Integrated Segmentation and Recognition of Hand-Printed Numerals
暂无分享,去创建一个
Neural network algorithms have proven useful for recognition of individual, segmented characters. However, their recognition accuracy has been limited by the accuracy of the underlying segmentation algorithm. Conventional, rule-based segmentation algorithms encounter difficulty if the characters are touching, broken, or noisy. The problem in these situations is that often one cannot properly segment a character until it is recognized yet one cannot properly recognize a character until it is segmented. We present here a neural network algorithm that simultaneously segments and recognizes in an integrated system. This algorithm has several novel features: it uses a supervised learning algorithm (backpropagation), but is able to take position-independent information as targets and self-organize the activities of the units in a competitive fashion to infer the positional information. We demonstrate this ability with overlapping handprinted numerals.
[1] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .
[2] Lawrence D. Jackel,et al. Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.
[3] Geoffrey E. Hinton,et al. A time-delay neural network architecture for isolated word recognition , 1990, Neural Networks.
[4] Michael I. Jordan,et al. Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..