For object recognition under varying illumination conditions, we propose a method based on photometric alignment. The photometric alignment is known as a technique that models both diffuse reflection components and attached shadows under a distant point light source by using three basis images. However, in order to reliably reproduce these components in a test image, we have to take into account outliers such as specular reflection components and shadows in the test image. Accordingly, our proposed method utilizes Random Sample Consensus (RANSAC), which has been used successfully for estimating basis images. In the present study, we have conducted experiments using the Yale Face Database B and confirmed that a combination of the photometric alignment and RANSAC provides a simple but effective method for object recognition under varying illumination conditions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Object recognition based on photometric alignment using RANSAC


    Beteiligte:
    Okabe, T. (Autor:in) / Sato, Y. (Autor:in)


    Erscheinungsdatum :

    2003-01-01


    Format / Umfang :

    373233 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Object Recognition Based on Photometric Alignment Using RANSAC

    Okabe, T. / Sato, Y. / IEEE | British Library Conference Proceedings | 2003


    Linear model hashing and batch RANSAC for rapid and accurate object recognition

    Shan, Y. / Matei, B. / Sawhney, H.S. et al. | IEEE | 2004


    Linear Model Hashing and Batch RANSAC for Rapid and Accurate Object Recognition

    Shan, Y. / Matei, B. / Sawhney, H. et al. | British Library Conference Proceedings | 2004


    Unsupervised Change Detection Using RANSAC

    Sharma, B. / Rishabh, I. / Rakshit, S. et al. | British Library Conference Proceedings | 2006


    Lane detection based on guided RANSAC

    Hu, Yi / Kim, You-Sun / Lee, Kwang-Wook et al. | Tema Archiv | 2010