CVision Tech CVision Tech
English French German Italian Japanese Korean Norwegian Polish Portuguese Spanish Swedish Thai Turkish
  • Download
  • Contact
  • Live Chat
  • Store
Store CVision Tech Contact Info
**
  • Home
  • Products
    • PdfCompressor
    • Maestro Recognition Server
    • PdfCompressor Developer’s SDK
    • OCR Engine
    • PDF Optimization Suite for Captiva
    • PDFOptimizer for OpenText Captiva
    • ImageOptimization for Documentum
    • PdfCompressor for Kofax
    • PdfCompressor
  • Solutions
    • File Compression
    • OCR
    • PDF Conversion
    • PDF Linearization
    • PDF/A Compliance for Archiving
      • DocArchiver
  • Industries
    • Banking and Financial Services
    • Tax and Accounting
    • Legal
      • Legal Document Management
      • Specific Needs for Legal Market
      • Specific Needs for Legal Market
    • Government
    • Education
    • Healthcare
    • Insurance
    • Wireless Telecom
    • Scanning Bureaus
    • Web Repositories
    • ASPs
    • News & Media
  • Resources
    • Resource Library
    • PdfCompressor Overview
    • Document Imaging Blog
    • The Visionary Newsletter
    • Compression
    • White Papers
      • PDF/A Document Archiving Primer
        • Challenges and Complexity of Document Archiving
        • Converting Documents to a Standard Electronic Format
        • PDF Evolves into the Electronic Document Standard
        • PDF as a Records Management Document Solution
        • PDF/A: Document Solution for Archiving and RM
      • Advanced Document Compression Primer
        • Reduced Storage Costs
        • Improved Collaboration Capabilities
        • Fully Searchable PDF Files
        • PdfCompressor’s Adjustable Settings
        • PdfCompressor - Complementing Document Management Workflow
      • OCR Software Primer
        • Thresholding within OCR
        • Texture Patterns and Small Fonts OCR
        • OCR, Neural Networks and other Machine learning Techniques
        • OCR, Crytorithms, Cryptograms and Substitution Ciphers
        • CAPTCHA: Human and Machine Readability & OCR
        • OCR & Novel Fonts, Multidirectional and Undersampled Text
        • Relationship between OCR & JBIG2
        • OCR, MRC & JPEG2000
        • Reverse Video & OCR
        • OCR & How they relate to MFPs (MultiFunctional Peripheral devices)
        • Dictionary Lookup and OCR
        • Rating an OCR System
        • Tweaking the System to Optimize OCR Performance
        • Searchable PDF using OCR
        • Electronic File Conversion & OCR
        • Bar Codes, OCR & ICR
        • OCR & Form Recognition
        • Data Extraction with OCR
        • Business Process Automation and How it Relates to OCR
        • OCR-based ROI
        • Towards the Paperless Office
      • JBIG2 Compression Primer
        • The Business Case for JBIG2 Compression
        • JBIG2 Compression Success Stories
        • JBIG2: A short history
        • Digital file formats: The short definition of JBIG2
        • JBIG2 and TIFF compared
        • JBIG2 and JBIG Comparison
        • Essential compression issues
        • Smart Compression Codecs: JBIG2, JPEG2000, and MPEG4
        • JBIG2: The Compression Connection
        • The JBIG2 Standard
        • Lossless, Lossy, and Perceptually Lossless Compression
        • JBIG2 Technical Advantages for Business Solutions
        • JBIG2 Technical Advantages: File Size
        • Efficient Encoding
        • OCR Support within PDF Format
        • PDF Web Optimization
        • Scanner Distortions Resolved
        • JBIG2-Compressed PDF Documents
        • Pattern Matching & Substitution
        • The Dangers of PM&S: Proceed with Caution
        • Verification
        • Halftoning in JBIG2
        • Utilizing a JBIG2 Encoder with No Information Loss
        • Overview: Benefits of PDF Compression and PDF Conversion
        • JBIG2 Compression Summary
    • Product Video Tutorials
      • PdfCompressor Demo Video
      • Maestro Demo Video
  • News & Events
    • Recent News and Events
      • CVISION Releases PdfCompressor 6.6
      • CVISION Releases PdfCompressor 6.5
      • CVISION Technologies will exhibit at Prophet 21 WWUG Conference in New Orleans
    • Industry News
  • Support
    • Support Login
    • System Requirements
    • Documentation
    • FAQs
      • Automatic Licensing Documentation
    • OCR Languages Supported
    • Submit a Ticket
  • About Us
    • Company Information
    • Partners
    • Success Stories
      • File Compression and Dept. of Homeland Security
      • Legal Industry Enjoys Freedom from Paper
      • University benefits from Improved Document Capture
      • Media Organization enjoys benefits of OCR, compression, conversion
      • Law Firm benefits from Auto-Routing & Filing of Image Documents
      • Improved Efficiency for the Legal Industry
      • New York City based law firm accelerates document efficiency with OCR
      • Leading hospital optimizes documents with compression and OCR
      • Global financial company utilizes digital mailroom
      • Energy Consulting and Construction Company Improves Document Accessibility
      • Manufacturing Company Reduces Accounts Payable Costs with Advanced Solution
      • Frontier Farm Credit Optimizes Accessibility with Distributed Capture Solution
      • Technology Company Reduces Storage Costs
      • CVISION Provides American Radio History a PDF Optimization Solution
      • Top 5 Global Financial Firm Processes 1.25 Billion Pages Yearly with PdfCompressor
      • Global Law Firm Resolves Bottleneck of Scanning and OCR with CVISION
      • Leading Distribution Company Realizes ROI Within 6 Months
      • Non-Profit Leverages Compression for Document Workflow
      • Large Government Agency Uses Compression to Accelerate File Transmission and Retrieval
      • Global Credit Card Company Accelerates Merchant Statement Processing Speed
      • Global Power Industry Leader Increases Document Handling Efficiency by More Than 50% with PdfCompressor
      • Argus der Presse Case Study
      • Healthcare Provider Improves Patient Care with Maestro OCR Software for EHR
      • Government Agency Improves OCR Efficiency with PdfCompressor
    • Client Testimonials
    • Customer Feedback
    • Careers
    • Contact
  • Home
  • Resources
  • White Papers
  • OCR Software Primer
  • Thresholding within OCR
 

