Recognition and Learning with Polymorphic Structural Components
Mark Burge
; Johannes Kepler University, Dept. of Systems Science, Computer Vision Laboratory, Linz, Austria
Wilhelm Burger
; Johannes Kepler University, Dept. of Systems Science, Computer Vision Laboratory, Linz, Austria
Wolfgang Mayr
; Johannes Kepler University, Dept. of Systems Science, Computer Vision Laboratory, Linz, Austria
APA 6th Edition Burge, M., Burger, W. i Mayr, W. (1996). Recognition and Learning with Polymorphic Structural Components. Journal of computing and information technology, 4 (1), 39-51. Preuzeto s https://hrcak.srce.hr/150305
MLA 8th Edition Burge, Mark, et al. "Recognition and Learning with Polymorphic Structural Components." Journal of computing and information technology, vol. 4, br. 1, 1996, str. 39-51. https://hrcak.srce.hr/150305. Citirano 23.01.2021.
Chicago 17th Edition Burge, Mark, Wilhelm Burger i Wolfgang Mayr. "Recognition and Learning with Polymorphic Structural Components." Journal of computing and information technology 4, br. 1 (1996): 39-51. https://hrcak.srce.hr/150305
Harvard Burge, M., Burger, W., i Mayr, W. (1996). 'Recognition and Learning with Polymorphic Structural Components', Journal of computing and information technology, 4(1), str. 39-51. Preuzeto s: https://hrcak.srce.hr/150305 (Datum pristupa: 23.01.2021.)
Vancouver Burge M, Burger W, Mayr W. Recognition and Learning with Polymorphic Structural Components. Journal of computing and information technology [Internet]. 1996 [pristupljeno 23.01.2021.];4(1):39-51. Dostupno na: https://hrcak.srce.hr/150305
IEEE M. Burge, W. Burger i W. Mayr, "Recognition and Learning with Polymorphic Structural Components", Journal of computing and information technology, vol.4, br. 1, str. 39-51, 1996. [Online]. Dostupno na: https://hrcak.srce.hr/150305. [Citirano: 23.01.2021.]
Sažetak We address the problem of describing, recognizing, and learning generic, free-form objects in real-world scenes. For this purpose, we have developed a hybrid appearance-based approach where objects are encoded as loose collections of parts and relations between neighboring parts. The key features of this approach are: part decomposition based on local structure segmentation derived from multi-scale wavelet filters, flexible and efficient recognition by combining weak structural constraints, and learning and generalization of generic object categories (with possibly large intra-class variability) from real examples.