IEEE Transactions on Neural Networks · 1993 · 61 citations · 6 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDigital Image ProcessingImage ClassificationImage ProcessingNeural NetworksObject RecognitionPattern RecognitionConvolutional Neural NetworksNeural Network-based RecognitionObject Classification
The authors describe a coarse coding technique and present simulation results illustrating its usefulness and its limitations. Simulations show that a third-order neural network can be trained to distinguish between two objects in a 4096x4096 pixel input field independent of transformations in translation, in-plane rotation, and scale in less than ten passes through the training set. Furthermore, the authors empirically determine the limits of the coarse coding technique in the position, scale, and rotation invariant (PSRI) object recognition domain.
6
Scale-space filtering: A new approach to multi-scale description
Andrew Witkin · 2005 · 1.1K citations