Self-organizing integrated segmentation and recognition neural network
暂无分享,去创建一个
We present a neural network algorithm that simultaneously performs segmentation and recognition of input patterns that self-organizes to detect input pattern locations and pattern boundaries. We outline the algorithm and demonstrate this neural network architecture and algorithm on character recognition using the NIST database and report results herein. The resulting system simultaneously segments and recognizes touching characters, overlapping characters, broken characters, and noisy images with high accuracy. We also detail some of the characteristics of the algorithm on an artificial database in the appendix.
[1] James A. Pittman,et al. Recognizing Hand-Printed Letters and Digits , 1989, NIPS.
[2] Lawrence D. Jackel,et al. Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.
[3] James D. Keeler,et al. Integrated Segmentation and Recognition of Hand-Printed Numerals , 1990, NIPS.
[4] Geoffrey E. Hinton,et al. A time-delay neural network architecture for isolated word recognition , 1990, Neural Networks.