Abstract: Disclosed is a character recognition preprocessing method and apparatus for correcting a nonlinear character string into a linear character string. A binarized character string region is divided into character regions on a character-by-character basis. Upper and lower feature points of each character region are derived, and an upper boundary line, which is a curve connecting the upper feature points of the character regions, and a lower boundary line, which is a curve connecting the lower feature points of the character regions, are generated by applying cubic spline interpolation. Nonlinearity is corrected through adaptive region enlargement by using the maximum horizontal length and the maximum height of the divided character regions.

Abstract: Disclosed is a method for retrieving a label in a portable terminal. The method includes obtaining a label image photographed through a camera, extracting characters included in the label image and recognizing the extracted characters, detecting at least one label including the recognized character from a label database including multiple labels and information on the multiple labels and constituting a preliminary label candidate group including said at least one label, detecting an image characteristic of the label image, detecting at least one label having an image characteristic, which is similar with the detected image characteristic, from the preliminary label candidate group, and constituting a final label candidate group, and providing each of said at least one label included in the final label candidate group and detailed information corresponding to each of said at least one label.

Abstract: A method for recognizing a music score included in an image and various information included in the music score, which may be obtained through a camera provided in a mobile terminal without requiring a separate editing program. The method includes detecting a region with staff lines from the image including the music score; detecting a region with an accompaniment chord from the image by taking the region with the staff lines and a region with a musical note into consideration; extracting and removing the staff lines from the music score included in the image; recognizing the musical note by extracting the musical note from the image, from which the staff lines have been removed; recognizing the accompaniment chord by extracting the accompaniment chord from the image, from which the staff lines have been removed; and generating data for reproducing a sound source corresponding to the musical note and accompaniment chord.

Abstract: A method of compensating for distortion in text recognition is provided, which includes extracting a text region from an image; estimating the form of an upper end of the extracted text region; estimating the form of a lower end of the extracted text region; estimating the form of left and right sides of the extracted text region; estimating a diagram constituted in the form of the estimated upper end, lower end, left and right sides, and including a minimum area of the text region; and transforming the text region constituting the estimated diagram into a rectangular diagram using an affine transform.

Abstract: Disclosed is a method of recognizing a text from an image. The method includes dividing the image into a predefined number of regions through a clustering technique; setting a certain area of the regions as a background region; identifying the outer peripheral pixel and inner peripheral pixel of each region except for the background region of the divided regions; setting a region identified as having one of its outer peripheral pixel and its inner peripheral pixel corresponding to a pixel of the background region, as a boundary region; and setting a region identified as having any of its outer peripheral pixel and its inner peripheral pixel not corresponding to a pixel of the background region, as a center text region, and excluding the boundary region from a binary-coding object of the text.

Abstract: There are provided a distributed video coding apparatus and method capable of controlling an encoding rate, the apparatus including: an intra-frame encoder encoding a key frame and outputting a bit stream of the encoded key frame; an encoder rate control (ERC) module calculating a bit rate according to motion complexity of a present Wyner-Ziv (WZ) frame by using a correlation between the motion complexity and the bit rate; and a turbo encoder encoding the present WZ frame by the bit rate calculated at the ERC module and outputting the encoded WZ bit stream.

Abstract: Disclosed is a character recognition preprocessing method and apparatus for correcting a nonlinear character string into a linear character string. A binarized character string region is divided into character regions on a character-by-character basis. Upper and lower feature points of each character region are derived, and an upper boundary line, which is a curve connecting the upper feature points of the character regions, and a lower boundary line, which is a curve connecting the lower feature points of the character regions, are generated by applying cubic spline interpolation. Nonlinearity is corrected through adaptive region enlargement by using the maximum horizontal length and the maximum height of the divided character regions.

Abstract: Disclosed is a method of removing staff lines from a music score an image. The method includes detecting a region with staff lines in an image including a music score; checking a gradient of the staff lines, and dividing the staff lines extending continuously in a longitudinal direction into a plurality of regions in consideration of the gradient, estimating each of the staff lines included in the divided regions by analyzing a histogram of the image, extracting each of the staff lines from the music score on the basis of the estimated staff lines and removing each of the extracted lines of the staff lines from the music score.

