Zone OCR is used to read document indexes or tags from text on the page. It is a great way to automate the data entry associated with scanning documents.
However, there are several limitations to zone OCR that must be overcome:
- Index information must be in the exact same place on every page
- Documents shift and skew during scanning, causing the zones to not line up
- If surrounding lines or text on the document are too close, they can encroach on the zone
Change the Dictionary Separator Value
This is used to change the dictionary separator value when doing thesaurus matching from the default character of | to any character(s) that you want. This can be useful in cases where the values you would like in your list or dictionary might include the pipe character or “|” or “Shift Backslash”
This setting is also used as the delimiter when parsing multiple index field values from bar codes (e.g. field1|field2|field3).
Instructions for changing the dictionary separator value:
- Right click on the Job Configuration file that you would like to suppress the prompt on and select Open With>Notepad
- Search the XML settings text open in Notepad for this term:
<OCR_DICT_SEPARATOR> - Change the value in-between from “|” to any other single character that you want.
- For TAB separation use %TAB%
Change the OCR Font or Type
This is used to changed the default OCR recognition font or type from the default, which is “To Be Detected”. This can be used to look for a specific type of OCR font and is especially useful for recognizing things like Dotmatrix, OCR A and OCR B.
Instructions for setting OCR Font:
1. Right click on the .sic file and select Open With a text editor (Notepad, Wordpad, etc.)
2. Find <OCR_TEXT_TYPE>. If you can’t find <OCR_TEXT_TYPE> then add the following as the last row in the text file:
<OCR_TEXT_TYPE>#</OCR_TEXT_TYPE>
3. Change the number in between: <OCR_TEXT_TYPE>#</OCR_TEXT_TYPE>
4. Number of desired font:
- 0 Normal
- 1 Typewriter
- 2 Dotmatrix
- 3 Index
- 5 OCR A
- 6 OCR B
- 7 MICR E13B
- 8 MICR CMC7
- 9 Gothic
- 10 To Be Detected
5. Close and save file
I’m using full page OCR. The information is all appearing in the txt file but it is losing format about half way through. Data to the right is ending up at the end of the txt doc. Can this be fixed?
SimpleIndex version 7 solves this problem with the incorporation of the FineReader OCR engine. Full text in PDFs will now flow with the formatting of the PDF.
Legacy Versions: SimpleIndex can also be used with other OCR applications and servers to improve accuracy, formatting and performance. Use the OCR applications to convert the scanned images to text or searchable PDF, and SimpleIndex can extract index values from the text and automatically sort and organize the files.
- Published in OCR
How do you train the OCR engine for better accuracy?
Training has been removed with version 7 due to the addition of the ABBYY FineReader OCR engine.
- Published in OCR
How do you configure full text searching in Retrieval mode?
On the Database tab there dropdown in the lower portion of the panel for Full Text OCR Field. Put the name of the field that will store the full-text data there. This must be configured both for Insert and Retrieval mode configurations. The database field needs to be sufficient length to store the entire text of your document.
Of course, the Insert Mode configuration must have “Enable Full Page OCR” checked to generate full text data from images. Text from MS Office documents, PDF files and existing OCR text files can be used without setting this option.
When designing your Retrieval Mode configuration, create a Text field to use for full text search queries. On the Database tab, set the corresponding “Database Field Name” to the full text database field.
When searching on your full text field, SimpleIndex finds the text you enter no matter where it appears in the document. It is able to match partial words. It does not perform boolean or natural language searches. The text entered must match the document text exactly.
- Published in Database & Retrieval, OCR
How can I improve recognition rates for my OCR fields?
There are several things you can do to improve accuracy for OCR.
-Scan at 300dpi, black & white for best results.
-Adjust the scan settings to remove background noise and improve the definition of characters.
-For Zone OCR, field recognition can often vary based on the surrounding white space and text in the zone. Try varying the size of the zone to achieve optimal results.
-For template matching, make sure all variations of the field format are included in the template list.
-For dictionary matching, add common variations and OCR mistakes to the “thesaurus” list.
-On the Zones & OCR tab (accessed from the Job Options) you can adjust the Max Errors setting to allow for more mistakes in the dictionary matching process.
-Use the Strip Spaces, Strip Characters, Replace Characters and Case Fixing options to standardize the field format prior to matching.
Please refer to the manual for details on how to configure these options.
Find out more about Optical Character Recognition on the SimpleOCR Guide. You may also check out our Advanced OCR Guide to find out how to use third-party OCR applications with SimpleIndex.
- Published in OCR
Can OCR text be saved to MS Word or HTML formats?
Yes. On the Zones & OCR tab of the Job Options, there is a dropdown list for “Full-page OCR file type”. By default it is set to TEXT, but can be changed to WORD, HTML or PDF.
