A Computer Vision Approach to Enhance Visual Data used to Overcome the Learning Disabilities in Higher Education

The potential application of computer vision techniques is to boost the learning experiences and academic outcomes of students having learning disabilities. Computer vision involves the analysis and interpretation of visual data, such as images and videos, using artificial intelligence, machine learning, and deep learning algorithms. By leveraging computer vision technologies, this study aims to address specific challenges faced by students with learning disabilities, such as visual processing difficulties, information retrieval, and comprehension of visual content etc. Computer vision supports the development of overall learning environments, adaptive visual materials, and personalized interference to scale access that enhance the ability of learning to the students. The study is intended to explore the role of confusion in detecting dyslexia, where dyslexic individuals exhibit errors due to perceptual distortion. Utilizing convolutional neural networks on EEG signals from dataset retrieved from Kaggle’s data repository i.e. “confused student EEG brainwave data,” the result shows remarkable accuracy that is 97.35% while predicting dyslexia-related confusion among students.