View in EDS

Measuring Representation of Race, Gender, and Age in Children's Books: Face Detection and Feature Classification in Illustrated Images

Saved in:
Bibliographic Details
Title: Measuring Representation of Race, Gender, and Age in Children's Books: Face Detection and Feature Classification in Illustrated Images
Language: English
Authors: Szasz, Teodora, Harrison, Emileigh, Liu, Ping-Jung, Lin, Ping-Chang, Runesha, Hakizumwami Birali, Adukia, Anjali
Source: Grantee Submission. 2022Paper presented at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (Jan 2022).
Peer Reviewed: Y
Page Count: 10
Publication Date: 2022
Sponsoring Agency: Institute of Education Sciences (ED)
Contract Number: R305A200478
Document Type: Speeches/Meeting Papers
Reports - Research
Descriptors: Childrens Literature, Books, Artificial Intelligence, Race, Sex, Age, Illustrations, Photography, Social Influences, Measurement Techniques, Social Bias, Racial Bias, Gender Bias, Prediction, Classification
Abstract: Images in children's books convey messages about society and the roles that people play in it. Understanding these messages requires systematic measurement of who is represented. Computer vision face detection tools can provide such measurements; however, state-of-the-art face detection models were trained with photographs, and 80\% of images in children's books are illustrated; thus existing methods both misclassify and miss classifying many faces. In this paper, we introduce a new approach to analyze images using AI tools, resulting in data that can assess representation of race, gender, and age in both illustrations and photographs in children's books. We make four primary contributions to the fields of deep learning and social sciences: (1) We curate an original face detection data set (IllusFace 1.0) by manually labeling 5,403 illustrated faces with bounding boxes. (2) We train two AutoML-based face detection models for illustrations: (i) using IllusFace 1.0 (FDAI); (ii) using iCartoon, a publicly available data set (FDAI_iC), each optimized for illustrated images, detecting 2.5 times more faces in our testing data than the established face detector using Google Vision (FDGV). (3) We curate a data set of the race, gender, and age of 980 faces manually labeled by three different raters (CBFeatures 1.0). (4) We train an AutoML feature classification model (FCA) using CBFeatures 1.0. We compare FCA with the performance of another AutoML model that we trained on UTKFace, a public data set (FCA_UTK) and of an established model using FairFace (FCF). Finally, we examine distributions of character identities over the last century across the models. We find that FCA is 34% more accurate than FCF in its race predictions. These contributions provide tools to educators, caregivers, and curriculum developers to assess the representation contained in children's content. [This paper was published in: "Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)," 2022, pp. 462-471.]
Abstractor: As Provided
IES Funded: Yes
Entry Date: 2022
Accession Number: ED620152
Database: ERIC
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=ED620152
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: ED620152
AccessLevel: 3
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Measuring Representation of Race, Gender, and Age in Children's Books: Face Detection and Feature Classification in Illustrated Images
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Szasz%2C+Teodora%22">Szasz, Teodora</searchLink><br /><searchLink fieldCode="AR" term="%22Harrison%2C+Emileigh%22">Harrison, Emileigh</searchLink><br /><searchLink fieldCode="AR" term="%22Liu%2C+Ping-Jung%22">Liu, Ping-Jung</searchLink><br /><searchLink fieldCode="AR" term="%22Lin%2C+Ping-Chang%22">Lin, Ping-Chang</searchLink><br /><searchLink fieldCode="AR" term="%22Runesha%2C+Hakizumwami+Birali%22">Runesha, Hakizumwami Birali</searchLink><br /><searchLink fieldCode="AR" term="%22Adukia%2C+Anjali%22">Adukia, Anjali</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Grantee+Submission%22"><i>Grantee Submission</i></searchLink>. 2022Paper presented at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (Jan 2022).
