Advantech VisionNavi User Manual page 30

- Set the save destination to SD card
- It temporarily saves it as a memory image, and saves only what you need in the
SSD.
2.3 Preprocessing
Filtering
By filtering the image and performing noise elimination / feature emphasis, an image
easy to post-process is generated.
The following shows the image (top) when binarization is executed without using a fil-
ter and the image (bottom) when binarization is executed after using the filter "
Remove black point ".
By using the filter, you can see that the image from which the noise component has
been removed is obtained.
By filtering images in this way, the following effects can be expected.
Make it easier to detect ambiguous edges
Make it easier to detect small dirt and scratches
Depending on the detection region setting, it is possible to narrow down the region to
be filtered. Processing time can be shorter than filtering over the entire image.
The results of executing several filters using the same image are shown below.
Various effects can be obtained depending on the type of filter and the strength
(level) of the
VisionNavi has 25 types of filters, each of which can specify filter strength in 12 lev-
els.
When you change the filter type and filter strength, the filtering process is immedi-
ately reflected on the selected image.
Filter type list
Averaging
Median
Binomial
Laplacian
Enhancement
Edge extraction
Edge X
Edge Y
Dilation
Erosion
Remove black point
Remove white point
Enhance black point,
Enhance white point
Shading correction
Gauss X
Gauss Y
Contrast flattening
Level correction
VisionNavi User Manual 24