Ch. Leung et Cy. Suen, MATCHING OF COMPLEX PATTERNS BY ENERGY MINIMIZATION, IEEE transactions on systems, man and cybernetics. Part B. Cybernetics, 28(5), 1998, pp. 712-720
Two patterns are matched by putting one on top of the other and iterat
ively moving their individual parts until most of their corresponding
parts are aligned. An energy function and a neighborhood of influence
are defined for each iteration. Initially, a large neighborhood is use
d such that the movements result in global features being coarsely ali
gned. The neighborhood size is gradually reduced in successive iterati
ons so that finer and finer details are aligned. Encouraging results h
ave been obtained when applied to match complex Chinese characters. It
has been observed that computation increases with the square of the n
umber of moving parts which is quite favorable compared with other alg
orithms. The method was applied to the recognition of handwritten Chin
ese characters, After performing the iterative matching, a set of simi
larity measures are used to measure the similarity in topological feat
ures between the input and template characters, An overall recognition
rate of 96.1% is achieved.