Multi-Level Visual Alphabets

Menno Israël, Jetske van der Schaar, Egon van den Broek, Marten J. den Uyl, Peter van der Putten

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    62 Downloads (Pure)


    A central debate in visual perception theory is the argument for indirect versus direct perception; i.e., the use of intermediate, abstract, and hierarchical representations versus direct semantic interpretation of images through interaction with the outside world. We present a content-based representation that combines both approaches. The previously developed Visual Alphabet method is extended with a hierarchy of representations, each level feeding into the next one, but based on features that are not abstract but directly relevant to the task at hand. Explorative benchmark experiments are carried out on face images to investigate and explain the impact of the key parameters such as pattern size, number of prototypes, and distance measures used. Results show that adding an additional middle layer improves results, by encoding the spatial co-occurrence of lower-level pattern prototypes.
    Original languageUndefined
    Title of host publicationIEEE/EURASIP Proceedings of the 2nd International Conference on Image Processing Theory, Tools & Applications (IPTA10)
    EditorsK. Djemal, M. Deriche
    Place of PublicationLos Alamitos
    PublisherIEEE Computer Society
    Number of pages6
    ISBN (Print)978-1-4244-7249-9
    Publication statusPublished - 7 Jul 2010

    Publication series

    PublisherIEEE Computer Society Press


    • IR-73564
    • METIS-270956
    • Content-Based Image Retrieval
    • Visual perception
    • Multilevel
    • HMI-CI: Computational Intelligence
    • code books
    • visual alphabets
    • HMI-HF: Human Factors
    • EWI-18242

    Cite this

    Israël, M., van der Schaar, J., van den Broek, E., den Uyl, M. J., & van der Putten, P. (2010). Multi-Level Visual Alphabets. In K. Djemal, & M. Deriche (Eds.), IEEE/EURASIP Proceedings of the 2nd International Conference on Image Processing Theory, Tools & Applications (IPTA10) (pp. 349-354). Los Alamitos: IEEE Computer Society.