A new method for automatic tracking of facial landmarks in 3D motion captured images (4D)

Al-Anezi, Thamer; Khambay, Balvinder; Peng, Matthew Jian-Qiao; O'Leary, Emer; Ju, Xiangyang; Ayoub, Ashraf

doi:10.1016/j.ijom.2012.10.035

Cited by 48 publications

(44 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, three-dimensional (3D) motion analysis is well recognized as an objective, non-invasive and quantitative method to assess facial movements before and after surgical rehabilitation, and several investigators have developed instruments and software to the scope [7][8][9][10][11][12][13][14] .…”

Section: Introductionmentioning

confidence: 99%

Double-powered free gracilis muscle transfer for smile reanimation: A longitudinal optoelectronic study

Sforza

Frigerio

Mapelli

et al. 2015

Journal of Plastic, Reconstructive & Aesthetic Surgery

View full text Add to dashboard Cite

The choice of the motor donor nerve is a crucial point in free flap transfer algorithms. In the case of unilateral facial paralysis, the contralateral healthy facial nerve can provide coordinated smile animation and spontaneous emotional expression, but with unpredictable axonal ingrowth into the recipient muscle. Otherwise, the masseteric nerve ipsilateral to the paralysis can provide a powerful neural input, without a spontaneous trigger of the smile. Harvesting a bulky muscular free flap may enhance the quantity of contraction but esthetic results are unpleasant. Therefore, the logical solution for obtaining high amplitude of smiling combined with spontaneity of movement is to couple the neural input: the contralateral facial nerve plus the ipsilateral masseteric nerve. Thirteen patients with unilateral dense facial paralysis underwent a one-stage facial reanimation with a gracilis flap powered by a double donor neural input, provided by both the ipsilateral masseteric nerve (coaptation by an end-to-end neurorrhaphy with the obturator nerve) and the contralateral facial nerve (coaptation through a cross-face nerve graft: end-to-end neurorrhaphy on the healthy side and end-to-side neurorrhaphy on the obturator nerve, distal to the masseteric/obturator neurorrhaphy). Their facial movements were evaluated with an optoelectronic motion analyzer. Before surgery, on average, the paretic side exhibited a smaller total three-dimensional mobility than the healthy side, with a 52% activation ratio and >30% of asymmetry. After surgery, the differences significantly decreased (analysis of variance (ANOVA), p < 0.05), with an activation ratio between 75% (maximum smile) and 91% (maximum smile with teeth clenching), and <20% of asymmetry. Similar modifications were seen for the performance of spontaneous smiles. The significant presurgical asymmetry of labial movements reduced after surgery. The use of a double donor neural input permitted both movements that were similar in force to that of the healthy side, and spontaneous movements elicited by emotional triggering.

show abstract

Section: Introductionmentioning

confidence: 99%

Double-powered free gracilis muscle transfer for smile reanimation: A longitudinal optoelectronic study

Sforza

Frigerio

Mapelli

et al. 2015

Journal of Plastic, Reconstructive & Aesthetic Surgery

View full text Add to dashboard Cite

show abstract

“…The landmarks were digitized twice and those associated with non-significant digitization errors were automatically tracked throughout the sequence of the 3D images of each facial expression. The Di4D facial imaging system has satisfactory proven automatic landmark tracking accuracy of 0.55mm (24) Five key 3D facial frames of each sequence of the 180 3D images/expression were used for the analysis, these were the initial rest pose, first quartile 3D image, maximum expression, third quartile 3D image, the rest pose at the end of the expression (Figure 3). …”

Section: Data Processing and Statistical Analysismentioning

confidence: 99%

Reproducibility of the dynamics of facial expressions in unilateral facial palsy

Alagha

Morley

et al. 2018

International Journal of Oral and Maxillofacial Surgery

Self Cite

View full text Add to dashboard Cite

Abstract:The aim of this study was to assess the reproducibility of non-verbal facial expressions in unilateral facial paralysis using the dynamic 4D imaging. Di4D system was utilized to record 5 facial expressions of 20-adult patients. The system captured 60 3D images/second; each facial expression took 3-4 seconds to record which generated a set of 180 3D facial images for each expression. The procedure was repeated after 30 minutes to assess the reproducibility of the expressions. A mathematical facial mesh which consists of thousand of quasi points "vertices" was conformed to the face to disclose the morphological characteristics in a comprehensive manner. The vertices of the conformed mesh were tracked throughout the sequence of the 180 3D images. Five key 3D facial frames of each sequence of images were analyzed.. We compared the 3D facial morphology at each of the five key frames of the first and the second capture of each facial expression to assess the reproducibility of the facial movements. The corresponding images were aligned using partial Procrustes analysis, the root square mean of the distances between these was calculated and statistically analyzed using paired student t-test at P=0.05. Facial expressions of lip purse, cheek puff and raising of the eyebrows were reproducible. The facial expressions of maximum smile and forceful eye closure were not reproducible. The limited coordination of various groups of facial muscles contributed to the lack of reproducibility of these facial expressions. The 4D imagining is a useful clinical tool for the assessment of facial expressions.Introduction:

show abstract

“…They have concluded that an accurate tracking solution facilitate the analysis of the dynamic motion. Shujaat et al (Shujaat et al, 2014) have pursued the study conducted in (Al-Anezi et al, 2013) and have developed a new method to quantify dynamic 3D facial animations, in order to characterize the dynamics of 3D lips movement in head, and neck oncology patients before and after lower lip split mandibulotomy. A dataset of 7 subjects aged 42-80 years old is collected.…”

Section: Prior Workmentioning

confidence: 99%

Facial Asymmetry Assessment from 3D Shape Sequences: The Clinical Case of Facial Paralysis

Desrosiers

Bennis

Amor

et al. 2016

Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

View full text Add to dashboard Cite

Abstract:This paper addresses the problem of quantifying the facial asymmetry from dynamic 3D data. We investigate here the role of 4D (i.e. 3D+time) data to reveal the amount of both static and dynamic asymmetry, in a clinical use-case of facial paralysis. The final goal is to provide tools and solutions to clinicians for facial paralysis assessment and monitoring, which can provide qualitative and quantitative evaluations. To this end, the approach proposed here consider 3D facial sequences and adopt a recently-developed Riemannian approach for facial deformation analysis. After a preprocessing step, each frame of a given 3D sequence is approximated by an indexed collection of elastic radial curves. Riemannian shape analysis of obtained curves and their symmetrical counterparts, both elements of the same shape space, give rise to a feature vector, called Dense Scalar Fields (DSFs). The use of these DSFs reveals the amount of bilateral asymmetry of the face, when conveying expressions. That is, given a 3D frame, it is first reflected with respect to the YZ-plane, then compared to the obtained reflection using the DSFs. To exemplify the use of the proposed approach, a new dataset have been collected (of patients) before and after injecting Botulinum Toxin (BT) in related facial muscles. Experimental results obtained on this dataset show that the proposed approach allows clinicians to evaluate the facial asymmetry before and after the medical treatment.

show abstract

A new method for automatic tracking of facial landmarks in 3D motion captured images (4D)

Cited by 48 publications

References 21 publications

Double-powered free gracilis muscle transfer for smile reanimation: A longitudinal optoelectronic study

Double-powered free gracilis muscle transfer for smile reanimation: A longitudinal optoelectronic study

Reproducibility of the dynamics of facial expressions in unilateral facial palsy

Facial Asymmetry Assessment from 3D Shape Sequences: The Clinical Case of Facial Paralysis

Contact Info

Product

Resources

About