CDVS
An event presentation from the CDVS Awareness Event held at the 112th WG 11 meeting.
An event presentation from the CDVS Awareness Event held at the 112th WG 11 meeting.
An event presentation from the CDVS Awareness Event held at the 112th WG 11 meeting.
An event presentation from the CDVS Awareness Event held at the 112th WG 11 meeting.
This document describes the Compact Descriptors for Visual Search (CDVS) Test Model (TM) 13.0 (CDVS1) (CDVS2). In particular, this document looks at the TM architecture, the operation of the informative component technologies (descriptor matching and retrieval) of the TM, and the offline or training procedures for both the normative (descriptor extraction) and the informative (descriptor matching and retrieval) component technologies of the TM.
This document is a working draft toward development of reference software and conformance testing specifications for Compact Descriptors for Visual Search (CDVS).
Event Description
This document is a (non-final draft) of the CDVS conformance test dataset and conditions. The conformance test dataset comprises a set of 1000 images. Reference bitstreams for the conformance test dataset are also provided. For each image cdvsxxx.jpg in the conformance dataset, six reference bitstreams are provided corresponding to the six descriptor lengths specified in the CDVS standard.
This document is a working draft of a specification for CDVS (compact descriptors for visual search) reference software.
The CDVS reference software is entirely written in C and C++. On Windows, it has been compiled and tested on Windows 7 Enterprise 64-bit using Visual C++ 2010 (64 bit). On Linux, it has been compiled and tested on Ubuntu 14.04 LTS (64-bit).
This document describes the Compact Descriptors for Visual Search (CDVS) Test Model (TM) 12.0 (CDVS1) (CDVS2). In particular, this document looks at the TM architecture, the operation of the informative component technologies (descriptor matching and retrieval) of the TM, and the offline or training procedures for both the normative (descriptor extraction) and the informative (descriptor matching and retrieval) component technologies of the TM.