System and method of performing data processing on similar forms

• US 8,589,416 B2
• Filed: 03/31/2010
• Issued: 11/19/2013
• Est. Priority Date: 01/20/2010
• Status: Expired due to Fees

• Current Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Original Assignee: Fuji Xerox Company Limited (Xerox Holdings Corp.)
• Inventors: Watanabe, Tsuyoshi
• Primary Examiner(s): Hong, Stephen
• Assistant Examiner(s): BLOOMQUIST, KEITH D
• Application Number:
  US12/751,447
• Publication Number:
  US 20110176735A1
• Time in Patent Office: 1,329 Days
• Field of Search: None
• US Class Current: 707/749
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06V 30/1914 Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries, e.g. user dictionaries
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images

Abstract

A form identification apparatus includes a form registration unit and a candidate registered form extracting unit. The form registration unit registers stylized forms as registered forms, and sets, for each of the registered forms, content of form processing and a threshold for determining a degree of difference in accordance with the content of the form processing. The candidate registered form extracting unit extracts, as a candidate registered form, the registered forms in which content of form processing executable on a to-be-processed form has been set, based on a degree of difference between an image of the to-be-processed form and an image of each of the registered forms and the threshold.

Claims

1. A form identification apparatus comprising:

a memory; and

a processor, the processor functioning as;

a form registration unit that stores stylized forms as registered forms in the memory, and associates with each of the registered forms a type of form processing to be performed on the registered form and a degree of difference threshold based on the type of the form processing in the memory, wherein the registered forms are a plurality of forms associated with one of types of form processing to be performed on the registered forms and one of degrees of difference thresholds based on the one of the types of form processings;

a difference degree computing portion that respectively compares an input form to the registered forms and determines degrees of difference between the input form and the registered forms based on results of the comparing;

a candidate registered form extracting unit that determines whether the degrees of difference between the input form and the registered forms are less than the degree of difference threshold, extracts from the memory, as a candidate registered form, at least one registered form among the registered forms in response to determining that the degree of difference between the input form and the registered form is less than the degree of difference threshold, and, if a plurality of candidate forms having the degrees of difference less than the degree of difference threshold are extracted from the memory, causes a display device to display the plurality of candidate forms for selection of one of the plurality of candidates forms displayed on the display device as the candidate registered form; and

an execution unit that executes for the input form a form processing associated with the candidate registered form.

2. The form identification apparatus according to claim 1, wherein the candidate registered form extracting unit determines that the degrees of difference between the input form and the registered forms are greater than the degrees of difference thresholds and presents, to a user, the candidate registered form based on updated degrees of difference thresholds greater than the degrees of difference thresholds.

3. The form identification apparatus according to claim 1, wherein the candidate registered form extracting unit determines that plural degrees of difference between the input form and the registered forms are smaller than the degrees of difference thresholds, extracts from the memory as a plurality of candidate registered forms the registered forms having the plural degrees of difference between the input form and the plurality of forms smaller than the degrees of difference thresholds, presents the plurality of candidate registered forms to a user, and selects one of the plurality of registered forms whose type of form processing is executed on the input form, based on instruction information inputted by the user.

4. The form identification apparatus according to claim 1, wherein the candidate registered form extracting unit determines that plural degrees of difference between the input form and the plurality of forms are smaller than the degrees of difference thresholds, extracts from the memory as a plurality of candidate registered forms the registered forms having the plural degrees of difference between the input form and the plurality of forms smaller than the degrees of difference thresholds, and selects the candidate registered form whose degree of difference between the input form is the smallest, as the candidate registered form whose type of form processing is executed on the input form.

5. The form identification apparatus according to claim 1, wherein the candidate registered form extracting unit extracts from the memory, as a plurality of candidate registered forms, a first registered form whose degree of difference between the input form is smaller than a first degree of difference threshold and a second registered form whose degree of difference between the input form is not smaller than a second threshold smaller than the first threshold but is smaller than that of the first registered form, presents the plurality of candidate registered forms to a user, and selects one of the plurality of candidate registered forms whose type of form processing is executed on the input form, based on instruction information inputted by the user.

