Real-Time Facial Feature Tracking on a Mobile Device

Tresadern, Philip A.; Ionita, Mircea C.; Cootes, Timothy F.

doi:10.1007/s11263-011-0464-9

Cited by 32 publications

(33 citation statements)

References 22 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Rigid and deformable tracking of faces and facial features have been a very popular topic of research over the past twenty years (Black and Yacoob 1995;Lanitis et al 1995;Sobottka and Pitas 1996;Essa et al 1996Essa et al , 1997Oliver et al 1997;Decarlo and Metaxas 2000;Jepson et al 2003;Xiao et al 2004;Patras and Pantic 2004;Kim et al 2008;Ross et al 2008;Papandreou and Maragos 2008;Amberg et al 2009;Kalal et al 2010a;Koelstra et al 2010;Tresadern et al 2012;Tzimiropoulos and Pantic 2013;Xiong and De la Torre 2013;Liwicki et al 2013;Smeulders et al 2014;Asthana et al 2014;Li et al 2016a;Xiong and De la Torre 2015;Snape et al 2015;Tzimiropoulos 2015). In this section we provide an overview of face tracking spanning over the past twenty years up to the present day.…”

Section: Related Workmentioning

confidence: 99%

“…Deformable tracking of faces can be further subdivided into i) tracking of certain facial landmarks (Lanitis et al 1995;Black and Yacoob 1995;Sobottka and Pitas 1996;Xiao et al 2004;Patras and Pantic 2004;Papandreou and Maragos 2008;Amberg et al 2009;Tresadern et al 2012;Xiong and De la Torre 2013;Asthana et al 2014;Xiong and De la Torre 2015) or ii) tracking/estimation of dense facial motion Yacoob and Davis 1996;Essa et al 1997;Decarlo and Metaxas 2000;Koelstra et al 2010;Snape et al 2015). The latter category of estimating a dense facial motion through a model-based system was proposed by MIT Media lab in mid 1990's (Essa et al 1997Basu et al 1996).…”

Section: Prior Artmentioning

confidence: 99%

“…Regarding tracking of facial landmarks, up until recently, the preferred method for assessing the performance was visual inspection in a number of selected facial videos (Xiong and De la Torre 2013;Tresadern et al 2012). Other methods were assessed on a small number of short (a few seconds in length) annotated facial videos (Sagonas et al 2014;Asthana et al 2014).…”

Section: Face Tracking Benchmarkingmentioning

confidence: 99%

See 2 more Smart Citations

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

et al. 2017

View full text Add to dashboard Cite

Recently, technologies such as face detection, facial landmark localisation and face recognition and verification have matured enough to provide effective and efficient solutions for imagery captured under arbitrary conditions (referred to as "in-the-wild"). This is partially attributed to the fact that comprehensive "in-the-wild" benchmarks have been developed for face detection, landmark localisation and recognition/verification. A very important technology that has not been thoroughly evaluated yet is deformable face tracking "in-the-wild". Until now, the performance has mainly been assessed qualitatively by visually assessing the result of a deformable face tracking technology on short videos. In this paper, we perform the first, to the best of our knowledge, thorough evaluation of state-of-theart deformable face tracking pipelines using the recently introduced 300 VW benchmark. We evaluate many different architectures focusing mainly on the task of on-line deformable face tracking. In particular, we compare the following general strategies: (a) generic face detection plus generic facial landmark localisation, (b) generic model free tracking plus generic facial landmark localisation, as well as (c) hybrid approaches using state-of-the-art face detection, model free tracking and facial landmark localisation technologies. Our evaluation reveals future avenues for further research on the topic.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Prior Artmentioning

confidence: 99%

Section: Face Tracking Benchmarkingmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

et al. 2017

View full text Add to dashboard Cite

show abstract

“…One can use an analytic approach by minimizing the objective function [28,45]. Other approaches solve this problem by learning a regression function directly from a set of known displacement and their corresponding residuals [44]. Despite their ability to handle facial deformations, these approaches are prone to local minima because they can mismanage illumination or occlusion.…”

Section: Spatial Restrictionsmentioning

confidence: 99%

Multi-Kernel Appearance Model

Rapp

Bailly

Senechal

et al. 2013

Image and Vision Computing

View full text Add to dashboard Cite

“…: 2016/21/B/ST6/01495. 1 For strictness: the 'Find' operation in this data structure is of amortized complexity O(log * n) -iterated logarithm of n. Wherein log * 2 n is not greater than 5 for all quantities n observable in the universe; in particular, log images [1,8]. One should be aware that the fast performance of Haar-like features is not owed to the nature of these features as such; they are simple differential features that can be viewed as rough contours (e.g.…”

Section: Introductionmentioning

confidence: 99%

Constant-Time Fourier Moments for Face Detection — Can Accuracy of Haar-Like Features Be Beaten?

Klęsk

2017

Artificial Intelligence and Soft Computing

View full text Add to dashboard Cite

Abstract. We demonstrate a technique allowing for constant-time calculation of low order Fourier moments, applicable in detection tasks. Real and imaginary parts of the moments can be used as features for machine learning and classification of image windows. The technique is based on a set of special integral images, prepared prior to the scanning procedure. The integral images are constructed as cumulative inner products between the input image and suitable trigonometric terms. Additional time invested in the preparation of such integral images is amortized later at the stage of scanning. Then, the extraction of each moment requires only 21 operations, regardless of the number of pixels in the detection window, and thereby is an O(1) calculation.As an application example, face detection experiments are carried out with detectors based on Haar-like features serving as opponents to the proposed Fourier-based detectors. IntroductionConstant-time computational complexity is the most attractive complexity for a computer scientist. Unfortunately, favourable opportunities to apply algorithms of that complexity are rare -typically, they pertain to some selected data structures e.g. hash tables, Union-Find 1 [2] and constitute a narrow fragment of a larger software. Often, one deals in fact with a so-called amortized constant-time complexity. This means that in the company of essential operations, performed are also some auxiliary operations meant to guarantee the speed for the future.Not so long ago an algorithmic idea of that class has appeared in the field of computer vision and works remarkably well -namely, the idea of Haar-like features due to Jones (2001, 2004) [9,10]. Haar-like features are now commonly applied to detect objects (faces, people, vehicles, road signs, etc.) in digitalThis work was financed by the National Science Centre, Poland. Research project no.: 2016/21/B/ST6/01495. 1 For strictness: the 'Find' operation in this data structure is of amortized complexity O(log * n) -iterated logarithm of n. Wherein log * 2 n is not greater than 5 for all quantities n observable in the universe; in particular, log * 2 2 65536 = 5.

show abstract

Real-Time Facial Feature Tracking on a Mobile Device

Cited by 32 publications

References 22 publications

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

Multi-Kernel Appearance Model

Constant-Time Fourier Moments for Face Detection — Can Accuracy of Haar-Like Features Be Beaten?

Contact Info

Product

Resources

About