A bayesian approach to automated creation of tactile facial images

Zheshen Wang, Baoxin Li

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Portrait photos (facial images) play important social and emotional roles in our life. This type of visual media is unfortunately inaccessible by users with visual impairment. This paper proposes a systematic approach for automatically converting human facial images into a tactile form that can be printed on a tactile printer and explored by a user who is blind. We propose a deformable Bayesian Active Shape Model (BASM), which integrates anthropometric priors with shape and appearance information learnt from a face dataset. We design an inference algorithm under this model for processing new face images to create an input-adaptive face sketch. Further, the model is enhanced by input-specific details through semantic-aware processing. We report experiments on evaluating the accuracy of face alignment using the proposed method, with comparison with other state-of-the-art results. Furthermore, subjective evaluations of the produced tactile face images were performed by 17 persons including six visually-impaired users, confirming the effectiveness of the proposed approach in conveying via haptics vital visual information in a face image.

Original languageEnglish (US)
Article number5437233
Pages (from-to)233-246
Number of pages14
JournalIEEE Transactions on Multimedia
Volume12
Issue number4
DOIs
StatePublished - Jun 2010

Fingerprint

Conveying
Processing
Semantics
Experiments

Keywords

  • Image matching
  • Image shape analysis
  • Pattern recognition
  • Tactile graphics

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Media Technology
  • Computer Science Applications

Cite this

A bayesian approach to automated creation of tactile facial images. / Wang, Zheshen; Li, Baoxin.

In: IEEE Transactions on Multimedia, Vol. 12, No. 4, 5437233, 06.2010, p. 233-246.

Research output: Contribution to journalArticle

@article{5948207a82154323b443b786e0227ad4,
title = "A bayesian approach to automated creation of tactile facial images",
abstract = "Portrait photos (facial images) play important social and emotional roles in our life. This type of visual media is unfortunately inaccessible by users with visual impairment. This paper proposes a systematic approach for automatically converting human facial images into a tactile form that can be printed on a tactile printer and explored by a user who is blind. We propose a deformable Bayesian Active Shape Model (BASM), which integrates anthropometric priors with shape and appearance information learnt from a face dataset. We design an inference algorithm under this model for processing new face images to create an input-adaptive face sketch. Further, the model is enhanced by input-specific details through semantic-aware processing. We report experiments on evaluating the accuracy of face alignment using the proposed method, with comparison with other state-of-the-art results. Furthermore, subjective evaluations of the produced tactile face images were performed by 17 persons including six visually-impaired users, confirming the effectiveness of the proposed approach in conveying via haptics vital visual information in a face image.",
keywords = "Image matching, Image shape analysis, Pattern recognition, Tactile graphics",
author = "Zheshen Wang and Baoxin Li",
year = "2010",
month = "6",
doi = "10.1109/TMM.2010.2046267",
language = "English (US)",
volume = "12",
pages = "233--246",
journal = "IEEE Transactions on Multimedia",
issn = "1520-9210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - A bayesian approach to automated creation of tactile facial images

AU - Wang, Zheshen

AU - Li, Baoxin

PY - 2010/6

Y1 - 2010/6

N2 - Portrait photos (facial images) play important social and emotional roles in our life. This type of visual media is unfortunately inaccessible by users with visual impairment. This paper proposes a systematic approach for automatically converting human facial images into a tactile form that can be printed on a tactile printer and explored by a user who is blind. We propose a deformable Bayesian Active Shape Model (BASM), which integrates anthropometric priors with shape and appearance information learnt from a face dataset. We design an inference algorithm under this model for processing new face images to create an input-adaptive face sketch. Further, the model is enhanced by input-specific details through semantic-aware processing. We report experiments on evaluating the accuracy of face alignment using the proposed method, with comparison with other state-of-the-art results. Furthermore, subjective evaluations of the produced tactile face images were performed by 17 persons including six visually-impaired users, confirming the effectiveness of the proposed approach in conveying via haptics vital visual information in a face image.

AB - Portrait photos (facial images) play important social and emotional roles in our life. This type of visual media is unfortunately inaccessible by users with visual impairment. This paper proposes a systematic approach for automatically converting human facial images into a tactile form that can be printed on a tactile printer and explored by a user who is blind. We propose a deformable Bayesian Active Shape Model (BASM), which integrates anthropometric priors with shape and appearance information learnt from a face dataset. We design an inference algorithm under this model for processing new face images to create an input-adaptive face sketch. Further, the model is enhanced by input-specific details through semantic-aware processing. We report experiments on evaluating the accuracy of face alignment using the proposed method, with comparison with other state-of-the-art results. Furthermore, subjective evaluations of the produced tactile face images were performed by 17 persons including six visually-impaired users, confirming the effectiveness of the proposed approach in conveying via haptics vital visual information in a face image.

KW - Image matching

KW - Image shape analysis

KW - Pattern recognition

KW - Tactile graphics

UR - http://www.scopus.com/inward/record.url?scp=77952258353&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952258353&partnerID=8YFLogxK

U2 - 10.1109/TMM.2010.2046267

DO - 10.1109/TMM.2010.2046267

M3 - Article

AN - SCOPUS:77952258353

VL - 12

SP - 233

EP - 246

JO - IEEE Transactions on Multimedia

JF - IEEE Transactions on Multimedia

SN - 1520-9210

IS - 4

M1 - 5437233

ER -