Transformation-invariant indexing and machine discovery for computer vision
作者： Darrell Conklin
DOI:
关键词: Invariant (mathematics) 、 Machine discovery 、 Computer vision 、 Theoretical computer science 、 Euclidean geometry 、 Artificial intelligence 、 Search engine indexing 、 Computer science 、 Scene analysis 、 Concept learning
摘要: Future computer vision systems must have the ability to discover new object models. This problem can be addressed by relational concept formation systems, which structure a stream of observations into taxonomy discovered concepts. paper presents representation for images is invariant under arbitrary groups transformations. The models, also being invariant, used as indices 3D images. methodology illustrated on small in molecular scene analysis, where Euclidean transformations, are efficiently recognized cluttered scene.
aaaipress.org 参考文章(19)
W. Eric L. Grimson, Object recognition by constrained search Artificial intelligence at MIT. pp. 288- 313 ,(1991) , 10.1016/B978-0-12-266722-0.50007-5
KEVIN THOMPSON, PAT LANGLEY, Concept formation in structured domains Concept formation knowledge and experience in unsupervised learning. pp. 127- 161 ,(1991) , 10.1016/B978-1-4832-0773-5.50011-0
W.A. Woods, UNDERSTANDING SUBSUMPTION AND TAXONOMY Principles of Semantic Networks. pp. 45- 94 ,(1991) , 10.1016/B978-1-4832-0771-1.50007-2
Haim J. Wolfson, Yehezkel Lamdan, Transformation invariant indexing Geometric invariance in computer vision. pp. 335- 353 ,(1992)
Patrick H. Winston, Learning Structural Descriptions From Examples The Psychology of Computer Vision. ,(1970)
J. F. A. K. Van Benthem, The Logic of Time Springer Netherlands. ,(1983) , 10.1007/978-94-010-9868-7
Darrell Conklin, Janice Glasgow, Spatial analogy and subsumption international conference on machine learning. pp. 111- 116 ,(1992) , 10.1016/B978-1-55860-247-2.50019-X
Stephen Michael Kosslyn, Olivier Koenig, None, Wet mind : the new cognitive neuroscience ,(1992)
Joseph L. Mundy, Andrew Zisserman, Geometric invariance in computer vision MIT Press. ,(1992)
Linda G. Shapiro, Robert M. Haralock, Computer and Robot Vision Addison-Wesley Longman Publishing Co., Inc.. ,(1991)