Table of contents

Go to DCV Architecture

The following diagram shows how sections connect to each other to form tasks:

flowchart LR;
     A[1.Region Pre-Detection]-->C[2.1.Shared Detection]
     C---D[2.2.Barcode Localization]
     C---E[2.2.Text-line Localization]
     C---F[2.2.Document Detection]
     D---G[3.Barcode Decoding]
     E---H[3.Text-line Recognition]
     F---I[3.Document Normalization]
     style C fill:#f96,stroke:#333,stroke-width:4px

In this article, we’ll discuss the special section - Shared Detection.

Section 2.1 - Shared Detection

As discussed in “Divide Tasks into Sections”, an image-processing task usually consists of three sections. The 2nd section is one of the following three

  • Barcode Localization
  • Text-line Localization
  • Document Detection

Each of these three sections consists of multiple stages and they all start with 11 identical stages which are grouped together with the name “Shared Detection”.

Important NOTE

The section “Shared Detection” is only a concept invented to simplify the explanation of the image-processing workflow. It doesn’t technically exist and is not a member of the parameter Section which are found in SectionImageParameterArray and TerminateSetting, etc. and cannot be assigned to the parameter StartSection.

Constituting Stages

  1. Cropping: to crop out the regions of interest which are found by the previous section “Region Pre-detection”. If no such region was found, return the original image as a whole.
  2. Down-scaling: to down-scale a massive image.
  3. Grayscaling: to convert a colour image to grayscale.
  4. Transforming: to transform a grayscale image.
  5. Enhancing: to improve the quality of a grayscale image.
  6. Binarizing: to convert a grayscale image to black & white.
  7. Texture-detecting: to detect texture on a binary image.
  8. Texture-removing-1: to remove the texture of a grayscale image.
  9. Texture-removing-2: to remove the texture of a binary image.
  10. Text-zone-detecting: to find the exact locations of text zones.
  11. Text-removing: to remove text from a binary image.

Output and Parameters

Each of these stages has its own output (known as an intermediate result) and usually a specific parameter that can regulate the operation:

Stage Intermediate Result Type Related Parameter
Down-scaling IRUT_SCALED_DOWN_COLOUR_IMAGE ScaleDownThreshold
Grayscaling IRUT_GRAYSCALE_IMAGE ColourConversionModes
Transforming IRUT_TRANSFORMED_GRAYSCALE_IMAGE GrayscaleTransformationModes
Enhancing IRUT_ENHANCED_GRAYSCALE_IMAGE GrayscaleEnhancementModes
Binarizing IRUT_BINARY_IMAGE BinarizationModes
Texture-detecting IRUT_TEXTURE_DETECTION_RESULT TextureDetectionModes
Text-zone-detecting IRUT_TEXT_ZONES TextDetectionMode

This page is compatible for:

Version 1.0

Is this page helpful?

YesYes NoNo

In this article:

latest version

    • Latest version (2.2.30)
    • Version 2.x
      • Version 2.2.20
      • Version 2.2.10
      • Version 2.2.0
      • Version 2.0.30
      • Version 2.0.20
      • Version 2.0.10
      • Version 2.0.0
    Change +
    © 2003–2024 Dynamsoft. All rights reserved.
    Privacy Statement / Site Map / Home / Purchase / Support