System and methods for Arabic text recognition based on effective Arabic text feature extraction
View Patent ↗A method for automatically recognizing Arabic text includes digitizing a line of Arabic characters to form a two-dimensional array of pixels each associated with a pixel value, wherein the pixel value is expressed in a binary number, dividing the line of the Arabic characters into a plurality of line images, defining a plurality of cells in one of the plurality of line images, wherein each of the plurality of cells comprises a group of adjacent pixels, serializing pixel values of pixels in each of the plurality of cells in one of the plurality of line images to form a binary cell number, forming a text feature vector according to binary cell numbers obtained from the plurality of cells in one of the plurality of line images, and feeding the text feature vector into a Hidden Markov Model to recognize the line of Arabic characters.
1. A computer-implemented method for automatically recognizing Arabic text, comprising:
acquiring a text image containing a line of Arabic characters;
digitizing the line of the Arabic characters to form a two-dimensional array of pixels each associated with a pixel value expressed in a binary number, wherein the two-dimensional array of pixels comprises a plurality of rows in a first direction and a plurality of columns in a second direction;
counting frequencies of consecutive pixels of a same pixel value in a string of pixels in a column of pixels, wherein adjacent strings of pixels each having different pixel values is defined by a transition in between, wherein the step of counting further comprises:
stopping counting frequencies of consecutive pixels of a same pixel value in a column when number of transitions in the column reaches a predetermined cut-off transition number, wherein the predetermined cut-off transition number is obtained by statistical analysis on Arabic text prior to the step of digitizing the line of the Arabic characters;
forming a text feature vector using the frequency counts obtained from the strings in the column of pixels; and
feeding the text feature vector into a Hidden Markov Model to recognize the line of Arabic characters.
2. The computer-implemented method of claim 1 , wherein the line of Arabic characters comprises a plurality of Arabic words.
3. The computer-implemented method of claim 1 , wherein the text feature vector is formed by a series of the frequency counts obtained from the consecutive strings of pixels in the column of pixels.
4. The computer-implemented method of claim 1 , wherein the predetermined cut-off transition number is six.
5. The computer-implemented method of claim 1 , wherein the pixel values in the two-dimensional array are expressed in single-bit binary numbers.
6. The computer-implemented method of claim 5 , wherein the step of counting frequencies comprises:
assigning the first frequency count to be “0” when the pixel value of the first one or more pixels in a column is “0”, wherein the second frequency count is the number of consecutive pixels having a “0” pixel value at the start of the column.
7. The computer-implemented method of claim 5 , wherein the step of counting frequencies comprises:
assigning the first frequency count to be “0” when the pixel value of the top one or more pixels in a column is “1”, wherein the second frequency count is followed by the number of consecutive pixels having a “1” pixel value at the start of the column.
8. A computer program product comprising a non-transitory computer useable medium having computer readable program code functions embedded in said medium for causing a computer to:
acquire a text image containing a line of Arabic characters;
digitize the line of the Arabic characters to form a two-dimensional array of pixels each associated with a pixel value expressed in a binary number, wherein the two-dimensional array of pixels comprises a plurality of rows in a first direction and a plurality of columns in a second direction;
count frequencies of consecutive pixels of a same pixel value in a string of pixels in a column of pixels, wherein adjacent strings of pixels each having different pixel values is defined by a transition in between, wherein the step of counting further comprises:
stopping counting frequencies of consecutive pixels of a same pixel value in a column when number of transitions in the column reaches a predetermined cut-off transition number, wherein the predetermined cut-off transition number is obtained by statistical analysis on Arabic text prior to the step of digitizing the line of the Arabic characters;
form a text feature vector using the frequency counts obtained from the strings in the column of pixels; and
feed the text feature vector into a Hidden Markov Model to recognize the line of Arabic characters.
9. The computer program product of claim 8 , wherein the line of Arabic characters comprises a plurality of Arabic words.
10. The computer program product of claim 8 , wherein the text feature vector is formed by a series of the frequency counts consecutively obtained from the consecutive strings of pixels in the column of pixels.
11. The computer program product of claim 8 , wherein the predetermined cut-off transition number is six.
12. The computer program product of claim 8 , wherein the pixel values in the two-dimensional array are expressed in single-bit binary numbers.
13. The computer program product of claim 12 , wherein the step of counting frequencies comprises:
assigning the first frequency count to be “0” when the pixel value of the first one or more pixels in a column is “0”, wherein the second frequency count is the number of consecutive pixels having a “0” pixel value at the start of the column.
14. The computer program product of claim 12 , wherein the step of counting frequencies comprises:
assigning the first frequency count to be “0” when the pixel value of the top one or more pixels in a column is “1”, wherein the second frequency count is followed by the number of consecutive pixels having a “1” pixel value at the start of the column.