Unseen object detection problem is known as a semantic matching problem. Thus, a semantic matcher takes two images as an input – the request image and the test image. The request image represents an object class needed to be found on the test image. In this paper, we propose a new region proposal based semantic matcher. In our region based semantic matcher we use the same ideas as in R-CNN. Our Body CNN also generates proposals similar to classical Faster R-CNN, and Head-CNN compares proposals with a request descriptor, extracted from the request image. To extract features from the request image we use Request descriptor CNN. All three CNNs – Head, Body and Request descriptor are trained together, end-to-end for seen class object detection by request and then applied to both seen and unseen classes. We have trained and tested our CNN on Pascal VOC Dataset.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Region proposal-based semantic matcher



    Conference:

    Automated Visual Inspection and Machine Vision III ; 2019 ; Munich,Germany


    Published in:

    Proc. SPIE ; 11061


    Publication date :

    2019-06-21





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Tire assembly line with Tire mark matcher

    CHO YOUNG HO | European Patent Office | 2019

    Free access

    A hybrid fingerprint matcher in memory constrained environments

    Krivec, V. / Birchbauer, J.A. / Marius, W. et al. | IEEE | 2003


    A Hybrid Fingerprint Matcher in Memory Constrained Environments

    Krivec, V. / Birchbauer, J. A. / Marius, W. et al. | British Library Conference Proceedings | 2003


    Patch-based face recognition using a hierarchical multi-label matcher

    Zhang, L. / Dou, P. / Kakadiaris, I.A. | British Library Online Contents | 2018


    Electro-optical image matcher for space guidance applications

    Packard, J.N. | Engineering Index Backfile | 1963