Object identification (OID) is specialized recognition where the category is known (e.g. cars) and the algorithm recognizes an object's exact identity (e.g. Bob's BMW). Two special challenges characterize OID. (1) Interclass variation is often small (many cars look alike) and may be dwarfed by illumination or pose changes. (2) There may be many classes but few or just one positive "training" examples per class. Due to (1), a solution must locate possibly subtle object-specific salient features (a door handle) while avoiding distracting ones (a specular highlight). However, (2) rules out direct techniques of feature selection. We describe an online algorithm that takes one model image from a known category and builds an efficient "same" vs. "different" classification cascade by predicting the most discriminative feature set for that object. Our method not only estimates the saliency and scoring function for each candidate feature, but also models the dependency between features, building an ordered feature sequence unique to a specific model image, maximizing cumulative information content. Learned stopping thresholds make the classifier very efficient. To make this possible, category-specific characteristics are learned automatically in an off-line training procedure from labeled image pairs of the category, without prior knowledge about the category. Our method, using the same algorithm for both cars and faces, outperforms a wide variety of other methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Building a classification cascade for visual identification from one example


    Beteiligte:
    Ferencz, A. (Autor:in) / Learned-Miller, E.G. (Autor:in) / Malik, J. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    403181 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Building a Classification Cascade for Visual Identification from One Example

    Ferencz, A. / Learned-Miller, E. / Malik, J. et al. | British Library Conference Proceedings | 2005


    Document Page Similarity Based on Layout Visual Saliency: Application to query by Example and Document Classification

    Eglin, V. / Bres, S. / Institute of Electrical and Electronics Engineers | British Library Conference Proceedings | 2003



    Training Effective Node Classifiers for Cascade Classification

    Shen, C. / Wang, P. / Paisitkriangkrai, S. et al. | British Library Online Contents | 2013


    Car detection and classification using cascade model

    Liang, Jun / Chen, Xu / He, Mei-ling et al. | IET | 2018

    Freier Zugriff