Scheme for extraction and recognition of telop characters from video data
First Claim
1. A method for recognizing character patterns, comprising the steps of:
- (a) dividing character patterns that are binarized into black pixels and white pixels into divided regions each containing one character;
(b) normalizing position and size of a character in each divided region;
(c) dividing a character pattern of each normalized character into mesh regions;
(d) counting a run-length of white pixels which are adjacent in each direction starting from a white pixel existing in each divided mesh region, for a plurality of prescribed directions;
(e) calculating a direction contributivity of each direction as a value obtained by averaging the run-length in each direction over an accumulated value of all the run-lengths for all the prescribed directions as counted by the step (d), for each divided mesh region;
(f) calculating a feature value of each divided mesh region by accumulating the direction contributivity of each direction for all white pixels in each divided mesh region and averaging an accumulated value of the direction contributivity of each direction over a number of white pixels within each mesh region; and
(g) carrying out a processing for recognizing the character pattern of each normalized character using the feature values obtained for all the mesh regions at the step (f).
0 Assignments
0 Petitions
Accused Products
Abstract
A scheme for detecting telop character displaying frames in video image which is capable of suppressing erroneous detection of frames without telop characters due to instability of image features is disclosed. In this scheme, each input frame constituting the video data is entered, and whether each input frame is a telop character displaying frame in which telop characters are displayed or not is judged, according to edge pairs detected from each input frame by detecting each two adjacent edge pixels for which intensity gradient directions are opposite on some scanning line used in judging an intensity gradient direction at each edge pixel and for which an intensity difference between said two adjacent edge pixels is within a prescribed range as one edge pair, edge pixels being pixels at which an intensity value locally changes by at least a prescribed amount with respect to a neighboring pixel among a plurality of pixels constituting each input frame.
-
Citations
6 Claims
-
1. A method for recognizing character patterns, comprising the steps of:
-
(a) dividing character patterns that are binarized into black pixels and white pixels into divided regions each containing one character;
(b) normalizing position and size of a character in each divided region;
(c) dividing a character pattern of each normalized character into mesh regions;
(d) counting a run-length of white pixels which are adjacent in each direction starting from a white pixel existing in each divided mesh region, for a plurality of prescribed directions;
(e) calculating a direction contributivity of each direction as a value obtained by averaging the run-length in each direction over an accumulated value of all the run-lengths for all the prescribed directions as counted by the step (d), for each divided mesh region;
(f) calculating a feature value of each divided mesh region by accumulating the direction contributivity of each direction for all white pixels in each divided mesh region and averaging an accumulated value of the direction contributivity of each direction over a number of white pixels within each mesh region; and
(g) carrying out a processing for recognizing the character pattern of each normalized character using the feature values obtained for all the mesh regions at the step (f).
-
-
2. A method for recognizing character patterns, comprising the steps of:
-
(a) dividing character patterns that are binarized into black pixels and white pixels into divided regions each containing one character;
(b) normalizing position and size of a character in each divided region;
(c) dividing a character pattern of each normalized character into mesh regions;
(d) counting a run-length of black pixels which are adjacent in each direction starting from a black pixel existing in each divided mesh region, for a plurality of prescribed directions;
(e) calculating a black pixel direction contributivity of each direction as a value obtained by averaging the run-length of black pixels in each direction over an accumulated value of all the run-lengths of black pixels for all the prescribed directions as counted by the step (d) for each divided mesh region;
(f) counting a run-length of white pixels which are adjacent in each direction starting from a white pixel existing in each divided mesh region, for a plurality of prescribed directions;
(g) calculating a white pixel direction contributivity of each direction as a value obtained by averaging the run-length of white pixels in each direction over an accumulated value of all the run-lengths of white pixels for all the prescribed directions as counted by the step (f), for each divided mesh region;
(h) calculating a black pixel feature value of each divided mesh region by accumulating the black pixel direction contributivity of each direction for all black pixels in each divided mesh region and averaging an accumulated value of the black pixel direction contributivity of each direction over a number of black pixels within each mesh region;
(i) calculating a white pixel feature value of each divided mesh region by accumulating the white pixel direction contributivity of each direction for all white pixels in each divided mesh region and averaging an accumulated value of the white pixel direction contributivity of each direction over a number of white pixels within each mesh region; and
(j) carrying out a processing for recognizing the character pattern of each normalized character using the black feature values obtained for all the mesh regions at the step (h) and the white feature values obtained for all the mesh regions at the step (i).
-
-
3. An apparatus for recognizing character patterns, comprising:
-
a unit (a) for dividing character patterns that are binarized into black pixels and white pixels into divided regions each containing one character;
a unit (b) for normalizing position and size of a character in each divided region;
a unit (c) for dividing a character pattern of each normalized character into mesh regions;
a unit (d) for counting a run-length of white pixels which are adjacent in each direction starting from a white pixel existing in each divided mesh region, for a plurality of prescribed directions;
a unit (e) for calculating a direction contributivity of each direction as a value obtained by averaging the run-length in each direction by an accumulated value of all the run-lengths for all the prescribed directions as counted by the unit (d), for each divided mesh region;
a unit (f) for calculating a feature value of each divided mesh region by accumulating the direction contributivity of each direction for all white pixels in each divided mesh region and averaging an accumulated value of the direction contributivity of each direction over a number of white pixels within each mesh region; and
a unit (g) for carrying out a processing for recognizing the character pattern of each normalized character using the features values obtained for all the mesh regions at the unit (f).
