Nice face recognition

Client: how much for a face recognition system?
...
Client: well fuck you that's too expensive, I ll have my nephew do it.

I somehow want to make an ai that analyses porn videos and learns to distinguish the parts when he cums on her face. I would call it facial recognition.

Sorry.

AI developers be like

The best motivation to quit Image Classification... x_x

Face recognition + login with face on web

Just to clarify thing, FaceID isn't the same tech as what we've had on Android.

In Android, it's based on image recognition. That's the reason it was so easy to bypass with a high resolution photograph.

In FaceID, it projects thousands of dots on your face and creates a depth inclusive map which is used for verification. That's the reason why it's supposed to work even if you have glasses on, etc

So please let's stop with the comparison

AI robo revolution 😁

Send help..

The project we're currently working on:

- an angular codebase that's broken beyond recognition - nothing's working as it should

- user stories are estimated in hours, but estimations are treated as hard facts. Since the app is so broken, everything takes longer than usual and it's almost impossible to consider every potential hardship during refinements, therefore, we constantly need more time than we have estimated

- retrospectives (intentional plural here, since one time isn't enough) are used to discuss why we cannot manage to finish tickets within the estimations

- the design was made beforehand and is extremely inconsistent and inaccessible

- if you open a new ticket, you need to add a reason for why this ticket is needed - in addition to the ticket description..

- The moment you move a ticket to QA, the "Scrum Master" breathes down your neck, shoving new tickets in your face. Despite having to finish up the other two you're still working on

- multiple teams are working on the application, but - of course - communication is overrated.

I could go on, but I'm too tired..
We were supposed to help the client for a couple of months - we're close to a year now and still nowhere near done.

"So Alecx, how did you solve the issues with the data provided to you by hr for <X> application?"

Said the VP of my institution in charge of my department.

"It was complex sir, I could not figure out much of the general ideas of the data schema since it came from a bunch of people not trained in I.T (HR) and as such I had to do some experiments in the data to find the relationships with the data, this brought about 4 different relations in the data, the program determined them for me based on the most common type of data, the model deemed it a "user", from that I just extracted the information that I needed, and generated the tables through Golang's gorm"

VP nodding and listening intently...."how did you make those relationships?" me "I started a simple pattern recognition module through supervised mach..." VP: Machine learning, that sounds like A.I

Me: "Yes sir, it was, but the problem was fairly easy for the schema to determ.." VP: A.I, at our institution, back in my day it was a dream to have such technology, you are the director of web tech, what is it to you to know of this?"

Me: "I just like to experiment with new stuff, it was the easiest rout to determine these things, I just felt that i should use it if I can"

VP: "This is amazing, I'll go by your office later"

Dude speaks wonders of me. The idea was simple, read through the CSV that was provided to me, have the parsing done in a notebook, make it determine the relationships in the data and spout out a bunch of JSON that I could use. Hook it up to a simple gorm golang script and generate the tables for that. Much simpler than the bullshit that we have in php. I used this to create a new database since the previous application had issues. The app will still have a php frontend and backend, but now I don't leave the parsing of the data to php, which quite frankly, php sucks for imho. The Python codebase will then create the json files through the predictive modeling (98% accuaracy) and then the go program will populate the db for me.

There are also some node scripts that help test the data since the data is json.

All in all a good day of work. The VP seems scared since he knows no one on this side of town knows about this kind of tech. Me? I am just happy I get to experiment. Y'all should have seen his face when I showed him a rather large app written in Clojure, the man just went 0.0 when he saw Lisp code.

I think I scare him.

Regarding Article 13 (or 17 or wherever it moved to now)… Let's say that the UK politicians decide to be dicks and approve the law. After that, we need to get it engineered in, right? Let's talk a bit about how.. well, I'd maybe go over it. Been thinking about it a bit in the shower earlier, so.. yeah.

So, fancy image recognition or text recognition from articles scattered all over the internet, I think we can all agree.. that's infeasible. Even more so, during this lobby with GitHub and OpenForum Europe, guy from GitHub actually made a very valid point. Now for starters, copyright infringement isn't an issue on the platform GitHub that pretty much breathes collaboration. But in the case of I-Boot for example, that thing from Apple that got leaked earlier. If that would get preemptively blocked.. well there's no public source code for it to get compared against to begin with, right? So it's not just "scattered all over the internet, good luck crawling it", it's nowhere to be found *at all*.

