Recent searches

No recent searches

Search options

Not available on photog.social.
photog.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A place for your photos and banter. Photog first is our motto Please refer to the site rules before posting.

Administered by:

Server stats:

245
active users

photog.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.3

#opencv

0 posts0 participants0 posts today
dawn @ Home 🏡

Prepping for my sci-fi inspired data science projects live stream

We decided on the last call to do img classification #CNN w/ #NVIDIA GPUs and #RAPIDS #opencv #cuml #seaborn #cuDF #cupy and started a PRD. I'll share my finished PRD and get to building live for 2 hours.

Wed, July 23 1:15p ET / 12:15p CT / 5:15p GMT

Feel free to come by & say 'hello'

youtube.com/live/2IPZ35XpZaY?s

YouTubeWorkshop Wednesday: Engineering Star Trek with Data ScienceBy The Bajoran Engineer
*
Stéphanie Vilayphiou

strip-p-ed out

A 3 months #research around #patterns to bypass #cctv #facerecognition.
Tested with #opencv.
Project done in the #fabricademy, a programme over textile and technology, at the @greenfabric node.

I knitted 2 kimonos on a #kniterate, a semi-industrial #machineknitting with deadstock yarns. The 3rd one is a deadstock fabric whose pattern was already a working #camouflage for opencv.

The project is fully documented here:
class.textile-academy.org/2024

Concerning cctv surveillance, France has recently gone crazy over it... it seems like they want to recognise logos from organisations in protests and faces associated with them... does someone know an opencv algorithm to detect specific images? Or does it necessarily go through machine learning?

Replied in thread
Feoh

@kevin @beeware This is so awesome.

I'll admit I struggled a bunch with both the open spaces and the sprints listing because they were hand written.

This stinks because I know that allowing humans to make marks with writing implements helps make the whole process feel more organic and genuine, but harder for anyone with vision problems to read.

I wonder if the #python #opencv #ai #ml folks have come up with models to read/parse handwriting yet? :)

Continued thread
dragfyre

After that, the last of the late great dragfyre bots to bring back from the dead would be @laughingman, which tbh is one of my favourites. The problem is, it uses #openCV to detect faces, and I can't run the newest versions of openCV on my potato compy. So that one's going to be considerably more difficult to resurrect. Maybe I'll wait 'til Easter. #bots

Replied in thread
Astatide

( all code adapted from here, if you're interested: docs.opencv.org/3.4/d1/de0/tut )

I'd upload to GitHub but I don't want to upload to *GitHub* specifically; I can certainly try to find another place to upload if anyone is interested! But it's mostly the result of that above link, + using Pillow for some image manipulation (combining the color channels) + rawpy to load the RAF images. I don't think everything is perfect yet

docs.opencv.orgOpenCV: Feature Matching + Homography to find Objects
#python#openCV#photography
*
Brett Edmond Carlock

Do I have anyone in my wider network with skills in programming CUDA, SYCL, and OpenCL?

We want to determine feasibility of migrating CUDA-only code to SYCL (via SYCLomatic?): OpenCV feature detection/extraction modules (SIFT, HAGOG, ORB, AKAZE).

The intent is to upstream all feasible work.

This, hopefully, should stand to benefit everyone instead of being limited to NVIDIA.

Currently in info gathering/people connecting phase, not yet funded & ready to go.

#CUDA#SYCL#OpenCL
Live feeds
About