A fundamental problem in image analysis is the integration of information across scale to detect and classify objects. We have developed, within a machine learning framework, two classes of multiresolution models for integrating scale information for object detection and classification-a discriminative model called the hierarchical pyramid neural network and a generative model called a hierarchical image probability model. Using receiver operating characteristic analysis, we show that these models can significantly reduce the false positive rates for a well-established computer-aided diagnosis system.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Hierarchical, multi-resolution models for object recognition: applications to mammographic computer-aided diagnosis


    Contributors:
    Sajda, P. (author) / Spence, C. (author) / Parra, L. (author) / Nishikawa, R. (author)


    Publication date :

    2000-01-01


    Size :

    718086 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Hierarchical, Multi-Resolution Models for Object Recognition: Applications to Mammographic Computer-Aided Diagnosis

    Sajda, P. / Spence, C. / Parra, L. et al. | British Library Conference Proceedings | 2000


    A novel approach to computer-aided diagnosis of mammographic images

    Sari-Sarraf, H. / Gleason, S.S. / Hudson, K.T. et al. | IEEE | 1996


    A Novel Approach to Computer-Aided Diagnosis of Mammographic Images

    Sari-Sarraf, H. / Gleason, S. S. / Hudson, K. T. et al. | British Library Conference Proceedings | 1996


    Computer diagnosis of mammographic masses

    Velthuizen, R.P. | IEEE | 2000


    Computer Diagnosis of Mammographic Masses

    Velthuizen, R. | British Library Conference Proceedings | 2000