2D Object Recognition

Object Recognition

The files below contains demonstrations of the Pairwise 2D Object Recognition software. The software can be used to automatically construct edge based representations of large numbers of objects and then recognise and locate these objects in cluttered scenes. The technique is view based and matches more closely the processes thought to exist in the primate brain. It is more generic than the wire frame techniques demonstrated in the 3D matcher and is suitable for fast implementation on fine-grained parallel hardware.

Library toolkit
binary 1
Sun Sparc - Solaris 2
binary 2
Intel x86 - Linux 2
[1] A.C.Evans, N.A.Thacker and J.E.W.Mayhew, `The Use of Geometric Histograms for Model Based Object Recognition.' Proc. 4th. BMVC, Guildford, p 429-438 Sept. 1993.
[2] P.A.Riocreux, N.A.Thacker and R.B.Yates, `An Analysis of Pairwise Geometric Histograms for View-Based Object Recognition.' Proc. BMVC York, Sept. 1994
[3] A.P.Ashbrook, N.A.Thacker and P.I.Rockett, `Scaling Properties of Pairwise Geometric Histograms.' Proc. for SCIA95, Uppsala, Sweden, pp271, 1995.
[4] A.P.Ashbrook, P.I.Rockett and N.A.Thacker, `Multiple Shape Recognitionusing Pairwise Geometric Histogram Based Algortihms.', IEE Image Processing, Edinburgh, July 1995.
[5] A.P.Ashbrook, N.A.Thacker, P.I.Rockett and C.I.Brown, `Robust Recognitionof Scaled Shapes Using Pairwise Geometric Histograms.', Proc BMVC 95 Birmingham, 503-512, July 1995.
[6] N.A.Thacker, P.A.Riocreux, and R.B.Yates, `Assessing the Completeness Properties of Pairwise Geometric Histograms', Image and Vision Computing, 13, 5, 423-429, 1995.
[7] C.I.Brown, N.A.Thacker and R.B.Yates, ` A VLSI Architecture for Wavelet Transforms', IEE Image Processing, Edinburgh, July 1995.
the end
[Back to software]