RGB based EEG Controlled Virtual Keyboard for Physically Challenged People

Naseeb, Noman; Alam, Mansoor; Samin, Omar Bin; Omar, Maryam; Khushbakht, Syeda Shaista; Shah, Samad Ali

doi:10.1109/icomet48670.2020.9073847

Cited by 4 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results of the experiment reveal an average spelling completion time of 2.3 minutes, a speed of 6.4 characters per minute (CPM), and an accuracy rate of 89.7%. [5] Nowadays, a significant portion of people's personal lives are shared on social media. Automatically identifying individuals in personal photographs may greatly increase user convenience by making photo album organization easier.…”

Section: Literature Surveymentioning

confidence: 99%

Exploring The Techniques and Applications of Hand Gesture Recognition for Human-Computer Interaction

Khada

2023

IJSREM

View full text Add to dashboard Cite

Hand gesture controlled applications are software applications that are controlled by the user's hand movements. Hand gesture controlled applications have the potential to improve user experience by offering more intuitive and immersive ways to interact with system. Hand gesture controlled applications have a huge scope, including gaming, virtual reality, robotics, healthcare, and various other sectors. In this paper, we have combined several disparate end results of subsystems such as virtual mouse, contactless keyboard, finger counting, taking selfies, sign language, game, handling installed applications and volume control using computer vision. For implementation, we used the open-source software library OpenCV, mediapipe and pyautogui. Various hand gestures are assigned to launch and control different applications. These hand gestures are recognized using machine learning trained models, Euclidean distance formula and pixel positions. Overall, it allows humans to interact with computers through hand gestures rather than traditional input/output mechanisms such as the keyboard and mouse, improving accessibility. Key Words: Computer vision, OpenCV, hand gesture, machine learning, TensorFlow, pyautogui, mediapipe, virtual mouse, virtual keyboard, sign language, gaming.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Exploring The Techniques and Applications of Hand Gesture Recognition for Human-Computer Interaction

Khada

2023

IJSREM

View full text Add to dashboard Cite

show abstract

“…BCI generates a signal that originates in the brain and translates it into a command on the computer [15], [21], [22]. The application of BCI has been carried out in various applications, such as in games [23], rehabilitation [6], [24], [25], implementation of smart homes [26], object recognition [14], detection of emotions in persons with disabilities [27], intelligent robotic exoskeleton [2], robotic hand [21], robotic arm [20], wheelchair [8], [17], control relay module [18], cursor control [19], virtual keyboard [7], [22] and others. The EEG signal is obtained from the voltage variation resulting from the flow of ions across the brain's nerve cell membrane by placing electrodes on the scalp [28].…”

Section: Introductionmentioning

confidence: 99%

Smart Room System for Paralysis Patients with Mindwave EEG Sensor Control

Anandika,

Ferdian,

Eriyandha

et al. 2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Persons with disabilities experience physical, intellectual, mental, or sensory difficulties. One type of disability is paralysis. Paralysis is a condition where there is interference with the nerves that control body movement, causing the limbs to be unable to move. Paralyzed people will find it difficult to move without the help of others. Therefore, research was carried out by creating an intelligent room system to help persons with disabilities manage their own rooms so that they do not always have to be accompanied by a nurse. Paralyzed people can turn lights or fans on and off, and send help messages to their carers via the Telegram bot. This study used the NeuroSky Mindwave EEG headset which detects the user's brain signals with outputs in the form of attention level, relaxation level (meditation), and blink strength level. The resulting signal is processed via a PC and sent via NodeMCU to give commands in the form of turning lights and fans on or off, as well as sending messages to nurses. From this research a system was produced that could turn on the lights based on the value of Attention ≥ 70, turn on the fan based on the Meditation value ≥ 74, then the value of BlinkStrength ≥ 81 which was counted 2 times to turn off the lights, 3 times to turn off the fan, 4 times to turn off the lights and fan, and more than 4 times sending help messages

show abstract