| 摘要 |
<p>A document image processing apparatus is provided, which comprises a structure analyzing unit for analytically dividing an input document image into sub-blocks having a specified physical positional relationship to each other, a structure forming unit for forming a representaion form corresponding to the physical positional relationship between the sub-blocks obtained by the structure analyzing unit, and a structure understanding unit for transforming the representation form obtained by the structure forming unit into a modified document image having a predetermined relationship between the sub-blocks.</p> |
