Facial Expression Electric Wheelchair Control Instruction Using Image Processing

Abstract

Tetraplegia is a type of paralysis that affects upper and lower limbs due to damage of spinal cord or brain. This condition causes difficulty to move and most of the time caretaker is needed to help the patients. This project proposed the design and implementation of an image processing technique in capturing and categorizing different facial gesture and use it as control instructions for electric wheelchair. The aim was to reduce the dependency to caretaker especially for mobility oftetraplegia patient. The deep learning Haar Cascade Classifier identify the expression of a face through image processing in livevideo capture. The Open Computer Vision (OpenCV) in Python was used to detect, recognize, and analyze the facial expression. Convolution Neural Network (CNN), a deep learning operation will act as trainer that analyze an open-source data to create a model as reference for the facial expression recognition. In orderto make the system operated as a standalone system, the Raspberry Pi module that connects with Pi Camera was used as the platform to capture the live video, perform processing, and produce the output control that give instructions to move such as forward, right, left and stop. Based on the analysis of the system performance, the system was capable to produce high accuracyof detection and correctly produce the electric wheelchair controlinstruction according to the facial expressions.