Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

3D scatterplot of an image

alexander.engineering

Post reply on HN
Print view View original

51–60 of 78 posts

Re: 3D scatterplot of an image

#51

Post by btbuildem »

MegaLeon wrote: post #41

Funny to see this, I made more or less the same thing in Processing for the google devart interactive competition a few years ago: https://www.youtube.com/watch?v=YaA3dAJz6sI&feature=youtu.be Has a few extra features like being able to see different visualisation methods and how basic colour correction influences those - also animates the visualisation while going through the image Realluy caught me off-guard because…

Very neat! I like how you aggregate the points with larger objects -- sort of a 3D contour plot.

Do you have an online demo handy?

Re: 3D scatterplot of an image

#52

Post by nitrogen »

thechao wrote: post #24

In the late '90s I was asked to do image segmentation of multispectral data of brightfield microscope data. That is, given a picture of a bunch of cells, find all of the cells. There were two problems: image segmentation of sick cells is really hard (they're very blobby & fragmented), and the computer I had available took more than 20 minutes per image. It was literally both cheaper and faster to have a grad student…

Sounds a lot like the simplifications I made to be able to process 3D Kinect data at near full speed on an ARM CPU with no FPU.

Instead of trying to segment objects, remove backgrounds, do skeleton tracking, etc., just count pixels that fall within a 3D bounding volume.

Simple solutions are sometimes underappreciated. It helps, as you allude to after "let's be clear," to know what problem you really are trying to solve.

Re: 3D scatterplot of an image

#53

Post by _han »

adrianmonk wrote: post #43

"based on the pixel values" I daresay technically this applies to all useful visualizations of the data. I don't think they'd be very useful if they weren't, in some way, based on the pixel values.

Sure, but here the pixel values are directly used as spatial coordinates, so it makes sense to mention this.

Re: 3D scatterplot of an image

#54

Post by the_cat_kittles »

thechao wrote: post #24

In the late '90s I was asked to do image segmentation of multispectral data of brightfield microscope data. That is, given a picture of a bunch of cells, find all of the cells. There were two problems: image segmentation of sick cells is really hard (they're very blobby & fragmented), and the computer I had available took more than 20 minutes per image. It was literally both cheaper and faster to have a grad student…

i love these kinds of problems, because it seems like there is often a really simple solution like that. just finding something different in a very simple feature like color, or shape, or size, or location. there is a reason our brains pay attention to these kinds of things!

Re: 3D scatterplot of an image

#55

Post by psyklic »

There is a really cool use of clustering with these scatterplots to do color quantization (i.e. reducing the number of colors).

If you want 16 colors, just find 16 clusters and their centroids (e.g. let k=16 for k-means clustering). Replace each pixel with the closest centroid. Then, your image is quantized (and can perhaps be stored more efficiently)!

Re: 3D scatterplot of an image

#56

Post by yorwba »

seanlinehan wrote: post #45
crispyambulance wrote: post #31

Earlier quoted context omitted.

Well, there's another neat thing that you can do if you want to generate an interesting 2D -> 2D representation: * Take fourier transform of the image for each color R, G, B * Randomly scramble the phase of the transformed image. * Perform the fourier inverse of that scrambled phase image. The result is another 2D image with the same colors AND spatial frequencies as the original image. It looks like you took the ori…

Do you have any examples of this? Sounds cool

I did a Jupyter notebook http://nbviewer.jupyter.org/github/Yorwba/image_frequency_sc...

I should have probably written more comments, but I really need to go sleep now.

Re: 3D scatterplot of an image

#58

Post by jpfed »

pavel_lishin wrote: post #3

This is cool, but I wonder why most of the demo images - and a lot of the images I uploaded - seem to have their colors aligned in a single plane.

Maybe planar colors make for better-looking images (a more cohesive feel) and the demo images were chosen because they look good.

Re: 3D scatterplot of an image

#60

Post by tovacinni »

thechao wrote: post #24

In the late '90s I was asked to do image segmentation of multispectral data of brightfield microscope data. That is, given a picture of a bunch of cells, find all of the cells. There were two problems: image segmentation of sick cells is really hard (they're very blobby & fragmented), and the computer I had available took more than 20 minutes per image. It was literally both cheaper and faster to have a grad student…

Sorry if this is a stupid question, but can't you do this without converting the image into an RGB 3D space? (i.e. iterate through the pixels and count the ones within a certain range of what you want)
Post reply on HN