-
-
4. An apparatus for recognizing character patterns, comprising:
-
a unit (a) for dividing character patterns that are binarized into black pixels and white pixels into divided regions each containing one character;
a unit (b) for normalizing position and size of a character in each divided region;
a unit (c) for dividing a character pattern of each normalized character into mesh regions;
a unit (d) for counting a run-length of black pixels which are adjacent in each direction starting from a black pixel existing in each divided mesh region, for a plurality of prescribed directions;
a unit (e) for calculating a black pixel direction contributivity of each direction as a value obtained by averaging the run-length of black pixels in each direction by an accumulated value of all the run-lengths of black pixels for all the prescribed directions as counted by the unit (d), for each divided mesh region;
a unit (f) for counting a run-length of white pixels which are adjacent in each direction starting from a white pixel existing in each divided mesh region, for a plurality of prescribed directions;
a unit (g) for calculating a white pixel direction contributivity of each direction as a value obtained by averaging the run-length of white pixels in each direction over an accumulated value of all the run-lengths of white pixels for all the prescribed directions as counted by the unit (f), for each divided mesh region;
a unit (h) for calculating a black pixel feature value of each divided mesh region by accumulating the black pixel direction contributivity of each direction for all black pixels in each divided mesh region and averaging an accumulated value of the black pixel direction contributivity of each direction over a number of black pixels within each mesh region;
a unit (i) for calculating a white pixel feature value of each divided mesh region by accumulating the white pixel direction contributivity of each direction for all white pixels in each divided mesh region and averaging an accumulated value of the white pixel direction contributivity of each direction over a number of white pixels within each mesh region; and
a unit (j) for carrying out a processing for recognizing the character pattern of each normalized character using the black feature values obtained for all the mesh regions at the unit (h) and the white feature values obtained for all the mesh regions at the unit (i).
-
-
5. A computer readable recording medium recording a program for causing a computer to execute processing including:
-
(a) the process step of dividing character patterns that are binarized into black pixels and white pixels into divided regions each containing one character;
(b) the process step of normalizing position and size of a character in each divided region;
(c) the process step of dividing a character pattern of each normalized character into mesh regions;
(d) the process step of counting a run-length of white pixels which are adjacent in each direction starting from a white pixel existing in each divided mesh region, for a plurality of prescribed directions;
(e) the process step of calculating a direction contributivity of each direction as a value obtained by averaging the run-length in each direction by an accumulated value of all the run-lengths for all the prescribed directions as counted by the process step of (d), for each divided mesh region;
(f) the process step of counting a run-length of white pixels which are adjacent in each direction starting from a white pixel existing in each divided mesh region, for a plurality of prescribed directions;
(g) the process step of calculating a white pixel direction contributivity of each direction as a value obtained by averaging the run-length of white pixels in each direction over an accumulated value of all the run-lengths of white pixels for all the prescribed directions as counted by the process step of (f), for each divided mesh region;
(h) the process step of calculating a black pixel feature value of each divided mesh region by accumulated the black pixel direction contributivity of each direction for all black pixels in each divided mesh region and averaging an accumulated value of the black pixels direction contributivity of each direction over a number of black pixels within each mesh region;
(i) the process step of calculating a white pixel feature value of each divided mesh region by accumulating the white pixel direction contributivity of each direction for all white pixels in each divided mesh region and averaging an accumulated value of the white pixel direction contributivity of each direction over a number of white pixels within each mesh region; and
(j) the process step of carrying out a processing for recognizing the character pattern of each normalized character using the black feature values obtained for all the mesh regions at the process step of (h) and the white feature values obtained for all the mesh regions at the process step of (i).
-
-
6. A computer readable recording medium recording a program for causing a computer to execute processing including:
-
(a) the process step of dividing character patterns that are binarized into black pixels and white pixels into divided regions each containing one character;
(b) the process step of normalizing position and size of a character in each divided region;
(c) the process step of dividing a character pattern of each normalized character into mesh regions;
(d) the process step of counting a run-length of black pixels which are adjacent in each direction starting from a black pixel existing in each divided mesh region, for a plurality of prescribed directions;
(e) the process step of calculating a black pixel direction contributivity of each direction as a value obtained by averaging the run-length of black pixels in each direction over an accumulated value of all the run-lengths of black pixels for all the prescribed directions as counted by the process step of (d), for each divided mesh region;
(f) the process step of counting a run-length of white pixels which are adjacent in each direction starting from a white pixel existing in each divided mesh region, for a plurality of prescribed directions;
(g) the process step of calculating a white pixel direction contributivity of each direction as a value obtained by averaging the run-length of white pixels in each direction over an accumulated value of all the run-lengths of white pixels for all the prescribed directions as counted by the process step of (f), for each divided mesh region;
(h) the process step of calculating a black pixel feature value of each divided mesh region by accumulating the black pixel direction contributivity of each direction for all black pixels in each divided mesh region and averaging an accumulated value of the black pixel direction contributivity of each direction over a number of black pixels within each mesh region;
(i) the process step of calculating a white pixel feature value of each divided mesh region by accumulating the white pixel direction contributivity of each direction for all white pixels in each divided mesh region and averaging an accumulated value of the white pixel direction contributivity of each direction over a number of white pixels within each mesh region; and
(j) the process step of carrying out a processing for recognizing the character pattern of each normalized character using the black feature values obtained for all the mesh regions at the process step of (h) and the white feature values obtained for all the mesh regions at the process step of (i).
-
Specification