Most of the easyTouch-tools available in MERLIC are optimised for processing byte images and generally do not work as expected for other pixel types, such as int1′, ‘int2’, ‘int4’, ‘int8’, ‘real’, and ‘uint2’. This is due to the extreme grey value ranges of non-byte images, and usually leads to a black or black and white visualisation, see fig. 1. a).
Fig. 1 b): The image 1 a) has 2257313 0-gray-values (black background) which are visualised in the first blue bin of the histogram and gray values ranging from 0 to 33376.
 Fig. 1 a): Visualisation of pipe joint on 3D-height image
|  Fig. 1 b): The image 1 a) has 2257313 0-gray-values (black background) which are visualised in the first blue bin of the histogram and gray values ranging from 0 to 33376. |
 Fig. 1 c): Visualisation of the pipe joint based on a grey value range from 26628 to 33376 |  Fig. 1 d): Visualisation of the pipe joint based on a grey value range from 31000 to 33000 |
In order to apply MERLIC’s standard tools to different pixel types, it is highly recommended to convert 3D-height images to byte images. In order to do so, two pre-processing tools are available: Remove Outlier Pixels and Scale Gray Range to 8 Bit.
The conversion of non-byte images to byte images by appropriate scaling should generally be based on the minimal grey value range that describes the working depth. This ensures the preservation of as much information as possible.
Depending on the use case, different approaches for adequate scaling can be used. Below, two different use cases are considered: an alignment task and reading embossed text, see fig. 2.
Fig. 2: Embossed text on pipe joint
For standard alignment tasks, first just determine the region that describes the object of interest. This region can be obtained by applying the tool Remove Outlier Pixels, see fig. 3. Then, use the returned region as Region for Scaling in the Scale Gray Range to 8 Bit.
Fig. 3: The 0-grey values (black background) are removed from the processing region (green) that describes the object.
After the image has been converted successfully to byte format, one of the easyTouch-based alignment tools can be applied, see fig. 4.
Fig. 4: Alignment of objects
However, in order to find smaller defects on the surface or to read the embossed text successfully, a smaller grey value range should be used. In the case of reading embossed text, this minimal grey value range can be determined by drawing a ROI around the text, see fig. 5.
Fig. 5: ROI For scaling (purple) is drawn around the text.
After converting non-byte 3D-height images to byte images, usually smaller structures in the height image will become visible, see fig. 6, due to the reduced range of grey values.
Fig. 6: Image after converting from non-byte pixel types to byte pixel type
Finally, after the 3D-height image has been converted to a byte image, the text can be read by Read Text and Numbers, see fig.7.
Fig. 7: Reading embossed text and numbers
Besides the method shown in our article, two more 3D pre-processing tools are available: Convert Disparity to Height Image, which converts disparity images from stereo cameras to calibrated height images and Level Surface, which levels tilted or curved surfaces.