MVTec Software GmbH
 

Blob Analysis

Featured in HALCON and MERLIC
Demo of blob analysis in action
Live demo about how fast and robust blob analysis works with MVTec products.

A fundamental image processing function is called blob analysis. It is the extraction of features from connected pixels that share the same logical state (blobs). MVTec’s software products contain a comprehensive collection of operators and tools that provide extreme flexibility and performance for the segmentation and analysis of many types of object features. MVTec’s software allows developers to define blobs of arbitrary shape (even if they are not connected) as Regions of Interest to which subsequent image processing operations are applied. This powerful method significantly reduces processing overhead and improves efficiency and execution speed compared to operating on regions defined by basic shapes like polygons or circles.

MVTec software performs blob analysis within milliseconds. Even when dealing with more complex images showing, for example, partially overlapping parts you want to measure. MVTec software provides many flexible tools for image segmentation like hysteresis, local, binary, and standard thresholding, along with over 20 additional segmentation operators. It also includes analysis functions for determining area, orientation, and about 50 more shape and gray value features.

A blob analysis mainly consists of three steps:

1. Acquire Image(s):

An image is acquired.

2. Segment Image(s):

Isolating the foreground pixels of interest from the image background using preprocessing tools and operations like thresholding and others. This is also called segmentation.

3. Extract Features:

Features like area (i.e., the number of pixels), center of gravity, or the orientation of a blob or blobs are calculated.

Blob Analysis
Original image.
Blob Analysis
Extracted blobs with calculated center
points.

The figure on the right shows tissue particles in a liquid. These particles are bright and the liquid (background) is dark. By selecting bright pixels (thresholding) the particles can be detected easily.

In many applications the contrast of dark and bright pixels may not be as good, but the same results can be achieved with extra pre-processing or alternative methods for pixel selection / grouping.

View Related References

25. Apr 2016 References

Vision System Checks Surface Mount Resistors - Envisage Systems

A vision system checks surface mounted resistors for defects such as blemishes, cracks, and scratches.

07. Sep 2013 References

Vision Q.400 – The Universal Inspection Software for Industrial Image Processing

The software package Vision Q.400 from Q.VITEC was first created 20 years ago in cooperation with MVTec. Since this time, it has been continuously...

02. Sep 2013 References

Vision System Inspects X-ray Dosimeter Badges – Helmholtz-Zentrum

In Germany, the inspection of x-ray dosimeters worn by people who may be exposed to radiation is a governmental responsibility. Only a handful of...

25. Aug 2013 References

Structured-light-based vision system inspects percussion caps – Tekniker

The Centro Tecnológico Tekniker has developed a very fast system to inspect percussion caps.

Percussion caps are a critical component used in...

24. Aug 2013 References

Circuit Breakers – Sensata

GigE camera, special oven, and image-processing algorithms test snap point of bimetal disks.

22. Aug 2013 References

Closing the Ring – NP Plastics

FireWire cameras, LED lighting, and software check for defects on plastic rings used to secure binders.

18. Aug 2013 References

The Industrial Inspection System for Board Implementation VARIR, Developed by Sony

Sony EMCS Corporation Kohda TEC is the leading manufacturer of electronic boards inspection systems in the world, and part of Sony, Japan.