This paper is published in Volume-7, Issue-2, 2021
Area
Computer Science
Author
Shaik Jahanara, Shobana Padmanabhan
Org/Univ
Alliance University, Anekal, Karnataka, India
Pub. Date
25 March, 2021
Paper ID
V7I2-1181
Publisher
Keywords
Autism Spectrum Disorder, Early Diagnosis, Deep Learning Technics

Citationsacebook

IEEE
Shaik Jahanara, Shobana Padmanabhan. Detecting autism from facial image, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Shaik Jahanara, Shobana Padmanabhan (2021). Detecting autism from facial image. International Journal of Advance Research, Ideas and Innovations in Technology, 7(2) www.IJARIIT.com.

MLA
Shaik Jahanara, Shobana Padmanabhan. "Detecting autism from facial image." International Journal of Advance Research, Ideas and Innovations in Technology 7.2 (2021). www.IJARIIT.com.

Abstract

Autism is a serious developmental spectrum disorder that puts constraints on the ability to communicate linguistic, cognitive, and social interaction skills. Autism spectrum disorder screening is the process of detecting potential autistic traits in an individual where the early diagnose shortens the process and has more accurate results. The methods used to predict the presence of autism by doctors involve physical identification of facial features and questioners, this conventional method of diagnosis needs more time, cost and in the case of pervasive developmental disorders, the parents feel inferior to come out in open. Therefore, a time-efficient and accessible ASD screening are imminent to help health professionals and inform individuals whether they should pursue formal clinical diagnosis or not. A screening tool that could identify ASD risk during infancy offers the opportunity for intervention before the full set of symptoms is present. The proposed model by using a convolution neural network classifier helps in predicting the early autistic traits in children through facial features in images, with the least cost, less time, and a greater amount of accuracy when compared to the traditional type of diagnosis.