If the output file type is set to PDF, OCR text will be embedded as hidden text in the PDF file.
Find out more about Optical Character Recognition on the SimpleOCR Guide.
- Published in Licensing & Installation, OCR
Can SimpleIndex create searchable PDF Image+Text files with hidden text?
If you enable full-page OCR and output to PDF, the full-page OCR text will be inserted as invisible text on each page.
With the addition of the FineReader Engine in version 7, SimpleIndex now creates PDF files with fully searchable text formatted to flow with the image of the document.
Find out more about Optical Character Recognition on the SimpleOCR Guide.
- Published in Export, OCR, Office PDF Text Processing
Indexing from Applications with Screen OCR
Some documents are difficult or impossible to automate with OCR. For example, documents with non-standard layouts, unconstrained handwriting or very poor scan quality. In applications like invoice processing, fully automating the data entry can require expensive software and weeks of consulting. Even after all that expense, many users miss the interface and data validations that their accounting software entry screens provide.
In cases like this, SimpleIndex can help improve data entry efficiency while archiving your scanned originals at the same time. Here’s how it works:
- Scan a batch of documents for data entry
- Place the SimpleIndex window side-by-side with your data entry window
- Enter the data normally, reading from the scanned image in SimpleIndex
- Press the hotkey combo to transfer the data to SimpleIndex
- Save the image and repeat with the next one
In this configuration, SimpleIndex captures an image of the data entry window, then uses OCR to read the data and index the image. Since the data entry screen has a consistent layout and clear, readable fonts, it can be reliably recognized with OCR.
There are several advantages to this approach:
- Configuration and training takes hours not weeks
- Scanned images are indexed with no extra work
- All the advantages of digital docs–security, searching, sharing, etc.
- Use all the data validation features of your software
- No flipping through paper documents
- Operator keeps eyes on the screen and hands on the keyboard
- Data entry can be done remotely
- Data entry performance improves and files are archived at the same time
Invoice Processing with Full Page OCR
This job configuration uses a 3-step process to automate the OCR processing:
Step 1 uses a full-page OCR process on each image. Field data is extracted from the full-page OCR using template and dictionary matching algorithms. This is done in Pre-Index mode to allow unattended processing. Data is saved to a database so it can be reviewed and corrected in Step 2.
Step 2 uses Database Update mode to find images with missing index values and allow the user to manually enter the correct data.
Step 3 uses a SimpleSearch configuration to search and view the indexed images, including full text searches.
FAQ Related to Invoice Processing
Coming SoonZone OCR with Template Matching
This video shows the Zone OCR Invoice Processing sample job. Zone OCR is the traditional method for extracting index data from printed text appearing in fixed locations on every page.
The video also shows how Zone OCR is enhanced with SimpleIndex‘s Template Matching and Dictionary Matching features, giving you much more margin for error than other solutions.
FAQ Related to Zone OCR
Coming SoonZone OCR and Dynamic OCR
Many document scanning solutions use Zone OCR to obtain index data from the page, while SimpleIndex improves upon this time-tested but ultimately limited model with its unique Dynamic OCR feature. Let’s look at the difference between the two methods:
Zone OCR
Zone OCR is used to read document indexes or tags from text on the page. It is a great way to automate the data entry associated with scanning documents.
However, there are several limitations to zone OCR that must be overcome:
- Index information must be in the exact same place on every page
- Documents shift and skew during scanning, causing the zones to not line up
- If surrounding lines or text on the document are too close, they can encroach on the zone
Dynamic OCR
SimpleIndex overcomes these limitations by using Dynamic OCR technology to locate the desired text even when it moves around on the page. Our simplified version of Dynamic OCR works great for many types of documents at a fraction of the cost of other solutions.
- Index information can appear anywhere on any page
- Unwanted characters are automatically ignored
- Find unique patterns of letters and numbers using Template Matching
(Social Security #, Date, etc.) - Use Dictionary Matching to find a value from a list of possible values
(Vendor Name, Document Type, etc.)
Dynamic OCR Examples
In the video we see how SimpleIndex approaches a typical Zone OCR example. With SimpleIndex you can use large zones that give a wide margin for error. Template and Dictionary matching are then used to extract the 7-digit Account Number, 6-digit Order Number and Company Name. SimpleIndex discards the surrounding text and keeps the correct value.
Another common example is finding a unique identifier, for example a social security number, that could appear anywhere on the page. Simply enter the template ###-##-#### and SimpleIndex will search the full OCR text until it finds a match. Since only one social security number is likely to appear on the page, a match on this pattern is almost certainly the required value.
With dictionary matching, you can give SimpleIndex a list of possible values and it will automatically search the zone or page for each possible value until it finds a match.
