Character line division apparatus and method, and storage medium

A character line division method comprising:

• acquiring character line information indicating a size and a position of each character line within a binary image obtained by binarizing a scanned image obtained by optically reading a document, and character information indicating a size and a position of each character in a character line within the binary image;
• extracting character height information indicating a character height from the character information;
• determining whether a character comes into contact with another character in a character height direction based on the character height information;
• determining whether a character line of interest among character lines in the document comes into contact with another character line in a height direction based on the character line information and determination results;
• obtaining a count value obtained by counting a number of black pixels in a width direction in a character line of interest in the character line of interest determined to come into contact with another character line, and
• performing character line division for the character line of interest determined to come into contact with another character line on a periphery of a reference point obtained from a position of a character line indicated by the character line information and the character height information by taking a first position at which the count value becomes a minimum in a height direction of the character line of interest as a character line division position.

A non-transitory computer readable storage medium storing a program for causing a computer to perform as a character line division apparatus, wherein

• the character line division apparatus comprises:
• an acquisition unit configured to acquire character line information indicating a size and a position of each character line within a binary image obtained by binarizing a scanned image obtained by optically reading a document, and character information indicating a size and a position of each character in a character line within the binary image;
• an extraction unit configured to extract character height information indicating a character height from the character information;
• a first determination unit configured to determine whether a character comes into contact with another character in a height direction based on the character height information;
• a second determination unit configured to determine whether a character line of interest among character lines in the document comes into contact with another character line in a height direction based on the character line information and determination results by the first determination unit;
• an obtaining unit configured to obtain a count value obtained by counting a number of black pixels in a width direction in a character line of interest in the character line of interest determined to come into contact with another character line by the second determination unit;
• and
• a character line division unit configured to perform character line division for the character line of interest determined to come into contact with another character line by the second determination unit on a periphery of a reference point obtained from a position of a character line indicated by the character line information and the character height information by taking a first position at which the count value becomes a minimum in a height direction of the character line of interest as a character line division position.