Image processing apparatus, and image processing method and program
When an electronic document is to be generated from an image of a document, reproduction of both an appearance of the document image and a logical structure is difficult because of format limitations imposed on the electronic document. According to the present invention, from among column arrangements allowed by the specifications of the electronic document, a column arrangement is selected by using which the positions of character areas in an input image and the logical structure analyzed from the input image can be most appropriately reproduced, and is used to generate an electronic document.
1. An image processing apparatus for generating an electronic document from an image comprising:
an identification unit configured to identify character areas in the image;
a character recognition unit configured to perform a character recognition process on the identified character areas;
a counting unit configured to count the number of characters in each of the identified character areas;
a selection unit configured to select, from among column arrangements allowed by specifications of the electronic document, a column arrangement that arranges the greatest number of characters by using the number of characters in each of the identified character areas; and
a generation unit configured to generate the electronic document based on the selected column arrangement and a result of the character recognition process.
2. A program stored in a non-transitory computer-readable medium for making a computer to function as an image processing apparatus according to claim 1 .
3. The apparatus according to claim 1 , wherein the number of characters arranged according to the selected column arrangement is greater than the number of characters to be arranged according to each of the others of the column arrangements allowed by specifications of the electronic document.
4. An image processing method, performed by an image processing apparatus for generating an electronic document from an image, comprising:
an identification step of identifying character areas in the image;
a character recognition step of performing a character recognition process on the identified character areas;
a count step of counting the number of characters in each of the identified character areas;
a selection step of selecting, from among column arrangements allowed by specifications of the electronic document, a column arrangement that arranges the greatest number of characters by using the number of characters in each of the identified character areas; and
a generation step of generating the electronic document based on the selected column arrangement and a result of the character recognition process.