2002 · 77 citations · 7 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningAction RecognitionDimensionality ReductionImage ClassificationPattern RecognitionRepresentation LearningSequence LearningLogarithmic Space ComplexitySelf-organizing MapsSelf-organizing Networks
We present a self-organizing framework called the SHOSLIF-M for learning and recognizing spatiotemporal events (or patterns) from intensity image sequences. The proposed framework consists of a multiclass, multivariate discriminant analysis to automatically select the most discriminating features (MDF), a space partition tree to achieve a logarithmic retrieval time complexity for a database of n items, and a general interpolation scheme to do view inference and generalization in the MDF space based on a small number of training samples. The system is tested to recognize 28 different hand signs. The experimental results show that the learned system can achieve a 96% recognition rate for test sequences that have not been used in the training phase.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
7
Matthew Turk, Alex Pentland · Journal of Cognitive Neuroscience · 1991 · 13.8K citations · Full text
Roger S. Pinkham, S. S. Wilks · American Mathematical Monthly · 1962 · 671 citations
Trevor Darrell, Alex Pentland · 2002 · 349 citations
James W. Davis · IEE Proceedings - Vision Image and Signal Processing · 1994 · 216 citations · Full text
Robust structure from motion using motion parallax
Roberto Cipolla, Y. Okamoto, Yoshinori Kuno · 2002 · 108 citations