Dynamic Gesture Recognition and Kinect with Python? - python

I am working on "Kinect for XBox One" on my HP Laptop with Windows 10 and 64-bit operating system. I have worked on python before and want to work in it only with jupyter notebok or python command line.
The topic of my project is Dynamic Sign Language Recognition and till now I have worked on only static images. I found many tutorials for working with kinect camera but every tutorial has been done with C++, C# or Sketch in Processing 3. I have downloaded Processing 3 and tried some programs in Sketch also by following this link: https://www.youtube.com/watch?v=XKatPT3HlqA
But even after 2 days, I am not able to run a simple program in it and only a black picture is there as an output, kinect is detected though.
I have also tried Pykinect and python example from this link: https://github.com/Kinect/PyKinect2
It was good and I was able to track the skeleton of the body. I want to learn Pykinect and many more such examples but I am not getting any source from where I can learn all these. My aim is to use all the three cues:RGB, Depth, and Skeleton for my work.
Even for dynamic gesture recognition, there are projects in C++ and languages other than python.
If you have any suggestions regarding kinect with python and dynamic gesture recognition, then you are welcome.


After searching for days, I figured out that there are no tutorials on Kinect using Python. Those who want to learn kinect with python and Windows should go to this link first: https://github.com/Kinect/PyKinect2
Go by the instructions and run the example programs whether in Visual studio, python command line or jupyter notebook. There are no tutorials defining the programming functions of Pykinect library. The only way to learn it is through one more link:
https://github.com/Microsoft/PTVS
Explore this link as it has one or two more examples which will help in understanding the functions. I am not done yet so I will keep updating my answer if I find any more sources.

Related

Create Microsoft Office Wordart with Python

I need to create a lot of wordart for a project I am working on
old 90s wordart from Microsoft Office.
I originally tried the pythonWordArt library for python 3 but this seems to no longer be functional for Windows 10 and Ubuntu 20.04 and 18.04
The test script runs but a white screen is returned on all 3 OSs.
Makewordart.com generates individual art however there is no way to do this automated other than through the front end with recorded keystrokes (which is not reliable)
Css3wordart contains css and js source code to generate the word art but I have no way to turn this into an image file
Is there any way for either the pythonWordArt library to be used or an alternative method?
Thanks in advance!

How to import a Python/OpenCV/OCR script into Android Studio?

I'm trying to build a small android app in which I will be able to recognize 7-segment digits or other type of numbers and display them on the screen.
I was able to make a small script in Python that can recognize any letters/numbers using OpenCV and Tesseract. For 7-segment digits, it doesn't seem to be as easy so I'm trying to use machine learning using this nice tutorial:
Simple Digit Recognition OCR in OpenCV-Python
On the other side, I have to learn how to use Android Studio (3.4.2) but I managed to import the OpenCV library (3.4.0) using this protocol:
https://android.jlelse.eu/a-beginners-guide-to-setting-up-opencv-android-library-on-android-studio-19794e220f3c
I have a general question. What strategy should I follow to conclude this project? Just the big lines ... or more if you want. Since I almost managed to make it work nicely using Python, how can I import my python code into Android Studio? Sorry for this stupid question. I just need to know if I'm taking the problem from the right angle. Is there an easy way to convert it to Java?....
Thanks for your advice.

Generate and execute python both on non-python machine

Short version:
Is it possible to create a standalone program that can be distributed to computers that don't have python installed, which writes a python script during runtime and executes it during or shortly after?
Long version:
A project I've been wanting to do for a while is to create a visual programming interface, that lets people use Machine Learning without needing to know python/keras/numpy syntax. Programs like lobe or rapidminer already do this, but they are all bound to their own interfaces and servers. What i would like to do is create a program that:
anyone can use without needing python/anaconda installed
allow the user to create visual scripts like in scratch or google-blocs
generates python code behind the scenes containing keras or tf code
is able to execute the script
is able to show the code to the user for:
educational purposes
allowing the user to use it as a base for a more complex program
Since the generation part would just need to create a text file almost any interface and language like python/java using Qt or C# / javascript using Unity, would qualify. I think that should definitely be doable, probably just very long, but that is not my largest concern.
The problem:
I have tried to search everywhere on the internet about things like standalone python programs which led me to for instance py2exe. Those kind of python-to-exe's work great, but they all require the script to be compiled on a machine containing a python environment. In my case i want to be able to generate a python script on the user's PC, and run it directly after from there.
The alternative
If this isn't possible i might just create the whole AI part myself, not using python nor libraries like keras or tensorflow, but in a unity game for instance. The downside to this would be that it exists already(like rapidminer), it would be less optimized/versatile/customizable and doesn't show what the "real" machine learning script would look.
If there are any other alternatives i would be happy to hear them
PS.
I have mostly Python & Keras, moderate Java and little Unity3D or web JS experience
I'm using Windows with anaconda
Distributing to linux/mac would be nice, but not required

maybe you should check the Orange Data Mining software, it's written in python and it has the same purpose as your project (https://orange.biolab.si/). On the other hand, some time ago I tried to compile my app that contains machine learning libraries but to date, I have not been able to achieve it. Instead, what I use is the WINPYTHON project, this is a portable Anaconda software that allows you to run projects on any PC without the need to install anything (https://winpython.github.io/).

Yes, it is possible!
I had the same requirement, so I wrote my visual programming language and IDE...
...that could generate an almost python-like script, and which is compiled natively inside the app, without the use of any external compilers or libraries.
My target architecture was mobile devices, but it also works on browsers via the unity plugin.
...and yes, that's correct, it runs natively on your phone or tablet in a simulated sandbox, with its own built-in IDE.
It's written in C#, and implemented in Unity3d
You can check it out at https://aiBoard.blog
..and see the videos at https://youtu.be/DIDgu9jrdLc

How to capture screen on Wayland(Gnome) in Python code?

I'm trying to capture my screen using Python because I'll use it on OpenCV, but I couldn't find a way to make it work on Gnome, since Gnome uses Wayland and all libraries that I've found only work with X11.
For now I'm not considering change my interface. I'm searching a solution to this problem.
Does someone know a solution?
To be more specific, I'll use the images to train an AI and so I need they continuously.
EDIT:
I've found this but how can I pass frames to OpenCV in Python instead of save a video file?

The proper way to do screencasting these days is by using the Screencast portal, which is part of XDG desktop portals and is already supported by GNOME, KDE, wlroots (and more). As an added advantage, this will also work in containerized formats like Flatpaks.
You can find an example on how to do screencasting in Pyhon using this snippet, created by one of the Mutter maintainers. If you look for parse_launch(), you will see a GStreamer pipeline which you can modify to include the GStreamer OpenCV elements that can do the processing for you.
Note: in your edit, you link to a predecessor of that portal, which is GNOME-specifc, internal API, so I wouldn't rely on it ;-)

what OCR algorithm does Microsoft Office Document Imaging use? Can I use it without installing office 2003?

Related to this question, I found a program, JOCR that has good results. It turns out it just uses Microsoft Office Document Imaging to do the OCR for it using COM. That works for me - I can spend some time trying to get it to work from Python (where I need it).
My questions are: what OCR algorithm do they use? Is it possible to get it (or one like it - tesseract and ocropus seem to only work with scanned images or pictures, but MODI OCR works great with on-screen text) elsewhere? Is it possible to install it on a computer without installing all of Office 2003?

Categories