Abstract: Provided are a method and apparatus for recognizing a plurality of faces. In the method, a plurality of faces are detected from received video frames, the detected faces are sequentially recognized in predetermined frames that fall within a predetermined recognition period from among the detected frames, and then, the recognized faces are sequentially displayed. Accordingly, the amount of calculation is less than when simultaneously performing face detection and recognition on each frame.

Abstract: An apparatus and method for digital auto-focus are provided. The apparatus includes a local block generator generating a local block from an input image, a distance-estimation unit estimating distances of each image of the local block, a focal-distance-setting unit setting one of the estimated distances of the local block image as a focal distance of the input image, a reblurred-image generator generating a reblurred image from the local block image, a reconstructed image generator generating an in-focus image focused to the estimated distances from the local block image, a local-block-image-matching unit matching the reblurred image to the in-focus image with different weight values based on the set focal distance, and a final-image generator generating a final image by summing the matched local block images.

Abstract: Provided are a method and apparatus for determining whether backlight exists. The method according to an embodiment of the present invention includes calculating scattering degrees of luminance values of pixels included in each of images which represent the same photographic subject and have different brightness levels from each other; and determining whether backlight exists on the photographic subject in consideration of the calculated scattering degrees.

Abstract: A method, medium, and apparatus for setting an exposure time is provided. The apparatus includes a section setting module which sets one or more luminance sections based on a luminance distribution of an input image, an image division module which divides the input image into two or more regions, a region classification module which classifies the regions into the luminance sections, and an exposure-time setting module which sets an exposure time for each of the regions with reference to a target luminance value, the target luminance value being set based on the results of the classification performed by the region classification module.

Abstract: A noise-reduction method and apparatus are provided. The noise-reduction method includes estimating activity levels of regions in an input image; and applying different weights to a large noise filter kernel and a small noise filter kernel according to the estimated activity levels, wherein the estimating includes calculating a noise level of the input image, generating a binary image by calculating signal-to-noise ratios (SNRs) of pixels of the input image and by comparing the SNRs of the pixels of the input image with a predefined threshold, and reducing binary data boundaries in the binary image.

Abstract: Provided is an image restoration method and apparatus, in which an image is restored by estimating the blur level of the image. The image restoration apparatus includes a block generation module which generates a plurality of overlapping blocks for an input image; a blur estimation module which generates a plurality of unit step responses for a current overlapping block from the overlapping blocks; a feature-map generation module which generates a feature map for the current overlapping block based on the unit step responses of the current overlapping block; and a filter application module which deblurs the current overlapping block by using a deconvolution filter to filter the feature map of the current overlapping block.

Abstract: An image-registration method, medium, and apparatus obtaining first and second images, generating first and second image pyramids based on the first and second images, respectively, by performing sub-sampling which reduces the length and width of each of the first and second images by half, and determining one of five directions as an optimal movement direction for a current level of the first and second image pyramids based on two images belonging to a corresponding level, updating a motion vector for the current level based on the optimal movement direction for the current level and updating a first image belonging to a level directly below the current level based on the updated motion vector for the current level, wherein the updating comprises updating a motion vector for each of a plurality of levels of the first and second image pyramids in an order from an uppermost level to a lowermost level.

Abstract: A system and method of correcting a light pathway is provided. A system for correcting a light pathway, the system including: a light pathway change amount measurement unit to measure a light pathway change amount using a movement amount of an image when a light pathway of incident light is changed due to shaking of a camera; and a curved prism driving unit to drive a curved prism, composed of a refraction surface, based on a light pathway correction amount determined by the light pathway change amount.

Abstract: A method and apparatus for restoring an image. The method includes extracting predetermined channels from image data including a plurality of channels; and restoring the extracted channels using a first filter.

Abstract: An apparatus and method for restoring an image are provided. The apparatus includes an edge-strength-detection module which detects an R-channel edge strength, a G-channel edge strength and a B-channel edge strength from an input image and generates an R-channel edge map, a G-channel edge map and a B-channel edge map based on the R-channel edge strength, the G-channel edge strength and the B-channel edge strength; an edge-strength-compensation module which compensates for the R-channel edge strength and the B-channel edge strength based on the G-channel edge strength; a valid-value-generation module which generates a valid value indicating a blur level based on the compensated R-channel edge strength and the compensated B-channel edge strength; a point spread function (PSF) estimation module which estimates a PSF corresponding to the valid value; and an image-restoration module which restores the input image using the PSF.

