Method for processing document, recorded medium on which document processing program is recorded and document processor

A document processing method comprising:

• an input step of inputting character box data which includes a title character formed of a set of dots, an entry box formed of a set of dots, and a written character;
• a character detection step of detecting character data of the written character according to the character box data input in the input step;
• a character-pattern removing step of removing a character pattern detected in the character detection step from the character box data input in the input step according to the character box data;
• an expansion step of performing an expansion process to an extent in which adjacent dots become linked;
• and
• a recognition step of recognizing the title character in a title in an image obtained in the expansion step.

A document processing method comprising:

• an input step of inputting character box data that includes an entry box which is formed of a set of dots and in which information has been embedded by changing such that the set of dots is not uniform, and a written character;
• a character detection step of detecting character data of the written character according to the character box data input in the input step;
• a character-pattern removing step of removing a character pattern detected in the character detection step from the character box data input in the input step according to the character box data;
• and
• a determination step of detecting a change in the set of dots of the entry box according to entry-box data obtained in the character-pattern removing step, to determine the information embedded in the entry box.

A recording medium readable by a computer, having recorded thereon a document processing program for causing the computer to perform:

• a document input step of inputting a document and of generating character box data which includes an entry box formed of a set of dots, and a written character;
• a character detection step of detecting character data of the written character according to the character box data generated in the document input step;
• an entry-box detection step of detecting entry-box-position data which indicates a position where a character is to be written according to the character box data generated in the document input step;
• a relating step of relating the character and the entry box to each other according to the character data detected in the character detection step and the entry-box-position data detected in the entry-box detection step to extract a character-pattern for each character;
• and
• a recognition step of recognizing each written character according to each character pattern extracted in the relating step.

A recording medium readable by a computer, having recorded thereon a document processing program for causing the computer to perform:

• an input step of inputting character box data which includes a title character formed of a set of dots, an entry box formed of a set of dots, and a written character;
• a character detection step of detecting character data of the written character according to the character box data input in the input step;
• a character-pattern removing step of removing a character pattern detected in the character detection step from the character box data input in the input step according to the character box data;
• an expansion step of performing an expansion process to an extent in which adjacent dots become linked;
• and
• a recognition step of recognizing the title character in a title in an image obtained in the expansion step.

A recording medium readable by a computer, having recorded thereon a document processing program for causing the computer to perform:

• an input step of inputting character box data that includes an entry box which is formed of a set of dots and in which information has been embedded by changing such that the set of dots is not uniform, and a written character;
• a character detection step of detecting character data of the written character according to the character box data input in the input step;
• a character-pattern removing step of removing a character pattern detected in the character detection step from the character box data input in the input step according to the character box data;
• and
• a determination step of detecting a change in the set of dots of the entry box according to entry-box data obtained in the character-pattern removing step, to determine the information embedded in the entry box.

A document processing apparatus comprising:

• document input means for inputting a document and for generating character box data which includes an entry box formed of a set of dots, and a written character;
• character detection means for detecting character data of the written character according to the character box data generated by the document input means;
• entry-box detection means for detecting entry-box-position data which indicates a position where a character is to be written according to the character box data generated by the document input means;
• relating means for relating the character and the entry box to each other according to the character data detected by the character detection means and the entry-box-position data detected by the entry-box detection means to extract a character pattern for each character;
• and
• recognition means for recognizing each written character according to each character pattern extracted by the relating means.

A document processing program for causing a computer to perform:

• a document input step of inputting a document and of generating character box data which includes an entry box formed of a set of dots, and a written character;
• a character detection step of detecting character data of the written character according to the character box data generated in the document input step;
• an entry-box detection step of detecting entry-box-position data which indicates a position where a character is to be written according to the character box data generated in the document input step;
• a relating step of relating the character and the entry box to each other according to the character data detected in the character detection step and the entry-box-position data detected in the entry-box detection step to extract a character pattern for each character;
• and
• a recognition step of recognizing each written character according to each character pattern extracted in the relating step.

A document processing program for causing a computer to perform:

• an input step of inputting character box data which includes a title character formed of a set of dots, an entry box formed of a set of dots, and a written character;
• a character detection step of detecting character data of the written character according to the character box data input in the input step;
• a character-pattern removing step of removing a character pattern detected in the character detection step from the character box data input in the input step according to the character box data;
• an expansion step of performing an expansion process to an extent in which adjacent dots become linked;
• and
• a recognition step of recognizing the title character in a title in an image obtained in the expansion step.

A document processing program for causing a computer to perform:

• an input step of inputting character box data that includes an entry box which is formed of a set of dots and in which information has been embedded by changing such that the set of dots is not uniform, and a written character;
• a character detection step of detecting character data of the written character according to the character box data input in the input step;
• a character-pattern removing step of removing a character pattern detected in the character detection step from the character box data input in the input step according to the character box data;
• and
• a determination step of detecting a change in the set of dots of the entry box according to entry-box data obtained in the character-pattern removing step, to determine the information embedded in the entry box.