White Fishing Line

[Tyler W. Davis]

Despite changing LED dimness and shutter speed, there is still a problem with yellow fishing line looking white, which is not correctly subtracted using the current 3D image processing method.

Look into methods for increasing contrast, reducing intensity, etc.

[Tyler W. Davis]

Possible methods to try:

Difference by Blurring

ref: stackoverflow

1. Open image
2. Convert image to grayscale
3. Create a duplicate layer
4. Apply Gaussian blur using a large kernel (10x10) to the top layer
5. Calculate the image difference between the top and bottom layer
6. Threshold the difference image to yield a binary image
7. Erode binary image

K-means Clustering in L*a*b* Color Space

ref: mathworks

1. Convert RGB imaget to L*a*b*
2. Apply K-means clustering on the color channels (i.e., a* and b*), assuming you have three colors in your image (i.e., black background, white foreground and yellow mesh)
3. Remove portions of your image based on the cluster index for yellow mesh

[Tyler W. Davis]

v0.8.0. Addresses #1 - new delta mask does a better job of removing mesh from some sequences. Addresses #2 - delta mask replaces positional mask, which performed poorly.

→ <<cset 8216a3692437>>

[Tyler W. Davis]

The delta mask adequately removes the fishing line; however, reflections off of the flat ends of the metal discs persist. This is not likely to be solved by image masking---possibly by dust filtering (implemented) or feature detection (currently unavailable).