Abstract: An apparatus and method of capturing images having an optimized quality during night time conditions is provided. The apparatus for capturing images includes an image-capturing unit that captures an light from an object and generates a first digital image, a night-scene-sensing unit sensing whether the first digital image is a night-scene image, an exposure-adjustment unit adjusting an optimized exposure time by comparing an edge level of the night-scene image with that of a pre-generated reference image if it is sensed that the input image is the night-scene image, and a controller controlling the image-capturing unit to generate a second digital image based on the adjusted exposure time.

Abstract: Provided are a method and apparatus for correcting chromatic aberration of an image, the method and apparatus used in an image processing apparatus for an image pickup device or a display image processing apparatus. The chromatic aberration correction apparatus includes a chromatic aberration region sensing unit analyzing a luminance signal of an input image and sensing a region having chromatic aberration; a color gradient calculation unit calculating a first weight, which indicates a degree of chromatic aberration, based on a difference between gradients of color components of the input image; a luminance gradient calculation unit calculating a second weight, which indicates the degree of chromatic aberration, based on gradients of luminance components of the input image; and a chrominance correction unit correcting chrominance of a pixel of the input image, which is included in the sensed region, based on a value obtained by multiplying the first weight by the second weight.

Abstract: A CMOS (Complementary Metal-Oxide Semiconductor) image sensor is provided. A CMOS image sensor includes a first light-receiving unit converting light into charge, a first floating diffusion region, in which a first potential corresponding to the converted amount of charge is generated and a second floating diffusion region, to which the charge in the first floating diffusion region is transmitted, and in which a second potential is generated, wherein a wide dynamic range signal is acquired from the first floating diffusion region, a high-sensitively signal is acquired from the second floating diffusion region, and the acquired signals are synthesized and output.

Abstract: An object-oriented photographing control method, medium, and apparatus. The object-oriented photographing control method includes detecting an interesting object registered in advance from an input image, estimating photographic information on the detected interesting object, and generating control information for capturing the input image by using the estimated photographing information, and capturing the input image according to the control information. Accordingly, states of a position and illuminance of the object are perceived in real-time, a high-quality image can be captured, and the user does not need to control the focus and the exposure of the input image.

Abstract: An apparatus, method, and medium for generating an image is provided. The apparatus includes an optical module, a filter module which includes a wide-band filter area that allows transmission of optical signals within a wavelength band corresponding to a color of a predetermined color, a narrow-band filter area that allows transmission of optical signals within a wavelength band corresponding to the predetermined color, and an all-pass filter area that allows transmission of optical signals in all wavelength bands, and an image generation module which generates an image by processing optical signals that transmit through the filter module, wherein the image generation module applies different weights to optical signals according to which of the wide-band filter area, the narrow-band filter area, and the all-pass filter area the optical signals respectively transmit through.

Abstract: Provided is an apparatus and method for enhancing an image by optimizing exposure and grayscale. The apparatus includes a component-extracting unit separating luminance signals and color signals from input image signals; a luminance-enhancing unit enhancing the luminance of the luminance signals; and a contrast-enhancing unit dividing the luminance signal having the enhanced luminance into one or more local areas, and enhancing the contrast of the luminance signal having the enhanced luminance for each local area.

Abstract: Provided are a noise reduction apparatus having an edge enhancement function and a method thereof, in which edges in an input image can be prevented from being blurred when reducing noise in the input image and a clear output image can be obtained by reducing edge discontinuities. The noise reduction apparatus includes a window setting module which sets a portion of an input image as a window, an edge-information detection module which detects edge information regarding the window, an image processing module which performs an image processing operation on the window, and an output-image generation module which generates an output image by reflecting the edge information into one or more windows obtained by the image processing operation.

Abstract: An image photographing apparatus and method, and more particularly, an image photographing apparatus and method that may divide each unit sensor of an image sensor into a high-sensitivity sensor and a low-sensitivity sensor and sense an incident optical signal using the high-sensitivity sensor and the low-sensitivity sensor. The image photographing apparatus may include a light reception unit receiving an optical signal, a sensor unit sensing the optical signal, which is incident to a pixel region, using a plurality of sensors with different sensitivity and converting the sensed optical signal into a plurality of electrical signals, and a signal extraction unit extracting the quantity of accumulated electric charge for the optical signal, which was sensed by each of the sensors, with reference to each of the electrical signals.

Abstract: A method and an apparatus enhance a local luminance of an image, and a computer-readable recording medium stores a computer program that enhances a local luminance of an image. The method includes: selecting a local area with a luminance to be compensated for from a luminance space, the luminance space representing a luminance of the input image; and compensating for the luminance of the selected local area.

Abstract: A method and apparatus for generating an image is provided. The method includes acquiring a plurality of images using different exposure amounts, white-balancing each of the raw images, and synthesizing the white-balanced images producing as a result an absolute HDR image.