In this page you will learn about IntelliGlove from a high-level description of how the system works and how the different parts work together.
Hardware Overview
The glove is equipped with five customized force sensors, each positioned at one of the five knuckles on the hand. A voltage divider circuit has been designed to convert the resistance of each sensor into an analog voltage reading. This analog voltage is then converted to a digital reading through the Analog-to-Digital Converter (ADC) from the FRDM-KL46Z board. The board would periodically update sensor data using the Periodic Interrupt Timer (PIT).
Software Overview
The readings from each sensor will be first averaged respectively by taking a list of samples and then classified into two states: linear and bending. We collected data for both the linear and bending states for each finger and processed it using Support Vector Machines (SVMs) to create a maximum margin classifier. This classifier efficiently determines the state of each finger with high accuracy. By analyzing the combination of these states across all five fingers, the system will be able to identify the specific gesture of the human hand. The gesture will then be translated into English words or numerical values, which will be displayed on the terminal.