To match Rl and Rr, a corresponding transform, which yields the minimum error (counted by number of errors) between Rl and Rr, needs to be searched. Note that E is a function of p, so the transform p looked for should satisfy

dis c ( R 1 , R r )= inf p { i W i C [ E i ( p ) ] }( 4.30 )

Referring back to eqs. (4.21) and (4.22), to match two relations sets X, and Xr, a set of transforms pj should be found, which make the following equation valid

dis c ( X 1 , X r )= inf p { j m V j i W ij c[ E ij ( p j ) ] }( 4.31 )

In eq. (4.31), it is assumed that n > m, where Vj are the weights for counting the different importance of relations. ...

Get Image Understanding now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.