Hand Gesture Recognition Using Nao Robot Athanasia Karalakou

Hand Gesture Recognition Using Nao Robot Athanasia Karalakou 2015030061 athanasiak 1997@gmail. com

The Goal of this Project The purpose of this work is to train a machine learning algorithm capable of classifying camera images of different hand motions and to associate it with the humanoid robot Nao.

Tensorflow Keras • free software library focused on machine learning. • for largescale neural networks creation • an opensource neural -network library written in Python • capable of running on top of Tensor. Flow Open. Cv • an open source computer vision and machine learning software library

The Training Process. Learns by generating an error signal that measures the difference between the predictions of the network and the desired values and then using this error signal to change the weights(or parameters) so that predictions get more accurate.

Model Testing

NAOqi What is NAOqi Framework: • The NAOqi Framework is the programming framework used to program NAO. • It answers to common robotics needs including: parallelism, resources, synchronization, events. • It allows homogeneous communication, programming and information sharing. Broker NAOqi Libraries Modules

Running Process Comparison Matched Gesture Extracted Gesture Task Performed Gesture Database Camera Image

For further information, about installation or execution, check the Read. Me. md file in my code repository.