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 10
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2022
– Name: SourceSuprt
  Label: Sponsoring Agency
  Group: SrcSuprt
  Data: Institute of Education Sciences (ED)
– Name: NumberContract
  Label: Contract Number
  Group: NumCntrct
  Data: R305A200478
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Speeches/Meeting Papers<br />Reports - Research
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Childrens+Literature%22">Childrens Literature</searchLink><br /><searchLink fieldCode="DE" term="%22Books%22">Books</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Race%22">Race</searchLink><br /><searchLink fieldCode="DE" term="%22Sex%22">Sex</searchLink><br /><searchLink fieldCode="DE" term="%22Age%22">Age</searchLink><br /><searchLink fieldCode="DE" term="%22Illustrations%22">Illustrations</searchLink><br /><searchLink fieldCode="DE" term="%22Photography%22">Photography</searchLink><br /><searchLink fieldCode="DE" term="%22Social+Influences%22">Social Influences</searchLink><br /><searchLink fieldCode="DE" term="%22Measurement+Techniques%22">Measurement Techniques</searchLink><br /><searchLink fieldCode="DE" term="%22Social+Bias%22">Social Bias</searchLink><br /><searchLink fieldCode="DE" term="%22Racial+Bias%22">Racial Bias</searchLink><br /><searchLink fieldCode="DE" term="%22Gender+Bias%22">Gender Bias</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction%22">Prediction</searchLink><br /><searchLink fieldCode="DE" term="%22Classification%22">Classification</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Images in children's books convey messages about society and the roles that people play in it. Understanding these messages requires systematic measurement of who is represented. Computer vision face detection tools can provide such measurements; however, state-of-the-art face detection models were trained with photographs, and 80\% of images in children's books are illustrated; thus existing methods both misclassify and miss classifying many faces. In this paper, we introduce a new approach to analyze images using AI tools, resulting in data that can assess representation of race, gender, and age in both illustrations and photographs in children's books. We make four primary contributions to the fields of deep learning and social sciences: (1) We curate an original face detection data set (IllusFace 1.0) by manually labeling 5,403 illustrated faces with bounding boxes. (2) We train two AutoML-based face detection models for illustrations: (i) using IllusFace 1.0 (FDAI); (ii) using iCartoon, a publicly available data set (FDAI_iC), each optimized for illustrated images, detecting 2.5 times more faces in our testing data than the established face detector using Google Vision (FDGV). (3) We curate a data set of the race, gender, and age of 980 faces manually labeled by three different raters (CBFeatures 1.0). (4) We train an AutoML feature classification model (FCA) using CBFeatures 1.0. We compare FCA with the performance of another AutoML model that we trained on UTKFace, a public data set (FCA_UTK) and of an established model using FairFace (FCF). Finally, we examine distributions of character identities over the last century across the models. We find that FCA is 34% more accurate than FCF in its race predictions. These contributions provide tools to educators, caregivers, and curriculum developers to assess the representation contained in children's content. [This paper was published in: "Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)," 2022, pp. 462-471.]
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: CodeSource
  Label: IES Funded
  Group: SrcInfo
  Data: Yes
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2022
– Name: AN
  Label: Accession Number
  Group: ID
  Data: ED620152
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=ED620152
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
    Subjects:
      – SubjectFull: Childrens Literature
        Type: general
      – SubjectFull: Books
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Race
        Type: general
      – SubjectFull: Sex
        Type: general
      – SubjectFull: Age
        Type: general
      – SubjectFull: Illustrations
        Type: general
      – SubjectFull: Photography
        Type: general
      – SubjectFull: Social Influences
        Type: general
      – SubjectFull: Measurement Techniques
        Type: general
      – SubjectFull: Social Bias
        Type: general
      – SubjectFull: Racial Bias
        Type: general
      – SubjectFull: Gender Bias
        Type: general
      – SubjectFull: Prediction
        Type: general
      – SubjectFull: Classification
        Type: general
    Titles:
      – TitleFull: Measuring Representation of Race, Gender, and Age in Children's Books: Face Detection and Feature Classification in Illustrated Images
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Szasz, Teodora
      – PersonEntity:
          Name:
            NameFull: Harrison, Emileigh
      – PersonEntity:
          Name:
            NameFull: Liu, Ping-Jung
      – PersonEntity:
          Name:
            NameFull: Lin, Ping-Chang
      – PersonEntity:
          Name:
            NameFull: Runesha, Hakizumwami Birali
      – PersonEntity:
          Name:
            NameFull: Adukia, Anjali
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2022
          Titles:
            – TitleFull: Grantee Submission
              Type: main
ResultId 1