Abstract: Disclosed is a method for retrieving a label in a portable terminal. The method includes obtaining a label image photographed through a camera, extracting characters included in the label image and recognizing the extracted characters, detecting at least one label including the recognized character from a label database including multiple labels and information on the multiple labels and constituting a preliminary label candidate group including said at least one label, detecting an image characteristic of the label image, detecting at least one label having an image characteristic, which is similar with the detected image characteristic, from the preliminary label candidate group, and constituting a final label candidate group, and providing each of said at least one label included in the final label candidate group and detailed information corresponding to each of said at least one label.

Abstract: A method of compensating for distortion in text recognition is provided, which includes extracting a text region from an image; estimating the form of an upper end of the extracted text region; estimating the form of a lower end of the extracted text region; estimating the form of left and right sides of the extracted text region; estimating a diagram constituted in the form of the estimated upper end, lower end, left and right sides, and including a minimum area of the text region; and transforming the text region constituting the estimated diagram into a rectangular diagram using an affine transform.

Abstract: Disclosed is a method of recognizing a text from an image. The method includes dividing the image into a predefined number of regions through a clustering technique; setting a certain area of the regions as a background region; identifying the outer peripheral pixel and inner peripheral pixel of each region except for the background region of the divided regions; setting a region identified as having one of its outer peripheral pixel and its inner peripheral pixel corresponding to a pixel of the background region, as a boundary region; and setting a region identified as having any of its outer peripheral pixel and its inner peripheral pixel not corresponding to a pixel of the background region, as a center text region, and excluding the boundary region from a binary-coding object of the text.

Abstract: An anisotropic diffusion method and apparatus based on the direction of an edge are disclosed. In the anisotropic diffusion apparatus, directional pattern masking is performed to determine the direction of an edge in an image including noise, and values obtained through the directional pattern masking are convoluted to calculate the magnitude of an image. If the calculated magnitude value of the edge is larger than a threshold value, the edge of the image is preserved, while if the calculated magnitude value of the edge is not larger than the threshold value, noise cancellation is strengthened, whereby noise can be effectively canceled (or concealed) while preserving the edge representing the characteristics of the image, and thus, an image of high quality can be obtained.

Abstract: A method for recognizing a music score included in an image and various information included in the music score, which may be obtained through a camera provided in a mobile terminal without requiring a separate editing program. The method includes detecting a region with staff lines from the image including the music score; detecting a region with an accompaniment chord from the image by taking the region with the staff lines and a region with a musical note into consideration; extracting and removing the staff lines from the music score included in the image; recognizing the musical note by extracting the musical note from the image, from which the staff lines have been removed; recognizing the accompaniment chord by extracting the accompaniment chord from the image, from which the staff lines have been removed; and generating data for reproducing a sound source corresponding to the musical note and accompaniment chord.

Abstract: There are provided a distributed video coding apparatus and method capable of controlling an encoding rate, the apparatus including: an intra-frame encoder encoding a key frame and outputting a bit stream of the encoded key frame; an encoder rate control (ERC) module calculating a bit rate according to motion complexity of a present Wyner-Ziv (WZ) frame by using a correlation between the motion complexity and the bit rate; and a turbo encoder encoding the present WZ frame by the bit rate calculated at the ERC module and outputting the encoded WZ bit stream.

Abstract: Disclosed is a method of removing staff lines from a music score an image. The method includes detecting a region with staff lines in an image including a music score; checking a gradient of the staff lines, and dividing the staff lines extending continuously in a longitudinal direction into a plurality of regions in consideration of the gradient, estimating each of the staff lines included in the divided regions by analyzing a histogram of the image, extracting each of the staff lines from the music score on the basis of the estimated staff lines and removing each of the extracted lines of the staff lines from the music score.