1999 · 13 citations · 8 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDocument Image AnalysisFeature ExtractionPattern RecognitionRepresentation LearningCharacter ClassificationHandwriting RecognitionHandwritten Character RecognitionIndependent Component AnalysisIndependent Component Analysis FeaturesMultilingual Character RecognitionSignals
What are the natural features of handwritten characters and how to arrive at them automatically? We apply independent components analysis on handwritten characters. Independent components analysis extracts the underlying statistically independent signals from a mixture of them. We expect strokes to be the independent components of handwritten characters. Our findings show that stroke-like features emerge as a result of the analysis confirming the above intuition. This finding is significant since it gives automatic procedures for extracting stroke-like features from multilingual character data sets. We use these features for handwritten digit recognition using a very simple classifier. The classifier is chosen to be simple so that the quality of the input feature set can be evaluated. The recognition results indicate that the features arrived at by independent component analysis are useful.
8
Optimization by Vector Space Methods
Students Quarterly Journal · 1970 · 6.1K citations
Natural Sciences, Industrial Engineering, Design Optimization +6
A Fast Fixed-Point Algorithm for Independent Component Analysis
Aapo Hyvärinen, Erkki Oja · Neural Computation · 1997 · 3.4K citations
The “independent components” of natural scenes are edge filters
Anthony J. Bell, T. J. Sejnowski · Vision Research · 1997 · 2.3K citations
Image feature extraction by sparse coding and independent component analysis
Aapo Hyvärinen, Erkki Oja, Patrik O. Hoyer et al. · 2002 · 93 citations