Face detection method based on photoplethysmography

Gibert, Guillaume; D’Alessandro, David A.; Lance, Florian

doi:10.1109/avss.2013.6636681

Cited by 17 publications

(16 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the proposed VPS method to the most recent FDR method [9], named the "Face Detection based on RPPG". Both methods are implemented by us in C++ using the OpenCV 2.4 library [15] and ran on a laptop with an Intel Core i7 processor (2.70 GHz) and 8 GB RAM.…”

Section: Compared Methodsmentioning

confidence: 99%

“…Both methods are implemented by us in C++ using the OpenCV 2.4 library [15] and ran on a laptop with an Intel Core i7 processor (2.70 GHz) and 8 GB RAM. The parameters in FDR are remained identical to [9], while the parameters in VPS are empirically defined as: (1) 3 scales segmentation with k = 16, 36 and 64 in Eq. 1; (2) T in Eq.…”

Section: Compared Methodsmentioning

confidence: 99%

“…To some extent, such strategy has already been exploited in [9] by slicing the video into fixed rigid-grids. However, the subject size is quantized by the grid geometry, which fails when the subject is small or when there is body motion.…”

Section: A Hierarchical Voxelsmentioning

confidence: 99%

“…In 2013, Gibert et al proposed a face detection method based on the pulse-signal [9]. This method slices the video into fixed rigid-grids for local pulse extraction.…”

Section: B Pulse-based Roi Detectionmentioning

confidence: 99%

See 3 more Smart Citations

Unsupervised Subject Detection via Remote PPG

Wang

Stuijk

Haan

2015

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-Subject detection is a crucial task for camera-based remote healthcare monitoring. Most existing methods in subject detection rely on supervised learning of physical appearance features. However, their performances are highly restricted to the pre-trained appearance model while still suffering from false detection of human-similar objects. In this paper, we propose a novel unsupervised method to detect alive subject in a video using physiological features. Our basic idea originates from the observation that only living skin tissue of a human presents pulse-signals, which can be exploited as the feature to distinguish human skin from non-human surfaces in videos. The proposed VPS method, named Voxel-Pulse-Spectral, consists of three steps: it (1) creates hierarchical voxels across the video for temporally parallel pulse extraction; (2) builds a similarity matrix for hierarchical pulse-signals based on their intrinsic properties; and (3) utilizes incremental sparse matrix decomposition with hierarchical fusion to robustly identify and combine the voxels that correspond to single/multiple subjects. Numerous experiments demonstrate the superior performance of VPS over a state-of-theart method. On average, VPS improves 82.2% on the precision of skin-region detection; 595.5% on the Pearson correlation and 542.2% on Bland-Altman agreement of instant pulse-rate. ANOVA shows that in all-round evaluations, the improvements of VPS are significant. The proposed method is the first method that uses pulse to robustly detect alive subjects in realistic scenarios, which can be favorably applied for healthcare monitoring.

show abstract

Section: Compared Methodsmentioning

confidence: 99%

Section: Compared Methodsmentioning

confidence: 99%

Section: A Hierarchical Voxelsmentioning

confidence: 99%

“…In 2013, Gibert et al proposed a face detection method based on the pulse-signal [9]. This method slices the video into fixed rigid-grids for local pulse extraction.…”

Section: B Pulse-based Roi Detectionmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Subject Detection via Remote PPG

Wang

Stuijk

Haan

2015

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…Therefore in the face detection processing, the paper will use ASM algorithm to solve the problems of face detection based on AdaBoost algorithm to improve detection performance [7]. Firstly, the AdaBoost algorithm will be used to detect a face for the very first time, secondly, the detection results will serve as inputs for the ASM algorithm to perform further face region filters to filter non face region which is taken for the face by AdaBoost.…”

Section: Face Detection Based On Adaboost and Asmmentioning

confidence: 99%

Research of Face Detection Based on AdaBoost and ASM

Han¹,

Han²,

Hou³

2015

TOCSJ

View full text Add to dashboard Cite

Face Detection is an essential first step of the face recognition process, and has significant effects on face feature extraction and the effects of face recognition. Face detection has extensive research value and significance. This paper deeply researches and analysis the principle, merits and demerits of the classic AdaBoost face detection algorithm and ASM algorithm based on point distribution model, using ASM to solve the problems of face detection based on AdaBoost. Firstly, the method uses the AdaBoost algorithm to detect original face from images or video stream. Secondly it uses ASM algorithm converges, which fit face region detected by Adaboost to detect faces more accurately. Finally, it cuts out the specified size of the facial region on the basis of the positioning coordinates of eyes. The experiment results indicate that this method can detect face rapidly and precisely, with a strong robustness.

show abstract

Heart Rate Based Face Synthesis for Pulse Estimation

Ciftci

Liu

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Face detection method based on photoplethysmography

Cited by 17 publications

References 11 publications

Unsupervised Subject Detection via Remote PPG

Unsupervised Subject Detection via Remote PPG

Research of Face Detection Based on AdaBoost and ASM

Heart Rate Based Face Synthesis for Pulse Estimation

Contact Info

Product

Resources

About