Machine Vision Bridge

The following illustration allows an overview based on an abstraction through functional modules.

Instrument Abstraction

Dependent on the acquisition technology, data are provided by the instrument (camera) in different formats. This functional module makes an instrument compatible by abstraction of its acquisition technology.

Instrument Standardization

Interferences caused by the acquisition technology are suppressed and hyperspectral data are corrected. These disorders are depending on the chosen instrument hardware. Such disorders could be:

• read-out noise
• dark current noise
• defect pixels
• wavelength calibration
• ...

Disturbing Influence Suppression

Interferences like the non-uniformity of illumination, which are caused by the measuring setup, are suppressed and data are corrected with regards to application relevant needs.

Hyperspectral Pre-processing

Application of typical (scientifically and industrially established) pre-processing methods to hyperspectral data like filtering, derivative, normalization, etc.

Hyperspectral Feature Extraction and Operation

By Hyperspectral features, information hidden in a spectral curve is described by a single value per pixel. This process leads to dimensional reduction e.g. from a 3 dimensional hyperspectral cube to a 2 dimensional feature image.

Advantages:

• The description of information by feature values is more specific and more understandable compared to investigation into a spectral curve.
• Feature operation often leads to the calculation of new (dependent) features as a function of base features. Often the result is a decision or a class-information like: “spectra are oversteered” or “a spectrum is similar to a referenced material”.

Output Interfacing

Information gained per object pixel is prepared to be compliant to machine vision standard formats.
Supported information formats are:

• Color information (3 values per object pixel)
• Multiple feature information (n values per object pixel)
• Decision information (1 value per object pixel)

To develop applications based on hyperspectral cameras it was usually necessary to seek advice from experts of chemometry and spectroscopy. - Till now! By Chemical Color Imaging hyperspectral cameras are integrated into existing image processing systems. By intuitive configuration options, chemical properties are extracted using established chemometric methods. By combining three properties, a color impression (representing chemical relations information) is generated which is simple to understand and can be processed by image processing methods.

The resulting Chemical Color Image of a scene shows object properties in Chemical Colors which do not represent the physical property color. Instead objects with similar molecular structure are represented by similar colors; different objects by different colors.

Center: CCI-preview of different plastics; right: Chemical Color Image of different plastics. The Chemical Colors correlate with the molecular structure of the samples. The dashed line marks the moment of record shown in the left handed image; Left: Hyperspectral image at a specific moment. Spectral information is shown horizontally and spatial information is shown vertically.