The application of image processing for Human-Computer Interface (HCI) using the Eye

The field of Human-Computer Interaction (HCI) has been developing tremendously since the past decade. The existence of smartphones or modern computers is already a norm in society these days which utilizes touch, voice and typing as a means for input. To further increase the variety of interaction, human eyes are set to be a good candidate for another form of HCI. The amount of information which the human eyes contain are extremely useful, hence, various methods and algorithm for eye gaze tracking are implemented in multiple sectors. However, some eye-tracking method requires infrared rays to be projected into the eye of the user which could potentially cause enzyme denaturation when the eye is subjected to those rays under extreme exposure. Therefore, to avoid potential harm from the eye-tracking method that utilizes infrared rays, this paper proposes an image-based eye tracking system using the Viola-Jones algorithm and Circular Hough Transform (CHT) algorithm. The proposed method uses visible light instead of infrared rays to control the mouse pointer using the eye gaze of the user. This research aims to implement the proposed algorithm for people with hand disability to interact with computers using their eye gaze.

Controlling a Mouse Pointer with a Single-Channel EEG Sensor

(1) Goals: The purpose of this study was to analyze the feasibility of using the information obtained from a one-channel electro-encephalography (EEG) signal to control a mouse pointer. We used a low-cost headset, with one dry sensor placed at the FP1 position, to steer a mouse pointer and make selections through a combination of the user’s attention level with the detection of voluntary blinks. There are two types of cursor movements: spinning and linear displacement. A sequence of blinks allows for switching between these movement types, while the attention level modulates the cursor’s speed. The influence of the attention level on performance was studied. Additionally, Fitts’ model and the evolution of the emotional states of participants, among other trajectory indicators, were analyzed. (2) Methods: Twenty participants distributed into two groups (Attention and No-Attention) performed three runs, on different days, in which 40 targets had to be reached and selected. Target positions and distances from the cursor’s initial position were chosen, providing eight different indices of difficulty (IDs). A self-assessment manikin (SAM) test and a final survey provided information about the system’s usability and the emotions of participants during the experiment. (3) Results: The performance was similar to some brain–computer interface (BCI) solutions found in the literature, with an averaged information transfer rate (ITR) of 7 bits/min. Concerning the cursor navigation, some trajectory indicators showed our proposed approach to be as good as common pointing devices, such as joysticks, trackballs, and so on. Only one of the 20 participants reported difficulty in managing the cursor and, according to the tests, most of them assessed the experience positively. Movement times and hit rates were significantly better for participants belonging to the attention group. (4) Conclusions: The proposed approach is a feasible low-cost solution to manage a mouse pointer.

A Human–Computer Interface Replacing Mouse and Keyboard for Individuals with Limited Upper Limb Mobility

People with physical disabilities in their upper extremities face serious issues in using classical input devices due to lacking movement possibilities and precision. This article suggests an alternative input concept and presents corresponding input devices. The proposed interface combines an inertial measurement unit and force sensing resistors, which can replace mouse and keyboard. Head motions are mapped to mouse pointer positions, while mouse button actions are triggered by contracting mastication muscles. The contact pressures of each fingertip are acquired to replace the conventional keyboard. To allow for complex text entry, the sensory concept is complemented by an ambiguous keyboard layout with ten keys. The related word prediction function provides disambiguation at word level. Haptic feedback is provided to users corresponding to their virtual keystrokes for enhanced closed-loop interactions. This alternative input system enables text input as well as the emulation of a two-button mouse.

User Behavior for Neural Network-based Web Search Results Filtering

This paper describes methodology and performance of an experimental research on filtering of web search results. Filtering was performed on the basis of predicted relevance of search results derived from users’ implicit feedback. The feedback was obtained from users’ web browsers and consisted of a set of browsing behavioral metrics, including reading time, clicks on links, mouse pointer and wheel movement patterns, bookmarking, sharing, copying, and whether the search was continued after the page was closed. A multi-layer neural network used to infer from the behaviors how much the user was interested in each filtered document. Neural network, therefore, performed deep learning without human supervision. Predicted relevance measure was compared to the explicit feedback. Obtained results of 89% correct relevance rating prediction suggest that selected set of metrics was successful in terms of correctly predict how relevant the web page was for the user involved in the study. More research is recommended for further advances of information filtering methods.

Human-Computer Interface with Eye Movement

This paper focuses on using IR handset to operate the PC's mouse pointer, which distinguishes the client's eyeball creation for Human Machine Interface. Having the ability to perform left, right, up, down and double taps based on different eye squints with significantly high precision, it uses a viable example classification calculation. In view of the actual usage of Eye Contact, the sensor projections are usually used to gage selflook headings in low- minus- calculations. The proposed architecture is a promising human-PC interface for flexible eye following applications due to its lightweight construction and strong precision.