Many dynamic forms processing applications can be implemented using these simple algorithms. This makes SimpleIndex far more versatile than other zone OCR solutions that require the index value to be in the exact same location on every page. Yet SimpleIndex costs only a fraction of the price!
SimpleIndex‘s dynamic forms processing can greatly speed up data entry by eliminating a good percentage of indexing work. For many this can put the labor cost of scanning within their reach.
Dynamic OCR can also be applied to MS Office and PDF files, creating a fully automated process for intelligently indexing and reorganizing electronic documents.
Support for Regular Expressions
SimpleIndex OCR has a simple built-in template format, as well as support for Regular Expressions. Regular Expressions (RegEx for short) let you define complex search patterns to extract matching values from the text. This greatly enhances the functionality of the dynamic OCR in SimpleIndex, making it capable of finding variable-length fields with no distinct pattern.
Regular Expressions are a commonly used in text parsing applications. The Perl programming language makes extensive use of RegEx, as do UNIX utilities like “grep”. Many programmers and IT personnel are already familiar with RegEx and can create complex expressions without specific training.
Click here for a reference guide to Regular Expressions
New OCR Features in Version 9
- OCR language pack now includes all available Tesseract languages including Hindi, Tamil, Arabic, Chinese, Thai, Vietnamese, Japanese, Korean, Indonesian, Hebrew and many more.
New OCR Features in Version 8
Versions 7 and above include the industry leading ABBYY FineReader® OCR engine for dramatically improved OCR accuracy and speed. Other OCR enhancements in version 8+ include:
- Point & Click OCR
- Tesseract OCR Engine now included with all license versions
- Match OCR index fields against other index fields
- Skip OCR processing on imported files that already include text, such as PDF + Text files for faster batch times
How to Configure SimpleIndex OCR
Watch this Simple Software University training video to see how to configure and run an OCR job with SimpleIndex.
KB Articles for Optical Character Recognition (OCR)
- Languages Supported in SimpleSoftware OCR Engines
- What is Document Imaging?
- Change the Dictionary Separator Value
- Change the OCR Font or Type
- Regular Expression (RegEx) - Syntax or Type
- Autonumber Increment Value
- I'm using full page OCR. The information is all appearing in the txt file but it is losing format about half way through. Data to the right is ending up at the end of the txt doc. Can this be fixed?
- Is there a way to just use part of a bar code or OCR value? For example, extract "50" from the value "124450"
- If I have a form which is filled manually by hand, can SimpleIndex read the data from it?
- How do you train the OCR engine for better accuracy?
Compare Leading Solutions
SimpleIndex™
Kodak Capture Pro™
Kofax Express™
PaperVision™ Capture Desktop
Note: This video depicts PaperVision Capture Desktop, a now discontinued software that has since been replaced by the similarly functioning updated version of PaperFlow.
Office Gemini DiamondVision™
Testing Methods
The benchmark times were recorded using all available software shortcuts, and by performing data entry and user interactions as fast as possible. The same scanner and computer hardware was used for each test. Much care was taken to ensure that each application yielded the most accurate OCR results possible given the sample documents. Unfortunately none our competitors could accurately capture the account number on all 10 pages. The extra time to correct these errors accounts for 15-30% of the difference in processing times. The difference in accuracy is due in large part to SimpleIndex‘s pattern matching OCR feature, which the other programs lack.
Video Demos
These videos demonstrate several ways SimpleIndex® can automatically index different types of documents. If you are new to SimpleIndex, watching these videos is the easiest way to see what it can do. You can follow along using the sample files included in the SimpleIndex Trial.
- Zone OCR with template matching
- Document barcode recognition
- PDF OCR text parsing
- Sort and index MS Office documents
- Indexing with full-text OCR
- Running jobs from an icon
The sample files are copied to your Configuration Folder when you run the SimpleIndex Trial for the first time. If you can’t find the samples, copy them with the Global Settings Wizard in the File menu.
Compare Major Scanning Solutions
Integrated Solutions Built with SimpleIndex
Zone OCR with Template Matching
Document Barcode Recognition
PDF OCR Text Parsing
Sort and Index MS Office Documents
Full Page OCR Invoice Processing
KB Articles for Optical Character Recognition
- Languages Supported in SimpleSoftware OCR Engines
- What is Document Imaging?
- Change the Dictionary Separator Value
- Change the OCR Font or Type
- Regular Expression (RegEx) - Syntax or Type
- Autonumber Increment Value
- I'm using full page OCR. The information is all appearing in the txt file but it is losing format about half way through. Data to the right is ending up at the end of the txt doc. Can this be fixed?
- Is there a way to just use part of a bar code or OCR value? For example, extract "50" from the value "124450"
- If I have a form which is filled manually by hand, can SimpleIndex read the data from it?
- How do you train the OCR engine for better accuracy?