Abstract: A method and apparatus with image processing are disclosed. The method includes determining a real part image, an imaginary part image, and an offset image based on input images that are dependent on infrared rays of different phases, removing noise from each of the real part image and the imaginary part image using the offset image as a noise removal guide, and generating a depth image based on an improved real part image and an improved imaginary part image corresponding to respective results of the removing.

Abstract: A method and apparatus with image processing are disclosed. The method includes determining a real part image, an imaginary part image, and an offset image based on input images that are dependent on infrared rays of different phases, removing noise from each of the real part image and the imaginary part image using the offset image as a noise removal guide, and generating a depth image based on an improved real part image and an improved imaginary part image corresponding to respective results of the removing.

Abstract: An image processing method includes: determining a source transmission map based on a dark channel map of an input image; determining transformed transmission maps by applying different filters to the determined source transmission map; generating haze-free images by removing haze from the input image based respectively on the determined transformed transmission maps; and generating an output image by blending the generated haze-free images.

Abstract: An image processing method acquires an image, restores a saturated region in which a pixel in the image has a first reference value based on a first illuminance component of the image, enhances a dark region in which a value of a pixel in the image is less than a second reference value based on the restored saturated region and the first illuminance component, and outputs a dark region-enhanced image.

Abstract: An image processing method includes: determining a source transmission map based on a dark channel map of an input image; determining transformed transmission maps by applying different filters to the determined source transmission map; generating haze-free images by removing haze from the input image based respectively on the determined transformed transmission maps; and generating an output image by blending the generated haze-free images.

Abstract: An image processing method acquires an image, restores a saturated region in which a pixel in the image has a first reference value based on a first illuminance component of the image, enhances a dark region in which a value of a pixel in the image is less than a second reference value based on the restored saturated region and the first illuminance component, and outputs a dark region-enhanced image.

Abstract: An image recovery apparatus and method are provided, where the image recovery apparatus calculates a reference color image based on a linear correlation between a color channel image and a luminance channel image, and corrects the luminance channel image based on residual information that indicates a difference between the reference color image and the color channel image, to recover an image.

Abstract: An image recovery apparatus and method are provided, where the image recovery apparatus calculates a reference color image based on a linear correlation between a color channel image and a luminance channel image, and corrects the luminance channel image based on residual information that indicates a difference between the reference color image and the color channel image, to recover an image.

Abstract: Provided is an image processing apparatus that can effectively display an image by using an optimized dynamic range compression technique and a method of processing an image by using the same. The method includes: obtaining a first blurred image and a second blurred image from the input image; estimating illuminance of the input image by combining the first blurred image and the second blurred image; generating a dark region amplified image from the input image; generating a bright region conserved image from the input image; applying weights to the dark region amplified image and the bright region conserved image, respectively, according to the estimated illuminance; and combining the weighted dark region amplified image and the weighted bright region conserved image to generate a final image.

Abstract: A camera system with a multi-spectral filter array and an image processing method thereof are disclosed. The method of processing an image that is output from an image sensor including a multi-spectral filter array including a color filter and a near infrared (NIR) filter includes interpolating an NIR channel of the image by using spatial information of color channels including a red channel, a green channel, and a blue channel; and interpolating the color channels of the image by using spatial information of the NIR channel.

Abstract: A method of processing an image includes: offsetting aliasing by analyzing frequency characteristics of at least one color channel and a NIR channel, of a MSFA pattern image; generating a high resolution base image; and offsetting an artifact from the high resolution base image by weighting the high resolution base image and a blur image, based on a pixel difference value between the blur image and the high resolution base image.

Abstract: Provided are a method and apparatus for canceling chromatic aberration. In the method, only chrominance signals are filtered using an asymmetrical mask according to the characteristics of chromatic aberration occurring from among a luminance/chrominance coordinates system. Accordingly, it is possible to cancel chromatic aberration regardless of the characteristics of a lens and prevent the resolution of the original image from degrading.

Abstract: Provided is a method and apparatus for restoring color of an input image. The method includes: separating multiple band information of a near infrared (NIR) channel from information of the input image by using a correlation between a color channel and the NIR channel in the input image; obtaining estimated invisible light band information of the NIR channel from the multiple band information of the NIR channel and estimated multiple band information of the NIR channel which is estimated from the color channel; estimating invisible light band information of the color channel based on the estimated invisible light band information of the NIR channel; and restoring a visible light band image of the color channel by removing the estimated invisible light band information of the color channel from multiple band information of the color channel included in the information of the input image.

Abstract: An image processing apparatus includes an adaptive interpolation device which converts a MFA pattern image into a quincuncial pattern image based on difference values, and interpolates color channels and an NIR channel, based on difference values of the converted quincuncial pattern image in vertical and horizontal pixel directions; a frequency compensation device which obtains a high-resolution MFA image using high-frequency and medium-frequency components of a high-resolution base image, based on linear regression analysis and compared energy levels of MFA channel images to an energy level of a base image; and a channel interference suppression device which removes color distortion generated between each channel of the high-resolution MFA image, and another channel of the high-resolution MFA image and a base channel using a weighted average of pixel value differences between each channel of the high-resolution MFA image, and the other channel of the high-resolution MFA image and the base channel.

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: A method and apparatus for reducing noise of a video image are provided. The method includes: reducing noise in a difference between a current frame and a previous frame in which temporal noise is reduced; detecting motion information about the current frame based on the difference in which the noise is reduced; reducing temporal noise in the current frame via a weighted sum of the current frame and the previous frame in which the temporal noise is reduced, according to the motion information; and reducing spatial noise in the current frame based on an edge direction of the current frame in which the temporal noise is reduced.

Abstract: A device and method of removing chromatic aberration which occurs in an image generated by capturing a target subject. The chromatic aberration removing device includes a chromatic aberration region detecting unit which detects a chromatic aberration occurrence region in an input image, a coefficient calculating unit which calculates a minimizing pixel value which minimizes a difference between sizes, numbers of pixels or intensities of edges of red, green, and blue (RGB) channels of the chromatic aberration occurrence region, a chroma signal processing unit which removes chromatic aberration in the chromatic aberration occurrence region, and a purple fringing removing unit which removes purple fringing.

Abstract: Provided is a method and apparatus for restoring color of an input image. The method includes: separating multiple band information of a near infrared (NIR) channel from information of the input image by using a correlation between a color channel and the NIR channel in the input image; obtaining estimated invisible light band information of the NIR channel from the multiple band information of the NIR channel and estimated multiple band information of the NIR channel which is estimated from the color channel; estimating invisible light band information of the color channel based on the estimated invisible light band information of the NIR channel; and restoring a visible light band image of the color channel by removing the estimated invisible light band information of the color channel from multiple band information of the color channel included in the information 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: Provided is an image processing apparatus that can effectively display an image by using an optimized dynamic range compression technique and a method of processing an image by using the same. The method includes: obtaining a first blurred image and a second blurred image from the input image; estimating illuminance of the input image by combining the first blurred image and the second blurred image; generating a dark region amplified image from the input image; generating a bright region conserved image from the input image; applying weights to the dark region amplified image and the bright region conserved image, respectively, according to the estimated illuminance; and combining the weighted dark region amplified image and the weighted bright region conserved image to generate a final image.