Improved Transfer-Learning-Based Facial Recognition Framework to Detect Autistic Children at an Early Stage

Abstract

Autism spectrum disorder (ASD) is a complex neuro-developmental disorder that affects social skills, language, speech and communication. Early detection of ASD individuals, especially children, could help to devise and strategize right therapeutic plan at right time. Human faces encode important markers that can be used to identify ASD by analyzing facial features, eye contact, and so on. In this work, an improved transfer-learning-based autism face recognition framework is proposed to identify kids with ASD in the early stages more precisely. Therefore, we have collected face images of children with ASD from the Kaggle data repository, and various machine learning and deep learning classifiers and other transfer-learning-based pre-trained models were applied. We observed that our improved MobileNet-V1 model demonstrates the best accuracy of 90.67% and the lowest 9.33% value of both fall-out and miss rate compared to the other classifiers and pre-trained models. Furthermore, this classifier is used to identify different ASD groups investigating only autism image data using k-means clustering technique. Thus, the improved MobileNet-V1 model showed the highest accuracy (92.10%) for k = 2 autism sub-types. We hope this model will be useful for physicians to detect autistic children more explicitly at the early stage.

Identification of Autism in Children Using Static Facial Features and Deep Neural Networks

“…Only a few research articles have been published on the issue, and it is claimed that one of the primary obstacles for the few studies that have been undertaken is a dearth of open access datasets. Our suggested Xception model outperformed a recently published study [ 27 ], which employed the same dataset and obtained an AUC of 90.67% using a MobileNet model. However, in comparison to the MobileNet and EfficientNet, a significant number of model parameters necessitate the use of the Xception, making it a computationally expensive model.…”

“…In recent years, machine learning (ML) methods have gained prominence in a variety of domains, including picture classification [ 25 , 26 , 27 ]. Because of their amazing capacity to learn from hidden patterns acquired from enormous volumes of data, machine learning algorithms can be an effective predictor.…”

“…Tania et al [ 27 ] were the first to publish a peer-reviewed paper titled “A transfer-learning-based autism classification model utilizing 2D face photos”, according to our understanding. To categorize the input image as autistic or usually developing, the researchers created an ML classifier.…”

Deep Learning Approach for Screening Autism Spectrum Disorder in Children with Facial Images and Analysis of Ethnoracial Factors in Model Development and Application

“…Race factors tend to be overlooked by researchers and readers. For example, we noticed that a recently published study [ 30 ] used the Kaggle ASD facial dataset entirely to derive its deep-learning solution and accuracy. We would like to illustrate the importance of race factors and discuss this topic from the anthropometrics perspective to draw proper attention from interested readers and authors to this matter.…”

A Survey of Face Recognition based on Convolutional Neural Network

“…Akter et al proposed a framework to detect autistic children through facial recognition [63]. The facial recognition was done through improved transfer learning using pre-trained CNN models.…”