Using words as lexical basis functions for automatically indexing face images in a manner that correlates with human perception of similarity

Mariano Phielipp, John A. Black, Sethuraman Panchanathan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

To facilitate collaboration between computers and people, computers should be able to perceive the world in a manner that correlates well with human perception. A good example of this is face image retrieval. Mathematically-based face indexing methods that are not based primarily on how humans perceive faces can produce retrievals mat are disappointing to human users. This raises the question "Can human faces be automatically indexed in a manner that correlates well with human perception of similarity?" Humans use words to describe faces - words such as braided, graybearded, bearded, bespectacled, bald, blondish, blond, freckled, blue eyed, mustached, pale, Caucasian, brown eyed, dark skinned, or black eyed. Such words represent dimensions that span a shared concept space for faces. Therefore they might provide a useful guide to indexing faces in an intuitive manner. This paper describes research that uses descriptive words such as these to index faces. Each word guides the design of one feature detector that produces a scalar coefficient, and those coefficients collectively define a feature vector for each face. Given these feature vectors, it is possible to compute a similarity measure between pairs of faces, and to compare that computed similarity to the similarity, as perceived by humans.

Original languageEnglish (US)
Title of host publicationHuman Vision and Electronic Imaging XI - Proceedings of SPIE-IS and T Electronic Imaging
DOIs
StatePublished - Apr 10 2006
EventHuman Vision and Electronic Imaging XI - San Jose, CA, United States
Duration: Jan 16 2006Jan 18 2006

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6057
ISSN (Print)0277-786X

Other

OtherHuman Vision and Electronic Imaging XI
CountryUnited States
CitySan Jose, CA
Period1/16/061/18/06

Keywords

  • Face indexing
  • Face recognition
  • Facial similarity
  • Feature detectors
  • Human visual perception
  • Human-computer collaboration
  • Lexical basis functions

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Using words as lexical basis functions for automatically indexing face images in a manner that correlates with human perception of similarity'. Together they form a unique fingerprint.

  • Cite this

    Phielipp, M., Black, J. A., & Panchanathan, S. (2006). Using words as lexical basis functions for automatically indexing face images in a manner that correlates with human perception of similarity. In Human Vision and Electronic Imaging XI - Proceedings of SPIE-IS and T Electronic Imaging [60571C] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6057). https://doi.org/10.1117/12.643692