The main aim of the project is to recognize the drawer of the assembly table is filled with material or is it empty, with other classes hand and tool. Output of the object recognition is considered further as a time series data for quality control or assembly assistance to the physically challenged persons with the process identification.
In neural networks, Convolutional Neural Network (ConvNets or CNNs) is one of the main categories to do images recognition. Transfer learning concept is used to take advantage of the already trained model with large and general enough dataset. For the process prediction a powerful type of neural network designed to handle sequence dependence called recurrent neural network used.
