K. Ito et al., INVARIANT OBJECT RECOGNITION BY ARTIFICIAL NEURAL-NETWORK USING FAHLMAN AND LEBIERES LEARNING ALGORITHM, IEICE transactions on fundamentals of electronics, communications and computer science, E76A(7), 1993, pp. 1267-1272
A new neural network system for object recognition is proposed which i
s invariant to translation, scaling and rotation. The system consists
of two parts. The first is a preprocessor which obtains projection fro
m the input image plane such that the projection features are translat
ion and scale invariant, and then adopts the Rapid Transform which mak
es the transformed outputs rotation invariant. The second part is a ne
ural net classifier which receives the outputs of preprocessing part a
s the input signals. The most attractive feature of this system is tha
t, by using only a simple shift invariant transformation (Rapid transf
ormation) in conjunction with the projection of the input image plane,
invariancy is achieved and the system is of reasonably small size. Ex
periments with six geometrical objects with different degrees of scali
ng and rotation shows that the proposed system performs excellent when
the neural net classifier is trained by the Cascade-correlation learn
ing algorithm proposed by Fahlman and Lebiere.(8)