Share Email Print

Proceedings Paper

Region proposal-based semantic matcher
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

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.

Paper Details

Date Published: 21 June 2019
PDF: 6 pages
Proc. SPIE 11061, Automated Visual Inspection and Machine Vision III, 1106109 (21 June 2019); doi: 10.1117/12.2525233
Show Author Affiliations
Anastasiia Moiseenko, GosNIIAS (Russian Federation)
Yuri Vizilter, GosNIIAS (Russian Federation)
Boris Vishnyakov, GosNIIAS (Russian Federation)
Vladimir Gorbatsevich, GosNIIAS (Russian Federation)
Oleg Vygolov, GosNIIAS (Russian Federation)

Published in SPIE Proceedings Vol. 11061:
Automated Visual Inspection and Machine Vision III
Jürgen Beyerer; Fernando Puente León, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?