Up | ImageResampler - 70 | Blob4 - 87 | TemplateFinder3 - 63 | Blob3 - 60 | MultiBlob - 47 | TemplateFinder2 - 44 | TextureMatcher - 53 | PolyLineGapFinder - 49 | ColorSegmentor - 57 | PolygonMatch - 62 | ColorAnalyzer - 80 | PolyLineEdgeFaults2 - 85 | PolarUnwrap - 113 | SurfaceAnalyzer - 91 | ImageMixer - 147 | AreaFilter - 158

Setup | Threshold | Advanced | Constraints | Visualisation | Results | Commands | Shortcuts | Examples | Release Notes


Blob4 - 87

A blob is defined as a region of connected pixels. Blob analysis is the identification and examination of these regions in an computer image. The pixels are divided in one of two categories: the foreground (typically pixels with a non-zero value or white) or the background (pixels with a zero value or white).

In typical applications that use blob analysis, the blob features usually calculated are area and perimeter, diameter, shape, and location.

The versatility of blob analysis tools makes them suitable for a wide variety of applications:

  • pick-and-place
  • pharmaceutical
  • inspection of food for foreign matter
  • counting
  • size measurement
  • identification by shape, position or size

Since a blob is a region of touching pixels, analysis tools typically consider touching foreground pixels to be part of the same blob. Consequently, what is easily identifiable by the human eye as several distinct but touching blobs may be interpreted by software as a single blob. Furthermore, any part of a blob that is in the background pixel state because of lighting or reflection is considered as background during analysis.

Blob4 is a Blob3 with integrated feature classification. A simpler blob tool is included in the Basic toolbox.

The figure below shows a blob that is a continuous area with the same shading limited by a contour, and possibly a number of internal holes.


Hole area 1 = H1
Hole area 2 = H2
Blob area = A
Contour area = A+H


Based on a set of filtering criteria, the Blob4 tool finds one or more (currently up to 32) blobs (areas within a contour) within the region of interest (ROI).

The following results are calculated:

  • General statistics
    • blob count
    • coverage
    • total blob area
  • Properties of the largest blob
    • largest contour area
  • Individual properties for the set of qualified blobs
  • Classification results, if classes are defined

Shape - Size Classification

The image shows the power of feature classification - the pills are easily divided into two classes - pill and half pill.










The tool delivers an output (child) reference coordinate system that is the incoming reference system translated to the center of gravity of, and rotated to the major axis of, the largest (or first, if sorted) blob found.


1: SDP-0076-Box-Picking-from-Conveyor

Scorpion Vision Version XII : Build 646 - Date: 20170225
Scorpion Vision Software® is a registered trademark of Tordivel AS.
Copyright © 2000 - 2017 Tordivel AS.