Sign language recogniton

Colaborators: Tim 4M

• Mateja Pejić
• Mate Poljak
• Mihaela Zima
• Mateo Martinjak

Used techologies,libraries and other resources

• Software used: It's very important to use these versions together,new versions may or may not work together.

  • Python 3.9
  • Tensorflow 2.8
  • CUDA 11.2: API that allows software to use certain types of GPU for general purpose processing
  • cuDNN 11.2: NVIDIA CUDA Deep Neural Network library (cuDNN) is a GPU-accelerated library of primitives for deep neural networks.

• Other resources:

  • Tensorflow models: repository with a number of different implementations of state-of-the-art (SOTA) models and modeling solutions for TensorFlow
  • OpenCV: Library used for video input/output
  • labelImg: graphical image annotation tool
  • SSD and Real-Time Object Detection article
  • A novel face recognition method based on sub-patternand tensor article

Files

• Code is located here.
• main.py can be used instead jupyter library above for a demo of the project.(it uses already learned model)
• Formal documentation
• Examples and dataset