Abu - Mostafa and Psaltis : Recognitive
نویسنده
چکیده
Moment invariants are evaluated as a feature space for pattern recognition in terms of discrimination power and noise tolerance. The notion of complex moments is introduced as a simple and straightforward way to derive moment invariants. Through this relation, properties of complex moments are used to characterize moment invariants. Aspects of information loss, suppression, and redundancy encountered in moment invariants are investigated and significant results are derived. The behavior of moment invariants in the presence of additive noise is also described.
منابع مشابه
Abu - Mostafa and Psal Tis : Image Normalization
The role of moments in image normalization and invariant pattern recognition is addressed. The classical idea of the principal axes is analyzed and extended to a more general definition. The relationship between moment-based normalization, moment invariants, and circular harmonics is established. Invariance properties of moments, as opposed to their recognition properties, are identified using ...
متن کاملUnsupervised Learning of Models for Object Recognition
iv Acknowledgements I am most indebted to my wife, Nathalie, who was on my side throughout this entire adventure. She has been extremely supportive and has accepted a great deal of hardship and sacrifices to give me the necessary time to complete this project. This is her accomplishment as well! At Caltech, my foremost thanks go to my advisor, Pietro Perona, who was always very supportive with ...
متن کاملA Note on a Capacity Result for theHop eld Neural Network
In this note we prove, by using straightforward arguments, a stronger version of a well-known capacity result proved by Abu-Mostafa and St. Jacques. Our results states that no Hoppeld memory can have a \capacity" (in Abu-Mostafa and St. Jacques's sense) exceeding 1, thereby showing the inadequacy of their capacity notion.
متن کامل