The Power of 3D Image Processing Software

Image Processing Software is typically used to inspect and evaluate an image, usually for quality and feedback purposes.  To fully realise the potential of the emerging 3D camera hardware, powerful software libraries such as MVTec’s HALCON have evolved to interface with these new imaging devices as well as handle new data types such as 3D point clouds (see Fig1).

3D cameras measure geometrical information rather than intensity or colour.

They can create point clouds where each point represents the coordinates of a point on the surface of an object as X, Y & Z coordinates.

With a point cloud we can determine 3D object features such as;

  • shape
  • position
  • orientation

As the image data is multi-dimensional it is possible to process it like never before and create automated machine vision solutions in an ever increasing range of industries and applications (see Table1)

Typical Applications for 3D inspection
• Optimisation of production processes
• 3D dimensioning, scanning and inspection
• Stacking of boxes and pallets
• Volume measurements
• Intelligent warehousing/shelf organisation
• Luggage/carton sorting and routing
• Robot bin picking
• Visual safety systems
• Automation of production processes
• Autonomous Vehicles



3D Imaging techniques
Depending on the application, there will be a one or more of the following 3D imaging techniques required.

3D reconstruction
Constructing a 3D depth maps or point clouds from image techniques like multi-view stereo, time-of-flight or laser triangulation.

3D registration
Generate a complete 360 degree representation of an object by aligning 3D point clouds from multiple 3D images.

3D object processing
Similar to blob analysis in 2D, developers are able to measure and extract various features from 3D point clouds as well as segment point clouds based on those features. Background points can easily be removed via thresholding and point clouds can be intersected by a plane to create a 2D cross-section profile.

3D Surface-based matching
This tool searches for arbitrarily shaped 3D objects in a scene and determines their pose in 3D space. It locates multiple objects in a single scene even if objects are partially occluded or not entirely contained in the scene. This is a powerful tool for robotic bin picking and automated portioning systems as well as many more 3D machine vision applications.

Fig1. Shows a point cloud image which is cluttered with various objects. Only the points highlighted in green match the object that is being searched for. The data returned from the 3 object matches will include all information required, for example, for a robot to pick ‘n’ place solution.

3D Surface Inspection
Alignment of an acquired 3D point cloud object with a known object model or point cloud template enables users to check for and locate variations and deviations in the surfaces profile of manufactured parts.


Fig2. This is a perfect example of how a complex object can be inspected in 3D for manufacturing errors. In this case, 3D surface inspection algorithms are used to compare the real-world object with a known good object (or 3D CAD file). The red area is highlighting an out of tolerance feature.

Before embarking on a 3D development, there are some important aspect to consider that will help determine the appropriate hardware and software tools required (see Table2)

What do you want to know?
Shape, position, orientation, alignment, presence…
Which degree of accuracy is required?
Micrometers, millimeters, centimeters…
What are the features of the object?
Size, relfectvity, transparency…
What are the general conditions?
Illumination, in-motion, processing time, budget…


Multipix Imaging is happy to offer advice on all aspects of 3D imaging and image processing.
Visit for further information or call 01730 233332 for advice.


[ + ]