So content filtering.. yeah. Nope, ain't gonna happen. Keep trying with that, EU politicians.

But let's say that I am a content creator who hates the cancer of joke/meme because more often than not it manifests itself as a clone of r/programmerhumor.. someone decides to freeboot my content. So I go out, look for it, find it. Facebook and the likes, make it easier to find it in the first place, you dicks. It's extremely hard to find your content there.

So Facebook implements a way to find that content a bit easier maybe. Me being the content creator finds it.. oh blimey! It can't be.. it's the king of freebooting on Facebook, SoFlo! Who would've thought?! So at that point.. I'd like to get it removed of course. Report it as copyright infringement? Of course. Again Facebook you dicks, don't make it so tedious to fill in that bloody report. And look into it quickly! The videos those SoFlo dicks post is only relevant in the first 48h or so. That's where they make the most money. So act more quickly.

So the report is filled, video's taken down.. what else? Maybe temporarily make them unable to post as a bit of a punishment so that they won't do it again? And put in a limit to the amount of reports they can receive. Finally, maybe reroute the revenue stream to the original content creator instead. That way stolen content suddenly becomes free exposure! Awesome!

*suddenly realizes that I've been talking about the YouTube copyright strike system all along*

… Well.. maybe something like that then? That shouldn't be too hard to implement, and on YouTube at least it seems to be quite effective. Just imagine SoFlo and the likes that are repeat offenders, every 3 posts they get their account and page shut down. Good luck growing an audience that way. And good luck making new accounts all the time to start with.. account verification technology is pretty good these days. Speaking of experience here, tried bypassing Facebook's signup hoops a fair bit and learned a bit about some of the things they have red flags on, hehe.

But yeah, something like that maybe for social media in general. And.. let's face it, the biggest one that would get hurt by something like this would be Facebook. And personally I think it's about time for that bastard company to get a couple of blows already.

What are your thoughts on this?

This pretty much sums up yesterday's Apple keynote.

python machine learning tutorials:
- import preprocessed dataset in perfect format specially crafted to match the model instead of reading from file like an actual real life would work
- use images data for recurrent neural network and see no problem
- use Conv1D for 2d input data like images
- use two letter variable names that only tutorial creator knows what they mean.
- do 10 data transformation in 1 line with no explanation of what is going on
- just enter these magic words
- okey guys thanks for watching make sure to hit that subscribe button

ehh, the machine learning ecosystem is burning pile of shit let me give you some examples:

- thanks to years of object oriented programming research and most wonderful abstractions we have "loss.backward()" which have no apparent connection to model but it affects the model, good to know
- cannot install the python packages because python must be >= 3.9 and at the same time < 3.9
- runtime error with bullshit cryptic message
- python having no data types but pytorch forces you to specify float32
- lets throw away the module name of a function with these simple tricks:
"import torch.nn.functional as F"
"import torch_geometric.transforms as T"
- tensor.detach().cpu().numpy() ???
- class NeuralNetwork(torch.nn.Module):
def __init__(self):
super(NeuralNetwork, self).__init__() ????
- lets call a function that switches on the tracking of math operations on tensors "model.train()" instead of something more indicative of the function actual effect like "model.set_mode_to_train()"
- what the fuck is ".iloc" ?
- solving environment -/- brings back memories when you could make a breakfast while the computer was turning on
- hey lets choose the slowest, most sloppy and inconsistent language ever created for high performance computing task called "data sCieNcE". but.. but. you can use numpy! I DONT GIVE A SHIT about numpy why don't you motherfuckers create a language that is inherently performant instead of calling some convoluted c++ library that requires 10s of dependencies? Why don't you create a package management system that works without me having to try random bullshit for 3 hours???
- lets set as industry standard a jupyter notebook which is not git compatible and have either 2 second latency of tab completion, no tab completion, no documentation on hover or useless documentation on hover, no way to easily redo the changes, no autosave, no error highlighting and possibility to use variable defined in a cell below in the cell above it
- lets use inconsistent variable names like "read_csv" and "isfile"
- lets pass a boolean variable as a string "true"
- lets contribute to tech enabled authoritarianism and create a face recognition and object detection models that china uses to destroy uyghur minority
- lets create a license plate computer vision system that will help government surveillance everyone, guys what a great idea

I don't want to deal with this bullshit language, bullshit ecosystem and bullshit unethical tech anymore.

our government's work documentation is digital now. 2 hours to convince a facial recognition app that i have a face just so i can start my job. fucking hell

OpenCV based face / eye recognition implemented in a discord bot.

