Automatic detection of obstructive sleep apnea using facial images

Balaei, Asghar Tabatabaei; Sutherland, Kate; Cistulli, Peter A.; Chazal, Philip de

doi:10.1109/isbi.2017.7950504

Cited by 15 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image-based automated facial landmark detection has been the topic of active research and has numerous applications, including facial identification, facial expression analysis, such as facial palsy, sleep apnea [16][17][18][19], face animation, 3D face reconstruction and registration [20][21][22][23], feature-based face recognition, verification, face tracking, and head gesture understanding [24][25][26][27][28]. The number of facial landmarks can be varied depending on intended applications.…”

Section: Facial Landmarks Detectionmentioning

confidence: 99%

Hybrid Facial Features with Application in Person Identification

Purahong

Chutchavong

Aoyama

et al. 2020

JMM

View full text Add to dashboard Cite

This paper presents the hybrid facial feature with identification and verification based on facial images. A query facial image had been taken under different conditions of the facial image of the same person (as the query). The query facial image database was constructed. We have used the technique of three-dimensional (3D) Dlib facial landmarks using a direct linear transform technique. A set of absolute affine invariance had been constructed from a series of the 3D landmark quadruplets, which make the facial identification robust to affine geometric transformation. These 3D facial features serve as a coarse feature depending on each individual facial structure. The construct of the 2D detail features represents the edge facial image confined between the 2D Dlib landmarks. The similarity of the 2D feature is achieved by aligning the 2D query edge image against that of the reference edge image. The geometric transformation matrix is estimated from the 2D Dlib landmarks, where correspondence is well established. An identification/verification cost function using a combination of local 2D facial features and global 3D facial features is utilized to verify and identify a query facial image against a candidate facial image(s). The performance of the algorithm yielding an area of 99.97% perfect classification is represented as a value under the receiver operating characteristic (ROC) curve.

show abstract

Section: Facial Landmarks Detectionmentioning

confidence: 99%

Hybrid Facial Features with Application in Person Identification

Purahong

Chutchavong

Aoyama

et al. 2020

JMM

View full text Add to dashboard Cite

show abstract

“…A clear, concise, and correct definition of what is to be achieved is crucial as it forms the basis of all other steps, design decisions, and is often a platform for solving more complex problems. Wu et al in 2012 [1] used facial landmarks to assist in age estimation and face verification; Devries et al [2] used landmarking in facial expression recognition while Tabatabaei Balaei et al [5] investigated the use of facial landmarks as a means of determining the likelihood that an individual sufferer from obstructive sleep apnoea (OSA).…”

Section: Stage 1: Objective Definitionmentioning

confidence: 99%

“…Performance metrics will vary depending upon the objective definition; Devries et al [2] used expression classification accuracy while Tabatabaei Balaei et al [5] measured performance based on rates of correct OSA diagnosis. While these measures determine overall system performance, measuring facial landmarking accuracy is required to ensure landmark predictions are acceptable.…”

Section: Measuring Performancementioning

confidence: 99%

“…The selected dataset must contain features with sufficient predictive power that the training process can 'learn' the relationships within the data. For many problems, such as the prediction of obstructive sleep apnoea [5] a custom dataset is required which itself may be subject to iterations of improvement to ensure the most appropriate features are being used.…”

Section: Stage 2: Dataset Selectionmentioning

confidence: 99%

“…Very recently, Guarin et al [3] described an automated facial landmarking tool which is used in the characterisation of facial displacements in sufferers of facial palsy; while the work by Anping et al [4] uses landmarks as predicted by Active Shape Models to assess facial *Correspondence: ben.johnston@sydney.edu.au 1 Sleep Research Group, Charles Perkins Centre, School of Electrical and Information Engineering, 2006 University of Sydney, Sydney, NSW, Australia 2 ResMed Ltd, 1 Elizabeth Macarthur Dr, 2153 Bella Vista, NSW, Australia nerve paralysis. The use of facial landmarking methodologies has been recently examined as a means of screening for sleep apnoea by Tabatabaei Balaei et al [5], looking at the association between the underlying structure of predicted facial landmarks and the likelihood of suffering from obstructive sleep apnoea. The authors of this review have also investigated the use of facial landmarks in sizing sleep apnoea masks [6], a critical device in sleep apnoea treatment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A review of image-based automatic facial landmark identification techniques

Johnston

Chazal

2018

J Image Video Proc.

View full text Add to dashboard Cite

The accurate identification of landmarks within facial images is an important step in the completion of a number of higher-order computer vision tasks such as facial recognition and facial expression analysis. While being an intuitive and simple task for human vision, it has taken decades of research, an increase in the availability of quality data sets, and a dramatic improvement in computational processing power to achieve near-human accuracy in landmark localisation. The intent of this paper is to provide a review of the current facial landmarking literature, outlining the significant progress that has been made in the field from classical generative methods to more modern techniques such as sophisticated deep neural network architectures. This review considers a generalised facial landmarking problem and provides experimental examples for each stage in the process, reporting repeatable benchmarks across a number of publicly available datasets and linking the results of these examples to the recently reported performance in the literature.

show abstract