2003 · 25 citations · 27 references
ComputingComputer ScienceVision ScienceComputer VisionMachine LearningVisual PerceptionImage ClassificationObject RecognitionPattern RecognitionRepresentation LearningScene UnderstandingSupport Vector MachinesAdaptation To Illumination ChangesDynamic Scene RepresentationIllumination EffectsRobust Object RecognitionRobustness To Illumination ChangesSpatial ContiguitySupport Vector Machine ClassificationVisual Object Representation
Psychophysical studies have shown that humans actively exploit temporal information such as contiguity of images in object recognition. We have recently developed a recognition system which uses temporal contiguity to learn extensible representations of objects on-line. The system performs well both on real-world and synthetic data and shows robustness under illumination changes. In this paper, we present results which compare the proposed representation against simple image-based representations of the same complexity using Minkowski minimum distance classifiers and support vector machine classifiers. Recognition results for all classifiers show large improvements with incorporated temporal information.
27
Michael J. Swain, Dana H. Ballard · International Journal of Computer Vision · 1991 · 5.6K citations
Recognition-by-components: A theory of human image understanding.
Irving Biederman · Psychological Review · 1987 · 5.6K citations
A morphable model for the synthesis of 3D faces
Volker Blanz, Thomas Vetter · 1999 · 4.8K citations · Full text
Making Large-Scale SVM Learning Practical
Thorsten Joachims · Technical reports · 2006 · 4.3K citations · Full text
Three-dimensional computer vision: a geometric viewpoint
Choice Reviews Online · 1994 · 3.1K citations