6. A form identification apparatus according to claim 1, wherein the degree of difference threshold is determined based on a level of security required for the type of form processing associated with the registered form.

10. The form identification apparatus according to claim 2, wherein the candidate registered form extracting unit, if a plurality of candidate forms are extracted having the degrees of difference less than the updated degrees of difference thresholds are extracted from the memory, causes the display device to display the plurality of candidate forms for selection of one of the plurality of candidate registered forms displayed on the display device as the candidate registered form.

11. The form identification apparatus according to claim 6, wherein the degree of difference threshold comprises a first degree of difference threshold and a second degree of difference threshold greater than the first degree of difference threshold, and

wherein a first level of security corresponding to the first degree of difference threshold is higher than a second level of security corresponding to the second degree of difference threshold.

7. A form processing system comprising:

a scanner that reads an input form;

a form identification apparatus, that stores stylized forms as registered forms in the memory, and associates with each of the registered forms a type of form processing to be performed on the registered form and a degree of difference threshold based on the type of the form processing in the memory, wherein the registered forms are a plurality of forms associated with one of types of form processing to be performed on the registered forms and one of degrees of difference thresholds based on the one of the types of form processings, acquires an image of the input form from the form reading apparatus, compares the image of the input form to the registered forms and determines degrees of difference between the input form and the registered forms based on results of the comparing, determines whether the degrees of difference between the input form and the registered forms are less than the degree of difference threshold, extracts from the memory, as a candidate form, at least one registered form among the registered forms in response to determining that the degree of difference between the input form and the registered form is less than the degree of difference threshold, and, if a plurality of candidate forms having the degrees of difference less than the degree of difference threshold are extracted from the memory, causes a display device to display the plurality of candidate forms for selection of one of the plurality of candidates forms displayed on the display device as the candidate registered form; and

a form processing apparatus that processes the input form in accordance with the type form processing associated with the candidate registered form.

8. A form processing method comprising:

storing stylized forms in a memory as registered forms, and associating with the registered forms a type of form processing to be performed on the form and a degree of difference threshold based on the type of the form processing in the memory, wherein the registered forms are a plurality of forms associated with one of types of form processing to be performed on the registered forms and one of degrees of difference thresholds based on the one of the types of form processings;

comparing an input form to the registered forms and determining degrees of difference between the input form and the registered forms based on results of the comparing;

determining whether the degrees of difference between the input form and the registered forms are less than the degree of difference threshold;

extracting from the memory, as a candidate registered form, at least one registered form among the registered forms in response to determining that the degree of difference between the input form and the registered form is less than the degree of difference threshold;

if a plurality of candidate forms having the degrees of difference less than the degree of difference threshold are extracted from the memory, displaying the plurality of candidate forms for selection of one of the plurality of candidates forms displayed on the display device as the candidate registered form; and

processing the input form in accordance with the type form processing associated with the candidate registered form.

9. A non-transitory computer readable recording medium storing a program causing a computer to execute a process for form processing, the process comprising:

storing stylized forms in a memory as registered forms, and associating with the registered forms a type of form processing to be performed on the form and a degree of difference threshold based on the type of the form processing in the memory, wherein the registered forms are a plurality of forms associated with one of types of form processing to be performed on the registered forms and one of degrees of difference thresholds based on the one of the types of form processings;

comparing an input form to the registered forms and determining degrees of difference between the input form and the registered forms based on results of the comparing;

determining whether the degrees of difference between the input form and the registered forms are less than the degree of difference threshold;

extracting from the memory, as a candidate registered form, at least one registered form among the registered forms in response to determining that the degree of difference between the input form and the registered form is less than the degree of difference threshold;

if a plurality of candidate forms having the degrees of difference less than the degree of difference threshold are extracted from the memory, displaying the plurality of candidate forms for selection of one of the plurality of candidates forms displayed on the display device as the candidate registered form; and

processing the input form in accordance with the type form processing associated with the candidate registered form.