The Headspace dataset

Christian Duncan, Rachel Armstrong, Alder Hey Craniofacial Unit, Liverpool, UK

Nick Pears, Hang Dai, Will Smith, Department of Computer Science, University of York, UK

Public release date: 6th June 2018

Supported by QIDIS and Google Faculty Awards

The Headspace dataset is a set of 3D images of the human head, consisting of 1519 subjects wearing tight fitting latex caps to reduce the effect of hairstyles. The indices of the 1212 subjects that we used for the LYHM 3D Morphable Model (3DMM) are provided with the dataset.

The data collection was planned and implemented by the Alder Hey Craniofacial Unit, under the direction of Christian Duncan, lead Craniofacial clinician. The process employed 3dMD's static 3dMDhead scanning system to capture 1519 3D images of the human head (filtered to 1212 images for our global 3D Morphable Model build). The initial collection was supported by QIDIS and the work in 2017-18 was supported by Google Faculty Awards in the 'Headspace Online' project, with sponsor Forrester Cole (Google, Cambridge, MA).

Headspace data formats

The data is in OBJ format with BMP textures and is available online for download. The dataset is free for research, and is subject to the same non-commercial restrictions as the LYHM morphable models. The same user agreement form can be used. The download file is a compressed tarball (.tar.gz), with file size 38GB. There is an auxilliary dataset available on request that contains the original PNG images and TKA camera calibration data (30GB) available upon request.

Directories are per subject and named with subject indices from 00001 to 01519. Within each directory are the following files, where root is 12 digit 3D image identifier.

Matlab code is included for viewing the dataset, or other utilities can be used, such as MeshLab.

Please cite the following paper if you publish results using the Headspace dataset:

Data example, subject 01242 (Christian Duncan)

Dataset version information (subject meta data correction in version 02)

Early releases of the dataset (pre August 2018) have 1518 subject ID directories, whilst later releases (v02) have 1519. This is because one OBJ file was put in the wrong subject ID directory on collection, and hence associated with the wrong subject meta-data (age, gender, etc). This is an 8-year old girl (meta data here), who was in the directory of a 26 year old male (meta data here). Her scan is moved from subject ID 01400 to 01519 in the v02 release, and the correct meta data of the 26 year-old male is now associated with subject 01400.

This is only important if you are using subject 1400 and the meta data. In this case you can clearly use ensure the correct meta data is being used by visual inspection.

York/Alder Hey publications using the Headspace dataset

3D morphable models

  1. Symmetric Shape Morphing for 3D Face and Head Modelling
      H. Dai, N. E. Pears, W. Smith and C. Duncan
      Proc. 2018 IEEE Int. Conf. Automatic Face and Gesture Recognition (FG 2018-to appear)

  2. A 3D Morphable Model of Craniofacial Shape and Texture Variation
      H. Dai, N. E. Pears, W. Smith and C. Duncan
      Proc. 2017 Int. Conf. Computer Vision (ICCV 2017)

  3. Symmetry-factored Statistical Modelling of Craniofacial Shape
      H. Dai, W. Smith, N. E. Pears, and C. Duncan
      Proc. 2017 PeopleCap Workshop, Int. Conf. Computer Vision (ICCV 2017) pp. 786-794

2D morphable models

  1. Modelling of Orthogonal Craniofacial Profiles
      H. Dai, N. E. Pears and C. Duncan
      Journal of Imaging, vol 3, number 55 (2017)

  2. A 2D Morphable Model of Craniofacial Profile and Its Application to Craniosynostosis
      H. Dai, N. E. Pears and C. Duncan
      Proc. 2017 Conf. Medical Image Understanding and Analysis (MIUA 2017).
      Communications in Computer and Information Science, pages 731-742, vol 723. Springer, Cham

Clinical abstracts

  1. A Morphable Model Of the Human Head Vaidating the Outcomes of An Age-Dependant Scaphocephaly Correction
      B. Robertson, H. Dai, N. E. Pears and C. Duncan
      Abstract in International Journal of Oral and Maxillofacial Surgery (vol 46, p68, 2017).

  2. A Morphable Profile Model of the Human Head as an Outcome Tool for Craniosynostosis Surgery
      Christian Duncan, Rachel Armstrong (Alder Hey Hospital, Liverpool) and Nick E. Pears
      16th Biennial Congress of the International Society of Craniofacial Surgery (ISCFS), Tokyo Bay, Japan, September 14th - 18th, 2015.
      Poster abstract P74 (page e91) in British Journal of Oral and Maxillofacial Surgery 54 (2016).

Inital arXiv publication

Our arXiv paper details our early 100-subject prototype models that were developed in 2015, and can be found here.

  1. Automatic 3D modelling of craniofacial form
      N. E. Pears and C. Duncan
      arXiv, 21st Jan 2016

Project sponsors

We thank the funding bodies that have supported this research which include

BACK to Nick Pears' Research Projects page.