Robust Template Matching via Hierarchical Convolutional Features from a Shape Biased CNN

Bo Gao*, Michael Spratling

*Corresponding author for this work

Research output: Contribution to conference typesPaperpeer-review

7 Citations (Scopus)

Abstract

Finding a template in a search image is an important task underlying many computer vision applications. Recent approaches perform template matching in a deep feature-space, produced by a convolutional neural network (CNN), which is found to provide more tolerance to changes in appearance. In this article, we investigate whether enhancing the CNN’s encoding of shape information can produce more distinguishable features, so as to improve the performance of template matching. This investigation results in a new template matching method that produces state-of-the-art results in a standard benchmark. To confirm these results, we also create a new benchmark and show that the proposed method also outperforms existing techniques on this new dataset. Our code and dataset is available at: https://github.com/iminfine/Deep-DIM.

Original languageEnglish
Pages333-344
Number of pages12
DOIs
Publication statusPublished - 1 Jan 2022
EventInternational Conference on Image, Vision and Intelligent Systems -
Duration: 19 Jun 202120 Jun 2021
http://www.icivis.net/icivis-2021/

Conference

ConferenceInternational Conference on Image, Vision and Intelligent Systems
Abbreviated titleICIVIS
Period19/06/202120/06/2021
Internet address

Fingerprint

Dive into the research topics of 'Robust Template Matching via Hierarchical Convolutional Features from a Shape Biased CNN'. Together they form a unique fingerprint.

Cite this