Abstract This paper presents a method to classify new objects with SURF descriptors and shape skeleton of objects in dataset. The objective of the research is to classify all objects which exist in all images. Stages in this method are consisting of three main stages: image segmentation, object recognition and object class recognition. The region of interest in this method is used the saliency based region selection. In this paper, SIFT and SURF also compare in aspects of speed and recognition accuracy too. The result has shown SURF cluttered dataset has a better accuracy and it is faster. Also for object class recognition purpose shape skeleton would help to classify same category objects. Finally the outputs will be train with fuzzy logic to make an accurate decision making. Results have shown the accuracy improved up to 94%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Object Class Recognition Using Surf Descriptors and Shape Skeletons

    Sahzabi, V.A. / Omar, K. | British Library Conference Proceedings | 2013


    Gauge-SURF descriptors

    Alcantarilla, P. F. / Bergasa, L. M. / Davison, A. J. | British Library Online Contents | 2013


    Strategies for shape matching using skeletons

    Goh, W. B. | British Library Online Contents | 2008


    Video-based descriptors for object recognition

    Lee, T. / Soatto, S. | British Library Online Contents | 2011


    Comparison of Invariant Descriptors for Object Recognition

    Choksuriwong, A. / Laurent, H. / Emile, B. | British Library Conference Proceedings | 2005