It is observed that in a production level digitization scenario, manual quality check of scanned images never achieves 100% correct results. In the best case 90% accuracy can be achieved. The residual 10% can sometimes lead to huge business risks specially in cases of regulatory requirement or compliance. Newgen’s Document Quality Analyzer(DQA) (patent pending) and Automatic Document Correction significantly reduces this risk to less than 1% by automatically flagging and correcting more than 25 types of errors.

DQA is a fully automated system to analyze the quality of the scanned document. The system exclusively focuses on ascertaining the document quality based on a list of pre-determined unique list of configurable parameters.

The system comprises of unique set of features, with specific parameter values to gauge the image quality of the document. Once the quality is known, the document can either be accepted for further processing or a request can be immediately sent to rescan the poor-quality document.

Why Document Quality Analyzer?

  • Ensure quality legible documents for business applications even if acquired through
    • Single / Multiple Outsourced Vendors
    • Different Internal Departments
  • Avoid hefty penalties imposed by regulators
  • Service customers on time
  • Service decision makers on time
  • High rescan cost if unusable document found at a later date

Inconsistent Scanning Quality – Causes

  • Different scanning vendors and scanner models
  • Faulty Scanners
  • Improper Environment
  • No single right configuration for all document types
  • Production pressure
  • Storage limitation
  • Unskilled scanning operator
  • Manual QC done on a sample basis
  • Unavailability of automatic scanning quality analyzer


(A) Image related Parameters:

  1. Too Dark/Too Light
  2. Skew
  3. Wrong Orientation
  4. Too much Noise
  5. Double Page
  6. Photo on B&W
  7. Blank Page
  8. Error in Automatic Cropping
  9. Readability Index
  10. Quality of Photographs
  11. Punch Hole Marks
  12. Stapler Marks
  13. Proper Margins
  14. Black Bands

(B) Scanning related Parameters:

  1. Piggy Back/Multi-feed
  2. Folded corner
  3. Torn document
  4. Dark/Light
  5. Out of Focus

(C) Format/Data

  1. Improper resolution
  2. Format/ compression not proper
  3. Dimensions
  4. Size of File


  1. Improper resolution
  2. Format/ compression not proper
  3. Dimensions
  4. Size of File
  5. Skew
  6. Wrong Orientation
  7. Noise
  8. Double Page
  9. Error in Automatic Cropping
  10. Punch Hole Marks
  11. Stapler Marks
  12. Proper Margins
  13. Black Bands