2023:Detect Signature (Value Extractor): Difference between revisions

From Grooper Wiki
Newer edit →
Created page with "{|class="wip-box" | '''WIP''' | This article is a work-in-progress or created as a placeholder for testing purposes. This article is subject to change and/or expansion. It may be incomplete, inaccurate, or stop abruptly. This tag will be removed upon draft completion. |} <!-- <blockquote> The ''Read Zone'' extractor allows you to extract text data in a rectangular region (called a "extraction zone" or just "zone") on a document. This can be a fixed zone, extracting..."
 
No edit summary
Line 8: Line 8:
|}
|}


<!--


<blockquote>
<blockquote>
The ''Read Zone'' extractor allows you to extract text data in a rectangular region (called a "extraction zone" or just "zone") on a document. This can be a fixed zone, extracting text from the same location on a document, or a zone relative to an extracted text anchor or shape location on the document.
The ''Detect Signature'' extractor uses zonal information to detect whether a document is signed or not. It uses many of the same functions as the ''Read Zone'' extractor, so please review the [[Read Zone - 2023]] article prior to following the tutorial in this article.  
</blockquote>
</blockquote>


{| class="wikitable" style="margin:left"
== About ==
! Previous Versions
 
''Detect Signature'' is a zonal extractor specifically designed to detect if a signature is present or not. It's very similar to the Read Zone extractor in that you use one of the four Location options (Fixed Region, Relative Region, Shape Region or Text Region) to draw an extraction zone on a geographic region of the page.
 
However, rather than returning the OCR or native text data within the zone, an OMR-style extraction is performed. Think about a signature line. If you drew a box around where you expect someone to sign, nothing would be in the box if it was not signed. But regardless of the signature, some of the box would be filled in if it were.
 
The same basic concept applies for the Detect Signature extractor. Detect Signature determines this by a simple pixel count of the percentage of black pixels in the zone. Essentially, the extractor counts the number of black pixels in the extraction zone. If the number of black pixels falls above a certain percentage threshold, the extractor returns a value of "Signed" and if below it returns a value of "Not Signed".
 
{|class="attn-box"
|-
|-
|⚠
|
|
[[Read Zone - 2021|Grooper 2021]]
This extractor shares some similarities to the ''Read Zone'' extractor. It is recommended you become familiar with the different aspects of the ''Read Zone'' extractor before configuring the ''Detect Signature'' extractor. For more information, please see the [[Read Zone - 2023]] article.
<br>
|}
|}


== About ==
== How To ==
{|cellpadding=10 cellspacing=5
 
|valign=top style="width:40%"|
In this example, a Value Reader is configured to return whether or not the "Senior Cow Representative Signature" is present on this Application for Cow Ownership form, using the Detect Signature Extractor Type.
 
 
[[File:2023 Detect Signature - 2023 01 How To 01.png]]


''Read Zone'' is useful for extracting data from highly structured documents.  If a document's structure is fixed, it's going to have the same fields in the same physical location from one document to the next. 


[[File:2023 Detect Signature - 2023 01 How To 02.png]]


For instance, the Application for Cow Ownership form to the right seems to be a fairly fixed form. We expect the "Birth Date" listed on the first page to be more or less in the same spot for every single Cow Ownership document. The value itself may change, but there's only so much room that this value can take up on the document.


[[File:2023 Detect Signature - 2023 01 How To 03.png]]


If you can draw a rectangle around the value you want to extract, and the value falls within the boundaries of that rectangle for every single document, extraction may be as simple as just extracting the text in the rectangle's location.  This is referred to as "zonal extraction".  You draw a zone where the value exists on the page and return the text data falling in the zone.
|
[[File:2023 Read Zone - 2023 01 About 01.png|500px|center]]
|}


[[File:2023 Detect Signature - 2023 01 How To 04.png]]


''Read Zone'' has a few different options for where the box is placed using the '''''Location''''' property.  This can be one of four options:


* Fixed Region
[[File:2023 Detect Signature - 2023 01 How To 05.png]]
* Relative Region
* Text Region
* Shape Region


The ''Read Zone'' extractor can optionally re-process the text data with an '''OCR Profile'''.  This can be used to perform custom OCR on the extracted text.


The text in the zone can also be itself extracted by a '''''Value Extractor'''''.  This allows you to break up the document into a smaller portion and run an extractor on just the zone instead of the full document.  Essentially, you use the ''Read Zone'' extractor to create a smaller data instance (from the larger document data instance) and use its '''''Value Extractor''''' property to return data from the smaller data instance.
[[File:2023 Detect Signature - 2023 01 How To 06.png]]


== How To ==


=== The Location Property ===
[[File:2023 Detect Signature - 2023 01 How To 07.png]]


==== Fixed Region ====


This option is the simplest to set up. As the name implies, the extraction zone will be fixed on the page. It will stay in the same coordinates for every document. All you need to do is draw the box where you want to extract data.
[[File:2023 Detect Signature - 2023 01 How To 08.png]]




[[File:2023 Read Zone - 2023 02 How To 01 Fixed Region 01.png]]
[[File:2023 Detect Signature - 2023 01 How To 09.png]]

Revision as of 14:53, 15 December 2023

WIP

This article is a work-in-progress or created as a placeholder for testing purposes. This article is subject to change and/or expansion. It may be incomplete, inaccurate, or stop abruptly.

This tag will be removed upon draft completion.


The Detect Signature extractor uses zonal information to detect whether a document is signed or not. It uses many of the same functions as the Read Zone extractor, so please review the Read Zone - 2023 article prior to following the tutorial in this article.

About

Detect Signature is a zonal extractor specifically designed to detect if a signature is present or not. It's very similar to the Read Zone extractor in that you use one of the four Location options (Fixed Region, Relative Region, Shape Region or Text Region) to draw an extraction zone on a geographic region of the page.

However, rather than returning the OCR or native text data within the zone, an OMR-style extraction is performed. Think about a signature line. If you drew a box around where you expect someone to sign, nothing would be in the box if it was not signed. But regardless of the signature, some of the box would be filled in if it were.

The same basic concept applies for the Detect Signature extractor. Detect Signature determines this by a simple pixel count of the percentage of black pixels in the zone. Essentially, the extractor counts the number of black pixels in the extraction zone. If the number of black pixels falls above a certain percentage threshold, the extractor returns a value of "Signed" and if below it returns a value of "Not Signed".

⚠

This extractor shares some similarities to the Read Zone extractor. It is recommended you become familiar with the different aspects of the Read Zone extractor before configuring the Detect Signature extractor. For more information, please see the Read Zone - 2023 article.

How To

In this example, a Value Reader is configured to return whether or not the "Senior Cow Representative Signature" is present on this Application for Cow Ownership form, using the Detect Signature Extractor Type.










Retrieved from "https://wiki.grooper.com/index.php?title=2023:Detect_Signature_(Value_Extractor)&oldid=16627"