FAVOURITE real time face recognition library?

I have an internship at some research company. My point is making face recognition apps with prog lang I know. This place is awesome. Well, compsci it's not my background, but I met many people. And they are great at math ....
.....

... Like they do 29 gray-scale images as a vector for PCA algorithm with size 64x64 pixel and COUNT A COVARIANCE MATRIXES WITHOUT TOUCHING ANY CALCULATOR OR PEN AND PAPER AND GET THE RIGHT NUMBER!

Man, this is insane. I don't even know 64x64. I love compsci

Asus critical update! Fucking handwriting recognition... So they're now employing the same tactics as criminals trying to get you to install a virus.

"Whoa, critical? I'd better stop whatever I'm doing and update, I sure am grateful that they tabbed me out of whatever unimportant crap I was doing before and shoved this popup in my face!"
-no one, ever

That shit is about as critical as birth control to a nun. Kindly fuck off with your pop ups and go work on something actually critical like my battery not exploding 6 months after buying it.

Data scientists unite!
I am working on a face recognition solution to identify and tag different faces in real time and currently using chinese whispers algorithm for clustring. The more I think about it the more inadequate it sounds (number of faces encoded increase over time thus the complexity). I've heard about YOLO but cant really decide. Please enlighten me!

!rant
My dad wants to add security cameras in our home. I kind of want to go ahead and add cool stuff(like automation or something) to our house using this opportunity.
What I am thinking of right now is salvaging an old desktop with an Nvidia GPU to add face recognition and motion detection to the mix. I am also thinking I could get an Alexa echo dot or something similar and hook everything up. Another idea is using owncloud to create my own cloud.
What do you guys think? Any ideas or suggestions? Maybe a cheaper way to do stuff?

It should be completely acceptable to not have your picture taken or spread through the internet.

I'd love a feature in Facebook / Instagram that uses face recognition to forbid people from uploading my photos if I want to. It should be required by law on all social media.

So I am opencv curious. I started wondering how to train a recognition model for a particular part of the body. Everything I search wants to talk about body recognition and face recognition. I did find one article that talks about training say for hands or feet or body posture. So to satisfy my curiosity I am going to be playing with opencv this weekend. I think it will be fun!

Every little positive thing has a cumulatively encouraging effect on the mind

It may not balance out the bad in someone's life

It may cause a diseased mind discomfort at first

But in the end in the former case it's better than not to have things that reinforce a sense of well being

And in the latter a mind caused discomfort by happy things is one that is used to hiding in its own misery to avoid its own pain and the recognition of that pain dragging it slowly out of it's mopey bleak existence is the first step towards self betterment

I thought of this as previously over the smile my fitness app brought on my face saying 'beyond awesome'

It's nice to have little reinforcers

And to all the bitter hateful disgusting garbage that takes joy in making any and all causes of joy except their own dysfunctional warped interests please get fucked to death with a steel pole with a wide hook on the end 😁

Started playing with Microsoft Cognitive Services for face recognition. I’m quite impressed. Any others I should look at.

Need help with selecting a proper backend and website frameworks. After trying out a couple identity verification service providers we were dissapointed with their lack of support (takes weeks to do minimal changes).

So now we are having discussions about building in-house id verification system. We already have libraries for ios/android apps (ZOOM lib for face recognition and another lib for data extraction via OCR from document picture). So what we need is a proper backend and then a decent web framework with proper ux/ui design for our web/ios/android apps.

Currently thinking what kind of backend framework should we choose? Backend's main responsibility is for each client registered from website to assign an api key and to create a database/storage where his users would authenticate via clients app and upload a picture and a video.

Also wondering what kind of framework for website apps (main web app, dashboard app where we display pending verifications, and of course verification app) to choose. Should be go for angular?