Feature extraction system

Claim 2

The method according to Claim 1, further comprising the step of analyzing all text blocks having a column or row address range in the table image data in order to determine if the text block can be further separated wherein each text block having either a column or row address range is analyzed to determine if a text block having either column or row address range can be further divided into at least one additional column or row, and, if it is determined that a text block can be further divided, dividing the text block.

Claim 3

The method according to Claim 1, further comprising the step of assigning a new text block address to text blocks divided in the analyzing step.

Claim 4

The method according to Claim 1, further comprising the step of storing the new text block address for each text block which was assigned an address in the text block address assigning step.

Claim 5

In a feature extraction system which creates a hierarchical tree structure corresponding to a block template of a document page, wherein the hierarchical tree structure includes a plurality of nodes each of which represents a block of image data in the block template of the document page and contains address data defining locations of the image data in the document page, a method of identifying table image data and locating text image data within the table, comprising the steps of: inputting image data of a document page; performing block selection processing so as to identify and separate image data into blocks having the same image type; identifying blocks of image data which contain table image data; locating text blocks within the table image data; horizontally sorting all text blocks located in the table image data based on horizontal position information; vertically sorting all text blocks located in the table image data based on vertical position information; separating text blocks into rows and columns based on a result of the vertical and the horizontal sorting steps; assigning address information to each text block in the table image data based on the separating step; and storing, in a node representing the block of table image data in the hierarchical tree, table address information and storing, in respective nodes representing text blocks branching from the node representing the table image data, text block address information.

Claim 6

The method according to Claim 5, further comprising the step of analyzing all text blocks having a column or row address range in the table image data, wherein each text block having either a column or row address range is analyzed to determine if a text block having either column or row address range can be further divided into at least one additional column or row, and, if it is determined that a text block can be further divided, dividing the text block.

Claim 7

The method according to Claim 5, further comprising the step of assigning a new text block address to new text blocks divided out in the analyzing step.

Claim 8

The method according to Claim 5, further comprising the step of storing, in a node branching from a text block from which a new text block was divided out, address information for the new text block.

Claim 9

A feature extraction system for analyzing image data of an input document image, comprising: input means for inputting image data of a document page; block selection processing means for performing block selection processing on the document page, said block selection processing means identifying and separating the image data into blocks having the same image type; identifying means for identifying table image data based on the separated blocks of image data; identifying means for identifying text blocks within the table image data; horizontal sorting means for sorting of all text blocks located in the table image data based on horizontal position information; vertical sorting means for sorting of all text blocks located in the table image data based on vertical position information; separating means for separating text blocks into rows and columns based on a result of the vertical and the horizontal sorting; address assigning means for assigning address information to each text block in the table image data separated by the separating means; and storing means for storing the assigned address of each text block.

Claim 10

The feature extraction system according to Claim 9, wherein the sorting means analyzes all text blocks having a column or row address range in the table image data in order to determine if the text block having either a column or row address range can be further divided into at least one additional column or row, and, if so, dividing the text block into at least two new text blocks.

Claim 11

The feature extraction system according to Claim 9, wherein the address assigning means assigns a new text block address in the case a text block having either a column or row address range is further divided into at least two new text blocks.

Claim 12

The feature extraction system according to Claim 9, wherein the storing means stores the text block address for each text block which was divided by the sorting means.

Claim 13

The method according to Claim 1, wherein, in said inputting step, the image data of the document page is input by a scanner.

Claim 14

The method according to Claim 5, wherein, in said inputting step, the image data of the document page is input by a scanner.

Claim 15

The feature extraction system according to Claim 9, wherein the input means is a scanner.