Abstract:
The aim of this project is for the machine to be able to analyse, monitor, and alert
Impulse Control Disorder behaviour in order to prevent people from doing them
subconsciously. This article examines the various methods for recognising human
expressions and movement. Various levels of image processing, such as pre processing, segmentation, and attribute extraction, will be analysed. The pre processing level, segmentation, and feature extraction are all stages of image
processing that will be analysed and addressed. Finally, the algorithms' output will be
written in Python. To design the algorithm, this research uses the Artificial
Convolutional Neural Network method. The key benefit ofthis method is that it allows
for the extraction and identification of features that are beneficial for gesture
recognition. Different neural network models are debated, with the Error-back
propagation algorithm being used because of its ability to construct internal
representations of features in classification. A suitable set of training parameters is
specified and a network configuration is generated after trials and errors. The system
begins by performing a pre-processing of the captured signal, which includes
thresholding, inverting, and smoothing. The method also includes filtering,
segmentation, resizing, and feature extraction. The feed forward method is then used
to generate an output matrix across the network. The recognised gesture can be
calculated using the output matrix. This device is intended to personalise the network
for each user. The report also includes recommendations for future progress and
findings.
