Method and system for processing images of forms which have irregular construction and/or determining whether characters are interior to a form
First Claim
1. A method of processing an image, comprising the steps of:
- obtaining an image which includes document image data;
determining a form candidate using the document image data;
extracting provisional ruled lines from the form candidate;
determining a structure of the form candidate by analyzing the provisional lines in a horizontal and vertical direction, including, determining whether or not the form candidate corresponds to a figure, determining whether or not the form candidate corresponds to a graph, determining whether or not the form candidate corresponds to a frame, and determining whether or not the form candidate corresponds to a form; and
determining if character candidates which are proximate to the form candidate which is determined to correspond to a form are inside or outside the corresponding form, wherein the step of determining if the character candidates which are proximate to the form are inside or outside the corresponding form comprises;
determining if the character candidates are between a first perimeter of the corresponding form in a first viewpoint;
determining if the character candidates are between a second perimeter of the corresponding form, the second perimeter being opposite the first perimeter, in a second viewpoint opposite the first viewpoint; and
determining that the character candidates are inside the corresponding form when it is determined that character candidates are not between the first perimeter in the first viewpoint, and are not between the second perimeter in the second viewpoint.
1 Assignment
0 Petitions
Accused Products
Abstract
A method and system for processing images. An input or scanned image is first processed into a plurality of rectangles. Using these rectangles, a rough classification process is performed to determine if the rectangles define character candidates, horizontal ruled line candidates, vertical line candidates, or form candidates. A processing of the form candidates is performed which allows the determination of whether the form has a regular shape such as a rectangular shape or an irregular shape which includes protrusions from a rectangular shape. The form candidates are analyzed in order to determine if they are irregular forms by constructing and analyzing one or more cores which define the form. After an irregular form is determined, a determination is made as to whether character candidates are inside of or outside of the form. If it is desirable to only perform character recognition on character candidates which are outside of the form, a scanning process is performed in order to determine whether the character candidates are inside of or outside of the form.
-
Citations
4 Claims
-
1. A method of processing an image, comprising the steps of:
-
obtaining an image which includes document image data;
determining a form candidate using the document image data;
extracting provisional ruled lines from the form candidate;
determining a structure of the form candidate by analyzing the provisional lines in a horizontal and vertical direction, including, determining whether or not the form candidate corresponds to a figure, determining whether or not the form candidate corresponds to a graph, determining whether or not the form candidate corresponds to a frame, and determining whether or not the form candidate corresponds to a form; and
determining if character candidates which are proximate to the form candidate which is determined to correspond to a form are inside or outside the corresponding form, wherein the step of determining if the character candidates which are proximate to the form are inside or outside the corresponding form comprises;
determining if the character candidates are between a first perimeter of the corresponding form in a first viewpoint;
determining if the character candidates are between a second perimeter of the corresponding form, the second perimeter being opposite the first perimeter, in a second viewpoint opposite the first viewpoint; and
determining that the character candidates are inside the corresponding form when it is determined that character candidates are not between the first perimeter in the first viewpoint, and are not between the second perimeter in the second viewpoint.
-
-
2. A method of analyzing whether character candidates are inside a form, comprising the steps of:
-
inputting an image containing a form and character candidates; and
determining if the character candidates are inside or outside the form, including the steps of, determining if the character candidates are between a first perimeter of the form in a first viewpoint;
determining if the character candidates are between a second perimeter of the form, the second perimeter being opposite the first perimeter, in a second viewpoint opposite the first viewpoint; and
determining that the character candidates are inside the form when it is determined that character candidates are not between the first perimeter in the first viewpoint, and are not between the second perimeter in the second viewpoint.
-
-
3. A system for processing an image, comprising:
-
means for obtaining an image which includes document image data;
means for determining a form candidate using the document image data;
means for extracting provisional ruled lines from the form candidate;
means for determining a structure of the form candidate by analyzing the provisional lines in a horizontal and vertical direction, including, determining whether or not the form candidate corresponds to a figure, determining whether or not the form candidate corresponds to a graph, determining whether or not the form candidate corresponds to a frame, and determining whether or not the form candidate corresponds to a form; and
means for determining if character candidates which are proximate to the form candidate which is determined to correspond to a form are inside or outside the corresponding form, wherein the means for determining if the character candidates which are proximate to the form are inside or outside the corresponding form comprises;
means for determining if the character candidates are between a first perimeter of the corresponding form in a first viewpoint;
means for determining if the character candidates are between a second perimeter of the corresponding form, the second perimeter being opposite the first perimeter, in a second viewpoint opposite the first viewpoint; and
means for determining that the character candidates are inside the corresponding form when it is determined that character candidates are not between the first perimeter in the first viewpoint, and are not between the second perimeter in the second viewpoint.
-
-
4. A system of analyzing whether character candidates are inside a form, comprising:
-
means for inputting an image containing a form and character candidates; and
means for determining if the character candidates are inside or outside the form, including, determining if the character candidates are between a first perimeter of the form in a first viewpoint;
means for determining if the character candidates are between a second perimeter of the form, the second perimeter being opposite the first perimeter, in a second viewpoint opposite the first viewpoint; and
means for determining that the character candidates are inside the form when it is determined that character candidates are not between the first perimeter in the first viewpoint, and are not between the second perimeter in the second viewpoint.
-
Specification