Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179304,
        author = {RENUKA SAHEBRAO SARSE and SHILPA KATIKAR},
        title = {MobileNet-Powered Autism Spectrum Disorder Detection from Facial Images},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {6101-6107},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179304},
        abstract = {A developmental disability linked to brain development, autism spectrum disorder (ASD) results in difficulties with behavior, socialization, and communication. Children with autism exhibit significant morphological alterations to their faces that distinguish them from normally developing (TD) children. Our aim is to assist psychiatrists by identifying children with ASD at an early age, which will lessen their symptoms and enhance their cognitive functioning. In this research study, we deploy a neural network-based binary classifier on a pre-trained model of MobileNet to a publically available data set named Autism_Image_Data that we obtained from Kaggle to present a functional model using a facial imaging for autism detection. The dataset contains 2540 training images with 300 test images. This model achieves an accuracy of 89.58% on the dataset that was trained using pre-trained MobileNet architecture model through transfer learning.},
        keywords = {Autism; facial images; convolution neural network; binary classifier; Activation function, transfer Learning; MobileNet; ASD.},
        month = {May},
        }