Abstract: Provided is an apparatus and method for generating a three-dimensional (3D) panoramic image using a single camera. The image processing apparatus may generate a two-dimensional (2D) reference panoramic image using a central area of each of a plurality of input image frames, and may extract a left-eye strip and a right-eye strip of when a similarity calculated in the plurality of input image frames based on the 2D reference panoramic image has a maximum value.

Abstract: Provided is an apparatus and method for extracting feature information of an image using a scale-invariant feature transform (SIFT) algorithm. The apparatus may include a first interface configured to generate one or more tile images from a first source image stored in a particular memory, such as a high-capacity short-term memory, and a feature information extractor configured to receive the generated one or more tile images and to respectively extract feature information from each of the one or more input tile images, where the first interface may be configured to generate the one or more tile images by selectively dividing the first source image into the one or more tile images based on a horizontal resolution of the first source image.

Abstract: An apparatus and method for calculating a cumulative histogram of an image are provided. A cumulative histogram calculation apparatus may include a cumulative value selecting unit to select cumulative data obtained by accumulating input data, based on a number of combinations of the input data, and a loading unit to load the selected cumulative value in a corresponding bin of a histogram.

Abstract: Apparatus and method for correcting a tone of a panoramic image. An image processing apparatus may acquire, from an overlapping region of a left image and a right image, ghost information based on an optimal threshold and a cost map in which a similarity between the left image and the right image is reflected, may generate a tone correction map based on a global tone correction function generated using the ghost information in the overlapping region, and based on a local tone correction level generated using local information of an optimal seam, and may correct the left image and the right image using a final tone correction map generated by applying, to the tone correction map, a weighting based on the left image and a weighting based on the right image.

Abstract: A transaction splitting apparatus and method are provided in which neighboring sub-transactions accessing a predetermined bank in each memory may access different banks. The transaction splitting apparatus includes a first processing unit to split a transaction into at least one sub-transaction, the transaction accessing a first bank among a plurality of banks comprised in a memory, and a second processing unit to translate an address of the at least one sub-transaction, to interleave the at least one sub-transaction using the plurality of banks.

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: A method of processing frames obtained by multiple exposures may include categorizing, by at least one processor, a plurality of frames captured by multiple exposures into one of a reference frame and a target frame, compensating for global motion resulting from motion of a capturing apparatus capturing an object, and compensating for local motion resulting from motion of the object, based on a joint histogram between the reference frame and the target frame.

Abstract: An apparatus and method creating a ghost-free High Dynamic Range Image (HDRI) based on filtering are provided. It is possible to effectively prevent a ghost phenomenon from occurring when a single HDRI is created from a plurality of LDRIs, by defining a ghost area using a probability based on a global transfer function indicating a relationship for intensities of several frames, rather than searching for or identifying a ghost area in a single or each image.

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 apparatus and method for calculating a cumulative histogram of an image are provided. A cumulative histogram calculation apparatus may include a cumulative value selecting unit to select cumulative data obtained by accumulating input data, based on a number of combinations of the input data, and a loading unit to load the selected cumulative value in a corresponding bin of a histogram.

Abstract: Provided is an apparatus and method for extracting feature information of an image using a scale-invariant feature transform (SIFT) algorithm. The apparatus may include a first interface configured to generate one or more tile images from a first source image stored in a particular memory, such as a high-capacity short-term memory, and a feature information extractor configured to receive the generated one or more tile images and to respectively extract feature information from each of the one or more input tile images, where the first interface may be configured to generate the one or more tile images by selectively dividing the first source image into the one or more tile images based on a horizontal resolution of the first source image.

Abstract: Provided is an apparatus and method for generating a three-dimensional (3D) panoramic image using a single camera. The image processing apparatus may generate a two-dimensional (2D) reference panoramic image using a central area of each of a plurality of input image frames, and may extract a left-eye strip and a right-eye strip of when a similarity calculated in the plurality of input image frames based on the 2D reference panoramic image has a maximum value.

Abstract: An apparatus and method of generating a three-dimensional (3D) panoramic image, using a single camera. The apparatus may include a frame slit capturing unit to capture a first frame slit in an Nth video frame, and to capture a second frame slit from an (N+2)th video frame, and a 3D image generating unit to generate a left image using the captured first frame slit and the captured second frame slit. Here, the frame slit capturing unit may capture a third frame slit in an (N+1)th video frame, and captures a fourth frame slit in an (N+3)th video frame, and the 3D image generating unit may generate a right image using the captured third frame slit and the captured fourth frame slit.

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: Apparatus and method for correcting a tone of a panoramic image. An image processing apparatus may acquire, from an overlapping region of a left image and a right image, ghost information based on an optimal threshold and a cost map in which a similarity between the left image and the right image is reflected, may generate a tone correction map based on a global tone correction function generated using the ghost information in the overlapping region, and based on a local tone correction level generated using local information of an optimal seam, and may correct the left image and the right image using a final tone correction map generated by applying, to the tone correction map, a weighting based on the left image and a weighting based on the right image.

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: 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 apparatus and method creating a ghost-free High Dynamic Range Image (HDRI) based on filtering are provided. It is possible to effectively prevent a ghost phenomenon from occurring when a single HDRI is created from a plurality of LDRIs, by defining a ghost area using a probability based on a global transfer function indicating a relationship for intensities of several frames, rather than searching for or identifying a ghost area in a single or each image.

Abstract: A method of processing frames obtained by multiple exposures may include categorizing, by at least one processor, a plurality of frames captured by multiple exposures into one of a reference frame and a target frame, compensating for global motion resulting from motion of a capturing apparatus capturing an object, and compensating for local motion resulting from motion of the object, based on a joint histogram between the reference frame and the target frame.

Abstract: A transaction splitting apparatus and method are provided in which neighboring sub-transactions accessing a predetermined bank in each memory may access different banks. The transaction splitting apparatus includes a first processing unit to split a transaction into at least one sub-transaction, the transaction accessing a first bank among a plurality of banks comprised in a memory, and a second processing unit to translate an address of the at least one sub-transaction, to interleave the at least one sub-transaction using the plurality of banks.