Pictorial Speller
The pictorial speller system is the eye-tracking spelling systems, which depend on the movement of the eye that controls a cursor on a virtual keyboard and selects the desired letters. Also, a simple eye blinking can be used as a communication method. Such and similar systems might not be suitable f
2025-06-28 16:34:28 - Adil Khan
Pictorial Speller
Project Area of Specialization Wearables and ImplantableProject SummaryThe pictorial speller system is the eye-tracking spelling systems, which depend on the movement of the eye that controls a cursor on a virtual keyboard and selects the desired letters. Also, a simple eye blinking can be used as a communication method. Such and similar systems might not be suitable for some patients who have lost the ability to precisely control fine ocular movements or who experience uncontrollable head movements. BCI is one of the most interesting technologies among other HCI (Human Computer Interaction) systems, mostly because of its capability of recording brain activities. MNDs (Motor Neuron Diseases) affect how the brain communicates with the other organs in the body by disrupting neurological networks; they mostly effect the motor control of the muscles. Fortunately, this is not the end of the story for these people. It is possible to bypass the damaged neural fibers and connect them to a device which acts based on the user’s intention and it’s the basic concept of a BCI system. This is very important problem that needs to be solved to help patients to gain their social way. This is an alternative way of communication that is much needed. A solution which would allow these patients to communicate is the utilization of modern BCI. A BCI system allows people to communicate through brain signals without the need of any muscular movement. It provides an artificial output that is different from the usual natural output of the nervous system, which is disabled in most MND patients. This project is very important for the disabled patients which will help them to do something.
The main aim of our project is to that subjects are potentially able to communicate the activity in less than ten seconds with an accuracy of 94.5%, which is more than twice as fast as the state of the art. In addition since our EEG device is wireless it offers an increased comfort to the subject.
we have divided our project into four stages that are:
• Data Acquisition
In this stage, we will create a graphical user interface using matlab and image processing of four pictures that were food, light, fan,water representing four classes of hunger detection, light detection, air conditioning and thirst detection respectively.
- Generate & randomize series of pictures of activities
- All Pictures Flashed
- Highlight activity
- Wait 100ms
- Revert picture to base color
- Wait 100ms
- END
- START
• Feature Extraction
In this stage, features are extracted by applying Fast Fourier Transform(FFT) over the recorded EEG signal, to transform this data in frequency domain.
• Feature Selection
Sometimes we may get some irrelevant or redundat features which can cause problem in future, so we need to select some of the required features from a bundle.For this we'll be going to use algorithms like Common Spatial Algorithm or Independent Compinent Analysis particularly designed for selection of thes feature.Using these algos, we can discard any redundant or repeated information and further train the system for classification.
• Classification
In this stage, we will apply supervised learning algorithm on the data uploaded in csv file and will then test the results to come up with the best algorithm technique to be used in
the project.
- Through PICTORIAL SPELLER, Paralyzed patients will be able to communicate with the external World.
- Brain reserach can be better like the Vision Based Functionality of barin can easily be investigated
In this project, we need a MUSE HEADSET, Computing Device or Window Based tablet.
Window Based tablet will be connected to the headset and Application will get data and Algorithms will Classify that data and will rerpresent the selected things.
Final Deliverable of the Project HW/SW integrated systemCore Industry HealthOther Industries IT Core Technology Artificial Intelligence(AI)Other Technologies NeuroTech, Wearables and ImplantablesSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 60000 | |||
| Muse Headset | Equipment | 1 | 50000 | 50000 |
| Software Open BCI Lab | Miscellaneous | 1 | 10000 | 10000 |