Neural Information Processing Systems · 1990 · 128 citations · 2 references
ComputingComputer ScienceArtificial IntelligenceComputer VisionMachine LearningImage SegmentationLetter RecognitionNeural NetworksNumeral RecognitionPattern RecognitionText SegmentationCharacter SegmentationHandwriting Letter RecognitionHandwritten Character RecognitionNeural Network-based RecognitionNumeral IdentificationPrinted Character RecognitionPrinted Text RecognitionRule-based Text Segmentation
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.
2
Backpropagation Applied to Handwritten Zip Code Recognition
Yann LeCun, Bernhard E. Boser, J. S. Denker et al. · Neural Computation · 1989 · 11.9K citations