A Data-Augmented 3D Morphable Model of the Ear

Dai, Hang; Pears, Nick; Smith, William A. P.

doi:10.1109/fg.2018.00065

Cited by 28 publications

(32 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study describes an AM framework that reduces manual labour time and running costs by as much as 2.5 h and $150, respectively. This framework is significantly less laborious than many other published AM methods, and can be further developed to enable the automation of the computer design processes with the potential to further reduce manual labour [46][47][48] .…”

Section: Discussionmentioning

confidence: 99%

An advanced prosthetic manufacturing framework for economic personalised ear prostheses

Cruz

Ross

Skewes

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Craniofacial prostheses are commonly used to restore aesthetics for those suffering from malformed, damaged, or missing tissue. Traditional fabrication is costly, uncomfortable for the patient, and laborious; involving several hours of hand-crafting by a prosthetist, with the results highly dependent on their skill level. In this paper, we present an advanced manufacturing framework employing three-dimensional scanning, computer-aided design, and computer-aided manufacturing to efficiently fabricate patient-specific ear prostheses. Three-dimensional scans were taken of ears of six participants using a structured light scanner. These were processed using software to model the prostheses and 3-part negative moulds, which were fabricated on a low-cost desktop 3D printer, and cast with silicone to produce ear prostheses. The average cost was approximately $3 for consumables and $116 for 2 h of labour. An injection method with smoothed 3D printed ABS moulds was also developed at a cost of approximately $155 for consumables and labour. This contrasts with traditional hand-crafted prostheses which range from $2,000 to $7,000 and take around 14 to 15 h of labour. This advanced manufacturing framework provides potential for non-invasive, low cost, and high-accuracy alternative to current techniques, is easily translatable to other prostheses, and has potential for further cost reduction.

show abstract

Section: Discussionmentioning

confidence: 99%

An advanced prosthetic manufacturing framework for economic personalised ear prostheses

Cruz

Ross

Skewes

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Numerous works have been published over the years on ear-based recognition [41], [42], thus making the ear an important structure to represent in any human head modeling. The two foremost examples of 3DMMs of the ear are those of Zolfghari et al [43] and Dai et al [44]. Both models were constructed by applying PCA to ear meshes from the SYMARE database [45], using 58 and 20 samples respectively.…”

Section: Eye and Ear Modelsmentioning

confidence: 99%

“…Both models were constructed by applying PCA to ear meshes from the SYMARE database [45], using 58 and 20 samples respectively. To overcome the limited statistical variation of their restricted sample size, [44] estimate the 3D shape of ears in a landmarked 2D ear image dataset and combine these with their initial model to propose a data-augmented 3DMM. Both the LSFM face model and the LYHM head model templates contain the ear; however, modelling the detailed shape of the ear was not the intention during the construction of either of these.…”

Section: Eye and Ear Modelsmentioning

confidence: 99%

Towards a Complete 3D Morphable Model of the Human Head

Ploumpis

Ververas

Sullivan

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

Self Cite

View full text Add to dashboard Cite

Three-dimensional Morphable Models (3DMMs) are powerful statistical tools for representing the 3D shapes and textures of an object class. Here we present the most complete 3DMM of the human head to date that includes face, cranium, ears, eyes, teeth and tongue. To achieve this, we propose two methods for combining existing 3DMMs of different overlapping head parts: i. use a regressor to complete missing parts of one model using the other, ii. use the Gaussian Process framework to blend covariance matrices from multiple models. Thus we build a new combined face-and-head shape model that blends the variability and facial detail of an existing face model (the LSFM) with the full head modelling capability of an existing head model (the LYHM). Then we construct and fuse a highly-detailed ear model to extend the variation of the ear shape. Eye and eye region models are incorporated into the head model, along with basic models of the teeth, tongue and inner mouth cavity. The new model achieves state-of-the-art performance. We use our model to reconstruct full head representations from single, unconstrained images allowing us to parameterize craniofacial shape and texture, along with the ear shape, eye gaze and eye color.

show abstract

“…3D morphable models (3DMMs) use advanced statistical methods applicable to a population of computational shapes to study and describe the population's complex 3D shape features. First proposed by Blanz and Vetter ( Blanz and Vetter, 1999 ; Booth et al, 2016 ) in 1999, 3DMMs have proven adept at modelling complex shape structures such as the human face, head, hand and ear ( Blanz and Vetter, 1999 ; Booth et al, 2016 ; Dai et al, 2018 ; Ploumpis et al, 2019 ; Dai et al, 2017 ; Zolfaghari et al, 2016 ; Khamis et al, 2015 ) despite limited input data. Paediatric skull models have also been constructed using 3DMMs, although the ability of these models to generate synthetic data has not yet been tested ( Li et al, 2015 ; Kuwahara et al, 2020 ; Libby et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

The 3D skull 0–4 years: A validated, generative, statistical shape model

et al. 2021

View full text Add to dashboard Cite

Background This study aims to capture the 3D shape of the human skull in a healthy paediatric population (0–4 years old) and construct a generative statistical shape model. Methods The skull bones of 178 healthy children (55% male, 20.8 ± 12.9 months) were reconstructed from computed tomography (CT) images. 29 anatomical landmarks were placed on the 3D skull reconstructions. Rotation, translation and size were removed, and all skull meshes were placed in dense correspondence using a dimensionless skull mesh template and a non-rigid iterative closest point algorithm. A 3D morphable model (3DMM) was created using principal component analysis, and intrinsically and geometrically validated with anthropometric measurements. Synthetic skull instances were generated exploiting the 3DMM and validated by comparison of the anthropometric measurements with the selected input population. Results The 3DMM of the paediatric skull 0–4 years was successfully constructed. The model was reasonably compact - 90% of the model shape variance was captured within the first 10 principal components. The generalisation error, quantifying the ability of the 3DMM to represent shape instances not encountered during training, was 0.47 mm when all model components were used. The specificity value was <0.7 mm demonstrating that novel skull instances generated by the model are realistic. The 3DMM mean shape was representative of the selected population (differences <2%). Overall, good agreement was observed in the anthropometric measures extracted from the selected population, and compared to normative literature data (max difference in the intertemporal distance) and to the synthetic generated cases. Conclusion This study presents a reliable statistical shape model of the paediatric skull 0–4 years that adheres to known skull morphometric measures, can accurately represent unseen skull samples not used during model construction and can generate novel realistic skull instances, thus presenting a solution to limited availability of normative data in this field.

show abstract

A Data-Augmented 3D Morphable Model of the Ear

Cited by 28 publications

References 23 publications

An advanced prosthetic manufacturing framework for economic personalised ear prostheses

An advanced prosthetic manufacturing framework for economic personalised ear prostheses

Towards a Complete 3D Morphable Model of the Human Head

The 3D skull 0–4 years: A validated, generative, statistical shape model

Contact Info

Product

Resources

About