A novel method using neural networks for translational invariant object recognition is described in this paper. The objective is to enable the recognition of objects in any shifted position when the objects are presented to the network in only one standard location during the training procedure. With the presence of multiple or overlapped objects in the scene, translational invariant object recognition is a very difficult task. Noise corruption of the image creates another difficulty. In this paper, a novel approach is proposed to tackle this problem, using neural networks with the consideration of multiple objects and the presence of noise. This method utilizes the secondary responses activated by the backpropagation network. A confirmative network is used to obtain the object identification and location, based on these secondary responses. Experimental results were used to demonstrate the ability of this approach.
[1]
Jerome A. Feldman,et al.
Connectionist models and parallelism in high level vision
,
1985,
Comput. Vis. Graph. Image Process..
[2]
Stephen Grossberg,et al.
The ART of adaptive pattern recognition by a self-organizing neural network
,
1988,
Computer.
[3]
Kiyohiro Shikano,et al.
Modularity and scaling in large phonemic neural networks
,
1989,
IEEE Trans. Acoust. Speech Signal Process..
[4]
Geoffrey E. Hinton,et al.
Phoneme recognition using time-delay neural networks
,
1989,
IEEE Trans. Acoust. Speech Signal Process..
[5]
Kunihiko Fukushima,et al.
Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position
,
1982,
Pattern Recognit..