Thresholding within OCR

Thresholding is the simplest method of grouping an image into regions, aka image segmentation. In the case of thresholding, there are only two types of pixels: foreground and background. Foreground pixels correspond to the text and the background pixels correspond to everything else, such as background texture, embedded images, etc.

Individual pixels in a grayscale image are typically marked as “object” pixels if their value is greater than some threshold value and as “background” pixels otherwise. Typically, an object pixel is given a value of “1” while a background pixel is given a value of “0.” This method employs a static threshold, namely, one value is used to threshold the entire page.

Static Threshold Methods

The key parameter in thresholding is obviously the choice of the threshold. Several different methods for choosing a “static” threshold exist. The simplest method would be to choose the mean or median value of the image, the rationale being that if the object pixels are brighter than the background, they should also be brighter than the average value. In a noiseless image with uniform background and object values, the mean or median will work quite well as the threshold. In many situations, however, this will not be the case.

A more sophisticated approach might be to create a histogram of the image pixel intensities and use the valley point as the threshold. The histogram approach assumes that there is some average value for the background and object pixels, but that the actual pixel values have some variation around these average values. However, computationally this is not as simple as we’d like, and many image histograms do not have clearly defined valley points. Ideally we’re looking for a method for choosing the threshold which is simple, does not require too much prior knowledge of the image, and works well for noisy images.

Semistatic Threshold Methods

Clearly, if the image page contains both video, i.e., dark text on light background, and reverse video, i.e., light text on dark background, then a single static threshold for the page will not suffice. A more complex thresholding algorithm may first try to segment the image into different backgrounds, not assuming a uniform image background. Then, for each background region, a static threshold value is selected. Methods such as this one, that are static for some local region but not for the entire image, are sometimes referred to as semistatic.

Of course, even the above method has its limitations. So for a book page where the background intensity varies smoothly this method may not be appropriate. Undersampled text, or documents that are cell phone scanned, may need special treatment including upsampling prior to thresholding. Gradient methods, akin to edge detection used in computer vision, may sometimes be appropriate for hard to threshold images.

« To Section 2: Document Capture & OCR
To Understanding OCR Technology
To Section 4: Texture Patterns and Small Fonts OCR »

Request Evaluation Download CVISION's Understanding OCR Technology
  • Privacy
  • Cookies
  • Sitemap
  • Reference
  • Library
  • Contact Us
CVISION Technologies Facebook Page CVISION Technologies LinkedIn Company Page CVISION Technologies Twitter Page Subscribe to The Visionary Newsletter CVISION Technologies Blog CVISION Technologies YouTube Channel
 
Copyright © 1998-2018 CVISION Technologies, Inc.
CVISION, CVista, CBatch, and the CVISION logo are registered trademarks of CVISION Technologies, Inc.