Autism Detection
Gandhapu Kalyan
New Delhi, Delhi
- 0 Collaborators
Learning to Predict Autism Spectrum Disorder based on the Visual Patterns of Eye-tracking Scanpaths. ...learn more
Project status: Under Development
Groups
DeepLearning
Overview / Usage
Autism Spectrum Disorder (ASD) is described as a pervasive developmental disorder characterized by a set of impairments including social communication problems, difficulties with reciprocal social interactions, and unusual patterns of repetitive behavior.Individuals diagnosed with ASD typically suffer from deficits in social communication and interaction across multiple contexts. Particularly, they could be incapable of making and maintaining eye contact, or keeping their focus on specific tasks. Such troubling symptoms can unfortunately place a considerable strain on their lives and their families.
So our idea is to detect this disease at the age of infants(early stage) so that it can be cured before it gets too late as parents generally get to know about this problem after the kids have grown up.
Methodology / Approach
For this we have developed a web app which allows user to take or upload a video of their kid's eye movements over a video . At the backend we basically process the video to track the gaze direction of the kid through out the video , then through this tracking we make a scan path , then this scan path is use to classify whether the kid is autistic or non autistic with the help of CNN based deep learning model , we trained this model with the help of ADS dataset which comprises of images of scan paths for both Autistic and Non-Autistic Infant. Hence , the predicted class is after wards reflected by the web app in real time.
Technologies Used
Tensorflow, OpenCv, Keras
Repository
https://github.com/gkalyan04/Autism_Care