which are horizontally symmetrical to each other with respect to the center of the face, and synthesize values obtained by filtering the input image at locations which are not symmetrical to each other with respect to the center of the face with the merged values. Therefore, the time, feature values, and storage space required to extract or compare facial features can be significantly reduced. In addition, a face recognition system that runs well on low specification hardware can be implemented.

Abstract: Object feature points are tracked in a video image, and detected feature points are affine-transformed. Then, it is determined whether the video image is a real object using characteristics of the affine-transformed feature points. Therefore, liveness detection resistant to spoofing can be performed without requiring user intervention and additional hardware.